mirror of
https://github.com/ruvnet/RuView
synced 2026-08-09 20:21:43 +00:00
feat: dual-modal WASM browser pose estimation demo (ADR-058)
Live webcam video + WiFi CSI fusion for real-time pose estimation. Two parallel CNN pipelines (ruvector-cnn-wasm) with attention-weighted fusion and dynamic confidence gating. Three modes: Dual, Video-only, CSI-only. Includes pre-built WASM package (~52KB) for browser deployment. - ADR-058: Dual-modal architecture design - ui/pose-fusion.html: Main demo page with dark theme UI - 7 JS modules: video-capture, csi-simulator, cnn-embedder, fusion-engine, pose-decoder, canvas-renderer, main orchestrator - Pre-built ruvector-cnn-wasm WASM package for browser - CSI heatmap, embedding space visualization, latency metrics - WebSocket support for live ESP32 CSI data - Navigation link added to main dashboard Co-Authored-By: claude-flow <ruv@ruv.net>
This commit is contained in:
ruv
@@ -0,0 +1,247 @@
|
||||
/**
|
||||
* CanvasRenderer — Renders skeleton overlay on video, CSI heatmap,
|
||||
* embedding space visualization, and fusion confidence bars.
|
||||
*/
|
||||
|
||||
import { SKELETON_CONNECTIONS } from './pose-decoder.js';
|
||||
|
||||
export class CanvasRenderer {
|
||||
constructor() {
|
||||
this.colors = {
|
||||
joint: '#00d878',
|
||||
jointGlow: 'rgba(0, 216, 120, 0.4)',
|
||||
limb: '#3eff8a',
|
||||
limbGlow: 'rgba(62, 255, 138, 0.15)',
|
||||
csiJoint: '#ffb020',
|
||||
csiLimb: '#ffc850',
|
||||
fused: '#00e5ff',
|
||||
confidence: 'rgba(255,255,255,0.3)',
|
||||
videoEmb: '#00e5ff',
|
||||
csiEmb: '#ffb020',
|
||||
fusedEmb: '#00d878',
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
* Draw skeleton overlay on the video canvas
|
||||
* @param {CanvasRenderingContext2D} ctx
|
||||
* @param {Array<{x,y,confidence}>} keypoints - Normalized [0,1] coordinates
|
||||
* @param {number} width - Canvas width
|
||||
* @param {number} height - Canvas height
|
||||
* @param {object} opts
|
||||
*/
|
||||
drawSkeleton(ctx, keypoints, width, height, opts = {}) {
|
||||
const minConf = opts.minConfidence || 0.3;
|
||||
const color = opts.color || 'green';
|
||||
const jointColor = color === 'amber' ? this.colors.csiJoint : this.colors.joint;
|
||||
const limbColor = color === 'amber' ? this.colors.csiLimb : this.colors.limb;
|
||||
const glowColor = color === 'amber' ? 'rgba(255,176,32,0.4)' : this.colors.jointGlow;
|
||||
|
||||
ctx.clearRect(0, 0, width, height);
|
||||
|
||||
if (!keypoints || keypoints.length === 0) return;
|
||||
|
||||
// Draw limbs first (behind joints)
|
||||
ctx.lineWidth = 3;
|
||||
ctx.lineCap = 'round';
|
||||
|
||||
for (const [i, j] of SKELETON_CONNECTIONS) {
|
||||
const kpA = keypoints[i];
|
||||
const kpB = keypoints[j];
|
||||
if (!kpA || !kpB || kpA.confidence < minConf || kpB.confidence < minConf) continue;
|
||||
|
||||
const ax = kpA.x * width, ay = kpA.y * height;
|
||||
const bx = kpB.x * width, by = kpB.y * height;
|
||||
const avgConf = (kpA.confidence + kpB.confidence) / 2;
|
||||
|
||||
// Glow
|
||||
ctx.strokeStyle = this.colors.limbGlow;
|
||||
ctx.lineWidth = 8;
|
||||
ctx.globalAlpha = avgConf * 0.4;
|
||||
ctx.beginPath();
|
||||
ctx.moveTo(ax, ay);
|
||||
ctx.lineTo(bx, by);
|
||||
ctx.stroke();
|
||||
|
||||
// Main line
|
||||
ctx.strokeStyle = limbColor;
|
||||
ctx.lineWidth = 2.5;
|
||||
ctx.globalAlpha = avgConf;
|
||||
ctx.beginPath();
|
||||
ctx.moveTo(ax, ay);
|
||||
ctx.lineTo(bx, by);
|
||||
ctx.stroke();
|
||||
}
|
||||
|
||||
// Draw joints
|
||||
ctx.globalAlpha = 1;
|
||||
for (const kp of keypoints) {
|
||||
if (!kp || kp.confidence < minConf) continue;
|
||||
|
||||
const x = kp.x * width;
|
||||
const y = kp.y * height;
|
||||
const r = 3 + kp.confidence * 3;
|
||||
|
||||
// Glow
|
||||
ctx.beginPath();
|
||||
ctx.arc(x, y, r + 4, 0, Math.PI * 2);
|
||||
ctx.fillStyle = glowColor;
|
||||
ctx.globalAlpha = kp.confidence * 0.6;
|
||||
ctx.fill();
|
||||
|
||||
// Joint dot
|
||||
ctx.beginPath();
|
||||
ctx.arc(x, y, r, 0, Math.PI * 2);
|
||||
ctx.fillStyle = jointColor;
|
||||
ctx.globalAlpha = kp.confidence;
|
||||
ctx.fill();
|
||||
|
||||
// White center
|
||||
ctx.beginPath();
|
||||
ctx.arc(x, y, r * 0.4, 0, Math.PI * 2);
|
||||
ctx.fillStyle = '#fff';
|
||||
ctx.globalAlpha = kp.confidence * 0.8;
|
||||
ctx.fill();
|
||||
}
|
||||
|
||||
ctx.globalAlpha = 1;
|
||||
|
||||
// Confidence label
|
||||
if (opts.label) {
|
||||
ctx.font = '11px "JetBrains Mono", monospace';
|
||||
ctx.fillStyle = jointColor;
|
||||
ctx.globalAlpha = 0.8;
|
||||
ctx.fillText(opts.label, 8, height - 8);
|
||||
ctx.globalAlpha = 1;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Draw CSI amplitude heatmap
|
||||
* @param {CanvasRenderingContext2D} ctx
|
||||
* @param {{ data: Float32Array, width: number, height: number }} heatmap
|
||||
* @param {number} canvasW
|
||||
* @param {number} canvasH
|
||||
*/
|
||||
drawCsiHeatmap(ctx, heatmap, canvasW, canvasH) {
|
||||
ctx.clearRect(0, 0, canvasW, canvasH);
|
||||
|
||||
if (!heatmap || !heatmap.data || heatmap.height < 2) {
|
||||
ctx.fillStyle = '#0a0e18';
|
||||
ctx.fillRect(0, 0, canvasW, canvasH);
|
||||
ctx.font = '11px "JetBrains Mono", monospace';
|
||||
ctx.fillStyle = 'rgba(255,255,255,0.3)';
|
||||
ctx.fillText('Waiting for CSI data...', 8, canvasH / 2);
|
||||
return;
|
||||
}
|
||||
|
||||
const { data, width: dw, height: dh } = heatmap;
|
||||
const cellW = canvasW / dw;
|
||||
const cellH = canvasH / dh;
|
||||
|
||||
for (let y = 0; y < dh; y++) {
|
||||
for (let x = 0; x < dw; x++) {
|
||||
const val = Math.min(1, Math.max(0, data[y * dw + x]));
|
||||
ctx.fillStyle = this._heatmapColor(val);
|
||||
ctx.fillRect(x * cellW, y * cellH, cellW + 0.5, cellH + 0.5);
|
||||
}
|
||||
}
|
||||
|
||||
// Axis labels
|
||||
ctx.font = '9px "JetBrains Mono", monospace';
|
||||
ctx.fillStyle = 'rgba(255,255,255,0.4)';
|
||||
ctx.fillText('Subcarrier →', 4, canvasH - 4);
|
||||
ctx.save();
|
||||
ctx.translate(canvasW - 4, canvasH - 4);
|
||||
ctx.rotate(-Math.PI / 2);
|
||||
ctx.fillText('Time ↑', 0, 0);
|
||||
ctx.restore();
|
||||
}
|
||||
|
||||
/**
|
||||
* Draw embedding space 2D projection
|
||||
* @param {CanvasRenderingContext2D} ctx
|
||||
* @param {{ video: Array, csi: Array, fused: Array }} points
|
||||
* @param {number} w
|
||||
* @param {number} h
|
||||
*/
|
||||
drawEmbeddingSpace(ctx, points, w, h) {
|
||||
ctx.fillStyle = '#050810';
|
||||
ctx.fillRect(0, 0, w, h);
|
||||
|
||||
// Grid
|
||||
ctx.strokeStyle = 'rgba(255,255,255,0.05)';
|
||||
ctx.lineWidth = 0.5;
|
||||
for (let i = 0; i <= 4; i++) {
|
||||
const x = (i / 4) * w;
|
||||
ctx.beginPath(); ctx.moveTo(x, 0); ctx.lineTo(x, h); ctx.stroke();
|
||||
const y = (i / 4) * h;
|
||||
ctx.beginPath(); ctx.moveTo(0, y); ctx.lineTo(w, y); ctx.stroke();
|
||||
}
|
||||
|
||||
// Axes
|
||||
ctx.strokeStyle = 'rgba(255,255,255,0.1)';
|
||||
ctx.lineWidth = 1;
|
||||
ctx.beginPath(); ctx.moveTo(w / 2, 0); ctx.lineTo(w / 2, h); ctx.stroke();
|
||||
ctx.beginPath(); ctx.moveTo(0, h / 2); ctx.lineTo(w, h / 2); ctx.stroke();
|
||||
|
||||
const drawPoints = (pts, color, size) => {
|
||||
if (!pts || pts.length === 0) return;
|
||||
const len = pts.length;
|
||||
for (let i = 0; i < len; i++) {
|
||||
const p = pts[i];
|
||||
if (!p) continue;
|
||||
const age = 1 - (i / len) * 0.7; // Fade older points
|
||||
const px = w / 2 + p[0] * w * 0.35;
|
||||
const py = h / 2 + p[1] * h * 0.35;
|
||||
|
||||
if (px < 0 || px > w || py < 0 || py > h) continue;
|
||||
|
||||
ctx.beginPath();
|
||||
ctx.arc(px, py, size, 0, Math.PI * 2);
|
||||
ctx.fillStyle = color;
|
||||
ctx.globalAlpha = age * 0.7;
|
||||
ctx.fill();
|
||||
}
|
||||
};
|
||||
|
||||
drawPoints(points.video, this.colors.videoEmb, 3);
|
||||
drawPoints(points.csi, this.colors.csiEmb, 3);
|
||||
drawPoints(points.fused, this.colors.fusedEmb, 4);
|
||||
ctx.globalAlpha = 1;
|
||||
|
||||
// Legend
|
||||
ctx.font = '9px "JetBrains Mono", monospace';
|
||||
const legends = [
|
||||
{ color: this.colors.videoEmb, label: 'Video' },
|
||||
{ color: this.colors.csiEmb, label: 'CSI' },
|
||||
{ color: this.colors.fusedEmb, label: 'Fused' },
|
||||
];
|
||||
legends.forEach((l, i) => {
|
||||
const ly = 12 + i * 14;
|
||||
ctx.fillStyle = l.color;
|
||||
ctx.beginPath();
|
||||
ctx.arc(10, ly - 3, 3, 0, Math.PI * 2);
|
||||
ctx.fill();
|
||||
ctx.fillStyle = 'rgba(255,255,255,0.5)';
|
||||
ctx.fillText(l.label, 18, ly);
|
||||
});
|
||||
}
|
||||
|
||||
_heatmapColor(val) {
|
||||
// Dark blue → cyan → green → yellow → red
|
||||
if (val < 0.25) {
|
||||
const t = val / 0.25;
|
||||
return `rgb(${Math.floor(t * 20)}, ${Math.floor(20 + t * 60)}, ${Math.floor(60 + t * 100)})`;
|
||||
} else if (val < 0.5) {
|
||||
const t = (val - 0.25) / 0.25;
|
||||
return `rgb(${Math.floor(20 + t * 20)}, ${Math.floor(80 + t * 100)}, ${Math.floor(160 - t * 60)})`;
|
||||
} else if (val < 0.75) {
|
||||
const t = (val - 0.5) / 0.25;
|
||||
return `rgb(${Math.floor(40 + t * 180)}, ${Math.floor(180 + t * 75)}, ${Math.floor(100 - t * 80)})`;
|
||||
} else {
|
||||
const t = (val - 0.75) / 0.25;
|
||||
return `rgb(${Math.floor(220 + t * 35)}, ${Math.floor(255 - t * 120)}, ${Math.floor(20 - t * 20)})`;
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,226 @@
|
||||
/**
|
||||
* CNN Embedder — Lightweight MobileNet-V3-style feature extractor.
|
||||
*
|
||||
* Architecture mirrors ruvector-cnn: Conv2D → BatchNorm → ReLU → Pool → Project → L2 Normalize
|
||||
* Uses pre-seeded random weights (deterministic). When ruvector-cnn-wasm is available,
|
||||
* transparently delegates to the WASM implementation.
|
||||
*
|
||||
* Two instances are created: one for video frames, one for CSI pseudo-images.
|
||||
*/
|
||||
|
||||
// Seeded PRNG for deterministic weight initialization
|
||||
function mulberry32(seed) {
|
||||
return function() {
|
||||
let t = (seed += 0x6D2B79F5);
|
||||
t = Math.imul(t ^ (t >>> 15), t | 1);
|
||||
t ^= t + Math.imul(t ^ (t >>> 7), t | 61);
|
||||
return ((t ^ (t >>> 14)) >>> 0) / 4294967296;
|
||||
};
|
||||
}
|
||||
|
||||
export class CnnEmbedder {
|
||||
/**
|
||||
* @param {object} opts
|
||||
* @param {number} opts.inputSize - Square input dimension (default 56 for speed)
|
||||
* @param {number} opts.embeddingDim - Output embedding dimension (default 128)
|
||||
* @param {boolean} opts.normalize - L2 normalize output
|
||||
* @param {number} opts.seed - PRNG seed for weight init
|
||||
*/
|
||||
constructor(opts = {}) {
|
||||
this.inputSize = opts.inputSize || 56;
|
||||
this.embeddingDim = opts.embeddingDim || 128;
|
||||
this.normalize = opts.normalize !== false;
|
||||
this.wasmEmbedder = null;
|
||||
|
||||
// Initialize weights with deterministic PRNG
|
||||
const rng = mulberry32(opts.seed || 42);
|
||||
const randRange = (lo, hi) => lo + rng() * (hi - lo);
|
||||
|
||||
// Conv 3x3: 3 input channels → 16 output channels
|
||||
this.convWeights = new Float32Array(3 * 3 * 3 * 16);
|
||||
for (let i = 0; i < this.convWeights.length; i++) {
|
||||
this.convWeights[i] = randRange(-0.15, 0.15);
|
||||
}
|
||||
|
||||
// BatchNorm params (16 channels)
|
||||
this.bnGamma = new Float32Array(16).fill(1.0);
|
||||
this.bnBeta = new Float32Array(16).fill(0.0);
|
||||
this.bnMean = new Float32Array(16).fill(0.0);
|
||||
this.bnVar = new Float32Array(16).fill(1.0);
|
||||
|
||||
// Projection: 16 → embeddingDim
|
||||
this.projWeights = new Float32Array(16 * this.embeddingDim);
|
||||
for (let i = 0; i < this.projWeights.length; i++) {
|
||||
this.projWeights[i] = randRange(-0.1, 0.1);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Try to load WASM embedder from ruvector-cnn-wasm package
|
||||
* @param {string} wasmPath - Path to the WASM package directory
|
||||
*/
|
||||
async tryLoadWasm(wasmPath) {
|
||||
try {
|
||||
const mod = await import(`${wasmPath}/ruvector_cnn_wasm.js`);
|
||||
await mod.default();
|
||||
const config = new mod.EmbedderConfig();
|
||||
config.input_size = this.inputSize;
|
||||
config.embedding_dim = this.embeddingDim;
|
||||
config.normalize = this.normalize;
|
||||
this.wasmEmbedder = new mod.WasmCnnEmbedder(config);
|
||||
console.log('[CNN] WASM embedder loaded successfully');
|
||||
return true;
|
||||
} catch (e) {
|
||||
console.log('[CNN] WASM not available, using JS fallback:', e.message);
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Extract embedding from RGB image data
|
||||
* @param {Uint8Array} rgbData - RGB pixel data (H*W*3)
|
||||
* @param {number} width
|
||||
* @param {number} height
|
||||
* @returns {Float32Array} embedding vector
|
||||
*/
|
||||
extract(rgbData, width, height) {
|
||||
if (this.wasmEmbedder) {
|
||||
try {
|
||||
const result = this.wasmEmbedder.extract(rgbData, width, height);
|
||||
return new Float32Array(result);
|
||||
} catch (_) { /* fallback to JS */ }
|
||||
}
|
||||
return this._extractJS(rgbData, width, height);
|
||||
}
|
||||
|
||||
_extractJS(rgbData, width, height) {
|
||||
// 1. Resize to inputSize × inputSize if needed
|
||||
const sz = this.inputSize;
|
||||
let input;
|
||||
if (width === sz && height === sz) {
|
||||
input = new Float32Array(rgbData.length);
|
||||
for (let i = 0; i < rgbData.length; i++) input[i] = rgbData[i] / 255.0;
|
||||
} else {
|
||||
input = this._resize(rgbData, width, height, sz, sz);
|
||||
}
|
||||
|
||||
// 2. ImageNet normalization
|
||||
const mean = [0.485, 0.456, 0.406];
|
||||
const std = [0.229, 0.224, 0.225];
|
||||
const pixels = sz * sz;
|
||||
for (let i = 0; i < pixels; i++) {
|
||||
input[i * 3] = (input[i * 3] - mean[0]) / std[0];
|
||||
input[i * 3 + 1] = (input[i * 3 + 1] - mean[1]) / std[1];
|
||||
input[i * 3 + 2] = (input[i * 3 + 2] - mean[2]) / std[2];
|
||||
}
|
||||
|
||||
// 3. Conv2D 3x3 (3 → 16 channels)
|
||||
const convOut = this._conv2d3x3(input, sz, sz, 3, 16);
|
||||
|
||||
// 4. BatchNorm
|
||||
this._batchNorm(convOut, 16);
|
||||
|
||||
// 5. ReLU
|
||||
for (let i = 0; i < convOut.length; i++) {
|
||||
if (convOut[i] < 0) convOut[i] = 0;
|
||||
}
|
||||
|
||||
// 6. Global average pooling → 16-dim
|
||||
const outH = sz - 2, outW = sz - 2;
|
||||
const pooled = new Float32Array(16);
|
||||
const spatial = outH * outW;
|
||||
for (let i = 0; i < spatial; i++) {
|
||||
for (let c = 0; c < 16; c++) {
|
||||
pooled[c] += convOut[i * 16 + c];
|
||||
}
|
||||
}
|
||||
for (let c = 0; c < 16; c++) pooled[c] /= spatial;
|
||||
|
||||
// 7. Linear projection → embeddingDim
|
||||
const emb = new Float32Array(this.embeddingDim);
|
||||
for (let o = 0; o < this.embeddingDim; o++) {
|
||||
let sum = 0;
|
||||
for (let i = 0; i < 16; i++) {
|
||||
sum += pooled[i] * this.projWeights[i * this.embeddingDim + o];
|
||||
}
|
||||
emb[o] = sum;
|
||||
}
|
||||
|
||||
// 8. L2 normalize
|
||||
if (this.normalize) {
|
||||
let norm = 0;
|
||||
for (let i = 0; i < emb.length; i++) norm += emb[i] * emb[i];
|
||||
norm = Math.sqrt(norm);
|
||||
if (norm > 1e-8) {
|
||||
for (let i = 0; i < emb.length; i++) emb[i] /= norm;
|
||||
}
|
||||
}
|
||||
|
||||
return emb;
|
||||
}
|
||||
|
||||
_conv2d3x3(input, H, W, Cin, Cout) {
|
||||
const outH = H - 2, outW = W - 2;
|
||||
const output = new Float32Array(outH * outW * Cout);
|
||||
for (let y = 0; y < outH; y++) {
|
||||
for (let x = 0; x < outW; x++) {
|
||||
for (let co = 0; co < Cout; co++) {
|
||||
let sum = 0;
|
||||
for (let ky = 0; ky < 3; ky++) {
|
||||
for (let kx = 0; kx < 3; kx++) {
|
||||
for (let ci = 0; ci < Cin; ci++) {
|
||||
const px = ((y + ky) * W + (x + kx)) * Cin + ci;
|
||||
const wt = (((ky * 3 + kx) * Cin) + ci) * Cout + co;
|
||||
sum += input[px] * this.convWeights[wt];
|
||||
}
|
||||
}
|
||||
}
|
||||
output[(y * outW + x) * Cout + co] = sum;
|
||||
}
|
||||
}
|
||||
}
|
||||
return output;
|
||||
}
|
||||
|
||||
_batchNorm(data, channels) {
|
||||
const spatial = data.length / channels;
|
||||
for (let i = 0; i < spatial; i++) {
|
||||
for (let c = 0; c < channels; c++) {
|
||||
const idx = i * channels + c;
|
||||
data[idx] = this.bnGamma[c] * (data[idx] - this.bnMean[c]) / Math.sqrt(this.bnVar[c] + 1e-5) + this.bnBeta[c];
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
_resize(rgbData, srcW, srcH, dstW, dstH) {
|
||||
const output = new Float32Array(dstW * dstH * 3);
|
||||
const xRatio = srcW / dstW;
|
||||
const yRatio = srcH / dstH;
|
||||
for (let y = 0; y < dstH; y++) {
|
||||
for (let x = 0; x < dstW; x++) {
|
||||
const sx = Math.min(Math.floor(x * xRatio), srcW - 1);
|
||||
const sy = Math.min(Math.floor(y * yRatio), srcH - 1);
|
||||
const srcIdx = (sy * srcW + sx) * 3;
|
||||
const dstIdx = (y * dstW + x) * 3;
|
||||
output[dstIdx] = rgbData[srcIdx] / 255.0;
|
||||
output[dstIdx + 1] = rgbData[srcIdx + 1] / 255.0;
|
||||
output[dstIdx + 2] = rgbData[srcIdx + 2] / 255.0;
|
||||
}
|
||||
}
|
||||
return output;
|
||||
}
|
||||
|
||||
/** Cosine similarity between two embeddings */
|
||||
static cosineSimilarity(a, b) {
|
||||
let dot = 0, normA = 0, normB = 0;
|
||||
for (let i = 0; i < a.length; i++) {
|
||||
dot += a[i] * b[i];
|
||||
normA += a[i] * a[i];
|
||||
normB += b[i] * b[i];
|
||||
}
|
||||
normA = Math.sqrt(normA);
|
||||
normB = Math.sqrt(normB);
|
||||
if (normA < 1e-8 || normB < 1e-8) return 0;
|
||||
return dot / (normA * normB);
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,242 @@
|
||||
/**
|
||||
* CSI Simulator — Generates realistic WiFi Channel State Information data.
|
||||
*
|
||||
* In live mode, connects to the sensing server via WebSocket.
|
||||
* In demo mode, generates synthetic CSI that correlates with detected motion.
|
||||
*
|
||||
* Outputs: 3-channel pseudo-image (amplitude, phase, temporal diff)
|
||||
* matching the ADR-018 frame format expectations.
|
||||
*/
|
||||
|
||||
export class CsiSimulator {
|
||||
constructor(opts = {}) {
|
||||
this.subcarriers = opts.subcarriers || 52; // 802.11n HT20
|
||||
this.timeWindow = opts.timeWindow || 56; // frames in sliding window
|
||||
this.mode = 'demo'; // 'demo' | 'live'
|
||||
this.ws = null;
|
||||
|
||||
// Circular buffer for CSI frames
|
||||
this.amplitudeBuffer = [];
|
||||
this.phaseBuffer = [];
|
||||
this.frameCount = 0;
|
||||
|
||||
// Noise parameters
|
||||
this._rng = this._mulberry32(opts.seed || 7);
|
||||
this._noiseState = new Float32Array(this.subcarriers);
|
||||
this._baseAmplitude = new Float32Array(this.subcarriers);
|
||||
this._basePhase = new Float32Array(this.subcarriers);
|
||||
|
||||
// Initialize base CSI profile (empty room)
|
||||
for (let i = 0; i < this.subcarriers; i++) {
|
||||
this._baseAmplitude[i] = 0.5 + 0.3 * Math.sin(i * 0.12);
|
||||
this._basePhase[i] = (i / this.subcarriers) * Math.PI * 2;
|
||||
}
|
||||
|
||||
// Person influence (updated from video motion)
|
||||
this.personPresence = 0;
|
||||
this.personX = 0.5;
|
||||
this.personY = 0.5;
|
||||
this.personMotion = 0;
|
||||
}
|
||||
|
||||
/**
|
||||
* Connect to live sensing server WebSocket
|
||||
* @param {string} url - WebSocket URL (e.g. ws://localhost:3030/ws/csi)
|
||||
*/
|
||||
async connectLive(url) {
|
||||
return new Promise((resolve) => {
|
||||
try {
|
||||
this.ws = new WebSocket(url);
|
||||
this.ws.binaryType = 'arraybuffer';
|
||||
this.ws.onmessage = (evt) => this._handleLiveFrame(evt.data);
|
||||
this.ws.onopen = () => { this.mode = 'live'; resolve(true); };
|
||||
this.ws.onerror = () => resolve(false);
|
||||
this.ws.onclose = () => { this.mode = 'demo'; };
|
||||
// Timeout after 3s
|
||||
setTimeout(() => { if (this.mode !== 'live') resolve(false); }, 3000);
|
||||
} catch {
|
||||
resolve(false);
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
disconnect() {
|
||||
if (this.ws) { this.ws.close(); this.ws = null; }
|
||||
this.mode = 'demo';
|
||||
}
|
||||
|
||||
get isLive() { return this.mode === 'live'; }
|
||||
|
||||
/**
|
||||
* Update person state from video detection (for correlated demo data)
|
||||
*/
|
||||
updatePersonState(presence, x, y, motion) {
|
||||
this.personPresence = presence;
|
||||
this.personX = x;
|
||||
this.personY = y;
|
||||
this.personMotion = motion;
|
||||
}
|
||||
|
||||
/**
|
||||
* Generate next CSI frame (demo mode) or return latest live frame
|
||||
* @param {number} elapsed - Time in seconds
|
||||
* @returns {{ amplitude: Float32Array, phase: Float32Array, snr: number }}
|
||||
*/
|
||||
nextFrame(elapsed) {
|
||||
const amp = new Float32Array(this.subcarriers);
|
||||
const phase = new Float32Array(this.subcarriers);
|
||||
|
||||
if (this.mode === 'live' && this._liveAmplitude) {
|
||||
amp.set(this._liveAmplitude);
|
||||
phase.set(this._livePhase);
|
||||
} else {
|
||||
this._generateDemoFrame(amp, phase, elapsed);
|
||||
}
|
||||
|
||||
// Push to circular buffer
|
||||
this.amplitudeBuffer.push(new Float32Array(amp));
|
||||
this.phaseBuffer.push(new Float32Array(phase));
|
||||
if (this.amplitudeBuffer.length > this.timeWindow) {
|
||||
this.amplitudeBuffer.shift();
|
||||
this.phaseBuffer.shift();
|
||||
}
|
||||
|
||||
// SNR estimate
|
||||
let signalPower = 0, noisePower = 0;
|
||||
for (let i = 0; i < this.subcarriers; i++) {
|
||||
signalPower += amp[i] * amp[i];
|
||||
noisePower += this._noiseState[i] * this._noiseState[i];
|
||||
}
|
||||
const snr = noisePower > 0 ? 10 * Math.log10(signalPower / noisePower) : 30;
|
||||
|
||||
this.frameCount++;
|
||||
return { amplitude: amp, phase, snr: Math.max(0, Math.min(40, snr)) };
|
||||
}
|
||||
|
||||
/**
|
||||
* Build 3-channel pseudo-image for CNN input
|
||||
* @param {number} targetSize - Output image dimension (square)
|
||||
* @returns {Uint8Array} RGB data (targetSize * targetSize * 3)
|
||||
*/
|
||||
buildPseudoImage(targetSize = 56) {
|
||||
const buf = this.amplitudeBuffer;
|
||||
const pBuf = this.phaseBuffer;
|
||||
const frames = buf.length;
|
||||
if (frames < 2) {
|
||||
return new Uint8Array(targetSize * targetSize * 3);
|
||||
}
|
||||
|
||||
const rgb = new Uint8Array(targetSize * targetSize * 3);
|
||||
|
||||
for (let y = 0; y < targetSize; y++) {
|
||||
const fi = Math.min(Math.floor(y / targetSize * frames), frames - 1);
|
||||
for (let x = 0; x < targetSize; x++) {
|
||||
const si = Math.min(Math.floor(x / targetSize * this.subcarriers), this.subcarriers - 1);
|
||||
const idx = (y * targetSize + x) * 3;
|
||||
|
||||
// R: Amplitude (normalized to 0-255)
|
||||
const ampVal = buf[fi][si];
|
||||
rgb[idx] = Math.min(255, Math.max(0, Math.floor(ampVal * 255)));
|
||||
|
||||
// G: Phase (wrapped to 0-255)
|
||||
const phaseVal = (pBuf[fi][si] % (2 * Math.PI) + 2 * Math.PI) % (2 * Math.PI);
|
||||
rgb[idx + 1] = Math.floor(phaseVal / (2 * Math.PI) * 255);
|
||||
|
||||
// B: Temporal difference
|
||||
if (fi > 0) {
|
||||
const diff = Math.abs(buf[fi][si] - buf[fi - 1][si]);
|
||||
rgb[idx + 2] = Math.min(255, Math.floor(diff * 500));
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return rgb;
|
||||
}
|
||||
|
||||
/**
|
||||
* Get heatmap data for visualization
|
||||
* @returns {{ data: Float32Array, width: number, height: number }}
|
||||
*/
|
||||
getHeatmapData() {
|
||||
const frames = this.amplitudeBuffer.length;
|
||||
const w = this.subcarriers;
|
||||
const h = Math.min(frames, this.timeWindow);
|
||||
const data = new Float32Array(w * h);
|
||||
for (let y = 0; y < h; y++) {
|
||||
const fi = frames - h + y;
|
||||
if (fi >= 0 && fi < frames) {
|
||||
for (let x = 0; x < w; x++) {
|
||||
data[y * w + x] = this.amplitudeBuffer[fi][x];
|
||||
}
|
||||
}
|
||||
}
|
||||
return { data, width: w, height: h };
|
||||
}
|
||||
|
||||
// === Private ===
|
||||
|
||||
_generateDemoFrame(amp, phase, elapsed) {
|
||||
const rng = this._rng;
|
||||
const presence = this.personPresence;
|
||||
const motion = this.personMotion;
|
||||
const px = this.personX;
|
||||
|
||||
for (let i = 0; i < this.subcarriers; i++) {
|
||||
// Base CSI profile (frequency-selective channel)
|
||||
let a = this._baseAmplitude[i];
|
||||
let p = this._basePhase[i] + elapsed * 0.05;
|
||||
|
||||
// Environmental noise (correlated across subcarriers)
|
||||
this._noiseState[i] = 0.95 * this._noiseState[i] + 0.05 * (rng() * 2 - 1) * 0.03;
|
||||
a += this._noiseState[i];
|
||||
|
||||
// Person-induced CSI perturbation
|
||||
if (presence > 0.1) {
|
||||
// Subcarrier-dependent body reflection (Fresnel zone model)
|
||||
const freqOffset = (i - this.subcarriers * px) / (this.subcarriers * 0.3);
|
||||
const bodyReflection = presence * 0.25 * Math.exp(-freqOffset * freqOffset);
|
||||
|
||||
// Motion causes amplitude fluctuation
|
||||
const motionEffect = motion * 0.15 * Math.sin(elapsed * 3.5 + i * 0.3);
|
||||
|
||||
// Breathing modulation (0.2-0.3 Hz)
|
||||
const breathing = presence * 0.02 * Math.sin(elapsed * 1.5 + i * 0.05);
|
||||
|
||||
a += bodyReflection + motionEffect + breathing;
|
||||
p += presence * 0.4 * Math.sin(elapsed * 2.1 + i * 0.15);
|
||||
}
|
||||
|
||||
amp[i] = Math.max(0, Math.min(1, a));
|
||||
phase[i] = p;
|
||||
}
|
||||
}
|
||||
|
||||
_handleLiveFrame(data) {
|
||||
const view = new DataView(data);
|
||||
// Check ADR-018 magic: 0xC5110001
|
||||
if (data.byteLength < 20) return;
|
||||
const magic = view.getUint32(0, true);
|
||||
if (magic !== 0xC5110001) return;
|
||||
|
||||
const numSub = Math.min(view.getUint16(8, true), this.subcarriers);
|
||||
this._liveAmplitude = new Float32Array(this.subcarriers);
|
||||
this._livePhase = new Float32Array(this.subcarriers);
|
||||
|
||||
const headerSize = 20;
|
||||
for (let i = 0; i < numSub && (headerSize + i * 4 + 3) < data.byteLength; i++) {
|
||||
const real = view.getInt16(headerSize + i * 4, true);
|
||||
const imag = view.getInt16(headerSize + i * 4 + 2, true);
|
||||
this._liveAmplitude[i] = Math.sqrt(real * real + imag * imag) / 2048;
|
||||
this._livePhase[i] = Math.atan2(imag, real);
|
||||
}
|
||||
}
|
||||
|
||||
_mulberry32(seed) {
|
||||
return function() {
|
||||
let t = (seed += 0x6D2B79F5);
|
||||
t = Math.imul(t ^ (t >>> 15), t | 1);
|
||||
t ^= t + Math.imul(t ^ (t >>> 7), t | 61);
|
||||
return ((t ^ (t >>> 14)) >>> 0) / 4294967296;
|
||||
};
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,166 @@
|
||||
/**
|
||||
* FusionEngine — Attention-weighted dual-modal embedding fusion.
|
||||
*
|
||||
* Combines visual (camera) and CSI (WiFi) embeddings with dynamic
|
||||
* confidence gating based on signal quality.
|
||||
*/
|
||||
|
||||
export class FusionEngine {
|
||||
/**
|
||||
* @param {number} embeddingDim
|
||||
*/
|
||||
constructor(embeddingDim = 128) {
|
||||
this.embeddingDim = embeddingDim;
|
||||
|
||||
// Learnable attention weights (initialized to balanced 0.5)
|
||||
// In production, these would be loaded from trained JSON
|
||||
this.attentionWeights = new Float32Array(embeddingDim).fill(0.5);
|
||||
|
||||
// Dynamic modality confidence [0, 1]
|
||||
this.videoConfidence = 1.0;
|
||||
this.csiConfidence = 0.0;
|
||||
this.fusedConfidence = 0.5;
|
||||
|
||||
// Smoothing for confidence transitions
|
||||
this._smoothAlpha = 0.85;
|
||||
|
||||
// Embedding history for visualization
|
||||
this.recentVideoEmbeddings = [];
|
||||
this.recentCsiEmbeddings = [];
|
||||
this.recentFusedEmbeddings = [];
|
||||
this.maxHistory = 50;
|
||||
}
|
||||
|
||||
/**
|
||||
* Update quality-based confidence scores
|
||||
* @param {number} videoBrightness - [0,1] video brightness quality
|
||||
* @param {number} videoMotion - [0,1] motion detected
|
||||
* @param {number} csiSnr - CSI signal-to-noise ratio in dB
|
||||
* @param {boolean} csiActive - Whether CSI source is connected
|
||||
*/
|
||||
updateConfidence(videoBrightness, videoMotion, csiSnr, csiActive) {
|
||||
// Video confidence: drops with low brightness, boosted by motion
|
||||
let vc = 0;
|
||||
if (videoBrightness > 0.05) {
|
||||
vc = Math.min(1, videoBrightness * 1.5) * 0.7 + Math.min(1, videoMotion * 3) * 0.3;
|
||||
}
|
||||
|
||||
// CSI confidence: based on SNR and connection status
|
||||
let cc = 0;
|
||||
if (csiActive) {
|
||||
cc = Math.min(1, csiSnr / 25); // 25dB = full confidence
|
||||
}
|
||||
|
||||
// Smooth transitions
|
||||
this.videoConfidence = this._smoothAlpha * this.videoConfidence + (1 - this._smoothAlpha) * vc;
|
||||
this.csiConfidence = this._smoothAlpha * this.csiConfidence + (1 - this._smoothAlpha) * cc;
|
||||
|
||||
// Fused confidence is the max of either (fusion can only help)
|
||||
this.fusedConfidence = Math.min(1, Math.sqrt(
|
||||
this.videoConfidence * this.videoConfidence + this.csiConfidence * this.csiConfidence
|
||||
));
|
||||
}
|
||||
|
||||
/**
|
||||
* Fuse video and CSI embeddings
|
||||
* @param {Float32Array|null} videoEmb - Visual embedding (or null if video-off)
|
||||
* @param {Float32Array|null} csiEmb - CSI embedding (or null if CSI-off)
|
||||
* @param {string} mode - 'dual' | 'video' | 'csi'
|
||||
* @returns {Float32Array} Fused embedding
|
||||
*/
|
||||
fuse(videoEmb, csiEmb, mode = 'dual') {
|
||||
const dim = this.embeddingDim;
|
||||
const fused = new Float32Array(dim);
|
||||
|
||||
if (mode === 'video' || !csiEmb) {
|
||||
if (videoEmb) fused.set(videoEmb);
|
||||
this._recordEmbedding(videoEmb, null, fused);
|
||||
return fused;
|
||||
}
|
||||
|
||||
if (mode === 'csi' || !videoEmb) {
|
||||
if (csiEmb) fused.set(csiEmb);
|
||||
this._recordEmbedding(null, csiEmb, fused);
|
||||
return fused;
|
||||
}
|
||||
|
||||
// Dual mode: attention-weighted fusion with confidence gating
|
||||
const totalConf = this.videoConfidence + this.csiConfidence;
|
||||
const videoWeight = totalConf > 0 ? this.videoConfidence / totalConf : 0.5;
|
||||
|
||||
for (let i = 0; i < dim; i++) {
|
||||
const alpha = this.attentionWeights[i] * videoWeight +
|
||||
(1 - this.attentionWeights[i]) * (1 - videoWeight);
|
||||
fused[i] = alpha * videoEmb[i] + (1 - alpha) * csiEmb[i];
|
||||
}
|
||||
|
||||
// Re-normalize
|
||||
let norm = 0;
|
||||
for (let i = 0; i < dim; i++) norm += fused[i] * fused[i];
|
||||
norm = Math.sqrt(norm);
|
||||
if (norm > 1e-8) {
|
||||
for (let i = 0; i < dim; i++) fused[i] /= norm;
|
||||
}
|
||||
|
||||
this._recordEmbedding(videoEmb, csiEmb, fused);
|
||||
return fused;
|
||||
}
|
||||
|
||||
/**
|
||||
* Get embedding pairs for 2D visualization (PCA projection)
|
||||
* @returns {{ video: Array, csi: Array, fused: Array }}
|
||||
*/
|
||||
getEmbeddingPoints() {
|
||||
// Simple 2D projection using first two principal components (approximated)
|
||||
const project = (emb) => {
|
||||
if (!emb || emb.length < 4) return null;
|
||||
// Use pairs of dimensions as crude 2D projection
|
||||
let x = 0, y = 0;
|
||||
for (let i = 0; i < emb.length; i += 2) {
|
||||
x += emb[i] * (i % 4 < 2 ? 1 : -1);
|
||||
if (i + 1 < emb.length) {
|
||||
y += emb[i + 1] * (i % 4 < 2 ? 1 : -1);
|
||||
}
|
||||
}
|
||||
return [x * 2, y * 2]; // Scale for visibility
|
||||
};
|
||||
|
||||
return {
|
||||
video: this.recentVideoEmbeddings.map(project).filter(Boolean),
|
||||
csi: this.recentCsiEmbeddings.map(project).filter(Boolean),
|
||||
fused: this.recentFusedEmbeddings.map(project).filter(Boolean)
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
* Cross-modal similarity score
|
||||
* @returns {number} Cosine similarity between latest video and CSI embeddings
|
||||
*/
|
||||
getCrossModalSimilarity() {
|
||||
const v = this.recentVideoEmbeddings[this.recentVideoEmbeddings.length - 1];
|
||||
const c = this.recentCsiEmbeddings[this.recentCsiEmbeddings.length - 1];
|
||||
if (!v || !c) return 0;
|
||||
|
||||
let dot = 0, na = 0, nb = 0;
|
||||
for (let i = 0; i < v.length; i++) {
|
||||
dot += v[i] * c[i];
|
||||
na += v[i] * v[i];
|
||||
nb += c[i] * c[i];
|
||||
}
|
||||
na = Math.sqrt(na); nb = Math.sqrt(nb);
|
||||
return (na > 1e-8 && nb > 1e-8) ? dot / (na * nb) : 0;
|
||||
}
|
||||
|
||||
_recordEmbedding(video, csi, fused) {
|
||||
if (video) {
|
||||
this.recentVideoEmbeddings.push(new Float32Array(video));
|
||||
if (this.recentVideoEmbeddings.length > this.maxHistory) this.recentVideoEmbeddings.shift();
|
||||
}
|
||||
if (csi) {
|
||||
this.recentCsiEmbeddings.push(new Float32Array(csi));
|
||||
if (this.recentCsiEmbeddings.length > this.maxHistory) this.recentCsiEmbeddings.shift();
|
||||
}
|
||||
this.recentFusedEmbeddings.push(new Float32Array(fused));
|
||||
if (this.recentFusedEmbeddings.length > this.maxHistory) this.recentFusedEmbeddings.shift();
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,295 @@
|
||||
/**
|
||||
* WiFi-DensePose — Dual-Modal Pose Estimation Demo
|
||||
*
|
||||
* Main orchestration: video capture → CNN embedding → CSI processing → fusion → rendering
|
||||
*/
|
||||
|
||||
import { VideoCapture } from './video-capture.js';
|
||||
import { CsiSimulator } from './csi-simulator.js';
|
||||
import { CnnEmbedder } from './cnn-embedder.js';
|
||||
import { FusionEngine } from './fusion-engine.js';
|
||||
import { PoseDecoder } from './pose-decoder.js';
|
||||
import { CanvasRenderer } from './canvas-renderer.js';
|
||||
|
||||
// === State ===
|
||||
let mode = 'dual'; // 'dual' | 'video' | 'csi'
|
||||
let isRunning = false;
|
||||
let isPaused = false;
|
||||
let startTime = 0;
|
||||
let frameCount = 0;
|
||||
let fps = 0;
|
||||
let lastFpsTime = 0;
|
||||
let confidenceThreshold = 0.3;
|
||||
|
||||
// Latency tracking
|
||||
const latency = { video: 0, csi: 0, fusion: 0, total: 0 };
|
||||
|
||||
// === Components ===
|
||||
const videoCapture = new VideoCapture(document.getElementById('webcam'));
|
||||
const csiSimulator = new CsiSimulator({ subcarriers: 52, timeWindow: 56 });
|
||||
const visualCnn = new CnnEmbedder({ inputSize: 56, embeddingDim: 128, seed: 42 });
|
||||
const csiCnn = new CnnEmbedder({ inputSize: 56, embeddingDim: 128, seed: 137 });
|
||||
const fusionEngine = new FusionEngine(128);
|
||||
const poseDecoder = new PoseDecoder(128);
|
||||
const renderer = new CanvasRenderer();
|
||||
|
||||
// === Canvas Elements ===
|
||||
const skeletonCanvas = document.getElementById('skeleton-canvas');
|
||||
const skeletonCtx = skeletonCanvas.getContext('2d');
|
||||
const csiCanvas = document.getElementById('csi-canvas');
|
||||
const csiCtx = csiCanvas.getContext('2d');
|
||||
const embeddingCanvas = document.getElementById('embedding-canvas');
|
||||
const embeddingCtx = embeddingCanvas.getContext('2d');
|
||||
|
||||
// === UI Elements ===
|
||||
const modeSelect = document.getElementById('mode-select');
|
||||
const statusDot = document.getElementById('status-dot');
|
||||
const statusLabel = document.getElementById('status-label');
|
||||
const fpsDisplay = document.getElementById('fps-display');
|
||||
const cameraPrompt = document.getElementById('camera-prompt');
|
||||
const startCameraBtn = document.getElementById('start-camera-btn');
|
||||
const pauseBtn = document.getElementById('pause-btn');
|
||||
const confSlider = document.getElementById('confidence-slider');
|
||||
const confValue = document.getElementById('confidence-value');
|
||||
const wsUrlInput = document.getElementById('ws-url');
|
||||
const connectWsBtn = document.getElementById('connect-ws-btn');
|
||||
|
||||
// Fusion bar elements
|
||||
const videoBar = document.getElementById('video-bar');
|
||||
const csiBar = document.getElementById('csi-bar');
|
||||
const fusedBar = document.getElementById('fused-bar');
|
||||
const videoBarVal = document.getElementById('video-bar-val');
|
||||
const csiBarVal = document.getElementById('csi-bar-val');
|
||||
const fusedBarVal = document.getElementById('fused-bar-val');
|
||||
|
||||
// Latency elements
|
||||
const latVideoEl = document.getElementById('lat-video');
|
||||
const latCsiEl = document.getElementById('lat-csi');
|
||||
const latFusionEl = document.getElementById('lat-fusion');
|
||||
const latTotalEl = document.getElementById('lat-total');
|
||||
|
||||
// Cross-modal similarity
|
||||
const crossModalEl = document.getElementById('cross-modal-sim');
|
||||
|
||||
// === Initialize ===
|
||||
function init() {
|
||||
resizeCanvases();
|
||||
window.addEventListener('resize', resizeCanvases);
|
||||
|
||||
// Mode change
|
||||
modeSelect.addEventListener('change', (e) => {
|
||||
mode = e.target.value;
|
||||
updateModeUI();
|
||||
});
|
||||
|
||||
// Camera start
|
||||
startCameraBtn.addEventListener('click', startCamera);
|
||||
|
||||
// Pause
|
||||
pauseBtn.addEventListener('click', () => {
|
||||
isPaused = !isPaused;
|
||||
pauseBtn.textContent = isPaused ? '▶ Resume' : '⏸ Pause';
|
||||
pauseBtn.classList.toggle('active', isPaused);
|
||||
});
|
||||
|
||||
// Confidence slider
|
||||
confSlider.addEventListener('input', (e) => {
|
||||
confidenceThreshold = parseFloat(e.target.value);
|
||||
confValue.textContent = confidenceThreshold.toFixed(2);
|
||||
});
|
||||
|
||||
// WebSocket connect
|
||||
connectWsBtn.addEventListener('click', async () => {
|
||||
const url = wsUrlInput.value.trim();
|
||||
if (!url) return;
|
||||
connectWsBtn.textContent = 'Connecting...';
|
||||
const ok = await csiSimulator.connectLive(url);
|
||||
connectWsBtn.textContent = ok ? '✓ Connected' : 'Connect';
|
||||
if (ok) {
|
||||
connectWsBtn.classList.add('active');
|
||||
}
|
||||
});
|
||||
|
||||
// Try to load WASM embedders (non-blocking)
|
||||
visualCnn.tryLoadWasm('./pkg/ruvector_cnn_wasm');
|
||||
csiCnn.tryLoadWasm('./pkg/ruvector_cnn_wasm');
|
||||
|
||||
// Auto-start camera for video/dual modes
|
||||
updateModeUI();
|
||||
startTime = performance.now() / 1000;
|
||||
isRunning = true;
|
||||
requestAnimationFrame(mainLoop);
|
||||
}
|
||||
|
||||
async function startCamera() {
|
||||
cameraPrompt.style.display = 'none';
|
||||
const ok = await videoCapture.start();
|
||||
if (ok) {
|
||||
statusDot.classList.remove('offline');
|
||||
statusLabel.textContent = 'LIVE';
|
||||
resizeCanvases();
|
||||
} else {
|
||||
cameraPrompt.style.display = 'flex';
|
||||
cameraPrompt.querySelector('p').textContent = 'Camera access denied. Try CSI-only mode.';
|
||||
}
|
||||
}
|
||||
|
||||
function updateModeUI() {
|
||||
const needsVideo = mode !== 'csi';
|
||||
const needsCsi = mode !== 'video';
|
||||
|
||||
// Show/hide camera prompt
|
||||
if (needsVideo && !videoCapture.isActive) {
|
||||
cameraPrompt.style.display = 'flex';
|
||||
} else {
|
||||
cameraPrompt.style.display = 'none';
|
||||
}
|
||||
}
|
||||
|
||||
function resizeCanvases() {
|
||||
const videoPanel = document.querySelector('.video-panel');
|
||||
if (videoPanel) {
|
||||
const rect = videoPanel.getBoundingClientRect();
|
||||
skeletonCanvas.width = rect.width;
|
||||
skeletonCanvas.height = rect.height;
|
||||
}
|
||||
|
||||
// CSI canvas
|
||||
csiCanvas.width = csiCanvas.parentElement.clientWidth;
|
||||
csiCanvas.height = 120;
|
||||
|
||||
// Embedding canvas
|
||||
embeddingCanvas.width = embeddingCanvas.parentElement.clientWidth;
|
||||
embeddingCanvas.height = 140;
|
||||
}
|
||||
|
||||
// === Main Loop ===
|
||||
function mainLoop(timestamp) {
|
||||
if (!isRunning) return;
|
||||
requestAnimationFrame(mainLoop);
|
||||
|
||||
if (isPaused) return;
|
||||
|
||||
const elapsed = performance.now() / 1000 - startTime;
|
||||
const totalStart = performance.now();
|
||||
|
||||
// --- Video Pipeline ---
|
||||
let videoEmb = null;
|
||||
let motionRegion = null;
|
||||
if (mode !== 'csi' && videoCapture.isActive) {
|
||||
const t0 = performance.now();
|
||||
const frame = videoCapture.captureFrame(56, 56);
|
||||
if (frame) {
|
||||
videoEmb = visualCnn.extract(frame.rgb, frame.width, frame.height);
|
||||
motionRegion = videoCapture.detectMotionRegion(56, 56);
|
||||
|
||||
// Feed motion to CSI simulator for correlated demo data
|
||||
if (motionRegion.detected) {
|
||||
csiSimulator.updatePersonState(
|
||||
1.0,
|
||||
motionRegion.x + motionRegion.w / 2,
|
||||
motionRegion.y + motionRegion.h / 2,
|
||||
frame.motion
|
||||
);
|
||||
} else {
|
||||
csiSimulator.updatePersonState(0, 0.5, 0.5, 0);
|
||||
}
|
||||
|
||||
fusionEngine.updateConfidence(
|
||||
frame.brightness, frame.motion,
|
||||
0, csiSimulator.isLive || mode === 'dual'
|
||||
);
|
||||
}
|
||||
latency.video = performance.now() - t0;
|
||||
}
|
||||
|
||||
// --- CSI Pipeline ---
|
||||
let csiEmb = null;
|
||||
if (mode !== 'video') {
|
||||
const t0 = performance.now();
|
||||
const csiFrame = csiSimulator.nextFrame(elapsed);
|
||||
const pseudoImage = csiSimulator.buildPseudoImage(56);
|
||||
csiEmb = csiCnn.extract(pseudoImage, 56, 56);
|
||||
|
||||
fusionEngine.updateConfidence(
|
||||
videoCapture.brightnessScore,
|
||||
videoCapture.motionScore,
|
||||
csiFrame.snr,
|
||||
true
|
||||
);
|
||||
|
||||
// Draw CSI heatmap
|
||||
const heatmap = csiSimulator.getHeatmapData();
|
||||
renderer.drawCsiHeatmap(csiCtx, heatmap, csiCanvas.width, csiCanvas.height);
|
||||
|
||||
latency.csi = performance.now() - t0;
|
||||
}
|
||||
|
||||
// --- Fusion ---
|
||||
const t0f = performance.now();
|
||||
const fusedEmb = fusionEngine.fuse(videoEmb, csiEmb, mode);
|
||||
latency.fusion = performance.now() - t0f;
|
||||
|
||||
// --- Pose Decode ---
|
||||
// For CSI-only mode, generate a synthetic motion region from CSI energy
|
||||
if (mode === 'csi' && !motionRegion) {
|
||||
const csiPresence = csiSimulator.personPresence;
|
||||
if (csiPresence > 0.1) {
|
||||
motionRegion = {
|
||||
detected: true,
|
||||
x: 0.25, y: 0.15, w: 0.5, h: 0.7,
|
||||
coverage: csiPresence
|
||||
};
|
||||
}
|
||||
}
|
||||
|
||||
const keypoints = poseDecoder.decode(fusedEmb, motionRegion, elapsed);
|
||||
|
||||
// --- Render Skeleton ---
|
||||
const labelMap = { dual: 'DUAL FUSION', video: 'VIDEO ONLY', csi: 'CSI ONLY' };
|
||||
renderer.drawSkeleton(skeletonCtx, keypoints, skeletonCanvas.width, skeletonCanvas.height, {
|
||||
minConfidence: confidenceThreshold,
|
||||
color: mode === 'csi' ? 'amber' : 'green',
|
||||
label: labelMap[mode]
|
||||
});
|
||||
|
||||
// --- Render Embedding Space ---
|
||||
const embPoints = fusionEngine.getEmbeddingPoints();
|
||||
renderer.drawEmbeddingSpace(embeddingCtx, embPoints, embeddingCanvas.width, embeddingCanvas.height);
|
||||
|
||||
// --- Update UI ---
|
||||
latency.total = performance.now() - totalStart;
|
||||
|
||||
// FPS
|
||||
frameCount++;
|
||||
if (timestamp - lastFpsTime > 500) {
|
||||
fps = Math.round(frameCount * 1000 / (timestamp - lastFpsTime));
|
||||
lastFpsTime = timestamp;
|
||||
frameCount = 0;
|
||||
fpsDisplay.textContent = `${fps} FPS`;
|
||||
}
|
||||
|
||||
// Fusion bars
|
||||
const vc = fusionEngine.videoConfidence;
|
||||
const cc = fusionEngine.csiConfidence;
|
||||
const fc = fusionEngine.fusedConfidence;
|
||||
videoBar.style.width = `${vc * 100}%`;
|
||||
csiBar.style.width = `${cc * 100}%`;
|
||||
fusedBar.style.width = `${fc * 100}%`;
|
||||
videoBarVal.textContent = `${Math.round(vc * 100)}%`;
|
||||
csiBarVal.textContent = `${Math.round(cc * 100)}%`;
|
||||
fusedBarVal.textContent = `${Math.round(fc * 100)}%`;
|
||||
|
||||
// Latency
|
||||
latVideoEl.textContent = `${latency.video.toFixed(1)}ms`;
|
||||
latCsiEl.textContent = `${latency.csi.toFixed(1)}ms`;
|
||||
latFusionEl.textContent = `${latency.fusion.toFixed(1)}ms`;
|
||||
latTotalEl.textContent = `${latency.total.toFixed(1)}ms`;
|
||||
|
||||
// Cross-modal similarity
|
||||
const sim = fusionEngine.getCrossModalSimilarity();
|
||||
crossModalEl.textContent = sim.toFixed(3);
|
||||
}
|
||||
|
||||
// Boot
|
||||
document.addEventListener('DOMContentLoaded', init);
|
||||
@@ -0,0 +1,185 @@
|
||||
/**
|
||||
* PoseDecoder — Maps fused 512-dim embedding → 17 COCO keypoints.
|
||||
*
|
||||
* Uses a learned linear projection (weights shipped as JSON or generated).
|
||||
* Each keypoint: (x, y, confidence) = 51 values from the embedding.
|
||||
*
|
||||
* In demo mode, generates plausible poses from motion detection + embedding features.
|
||||
*/
|
||||
|
||||
// COCO keypoint definitions
|
||||
export const KEYPOINT_NAMES = [
|
||||
'nose', 'left_eye', 'right_eye', 'left_ear', 'right_ear',
|
||||
'left_shoulder', 'right_shoulder', 'left_elbow', 'right_elbow',
|
||||
'left_wrist', 'right_wrist', 'left_hip', 'right_hip',
|
||||
'left_knee', 'right_knee', 'left_ankle', 'right_ankle'
|
||||
];
|
||||
|
||||
// Skeleton connections (pairs of keypoint indices)
|
||||
export const SKELETON_CONNECTIONS = [
|
||||
[0, 1], [0, 2], [1, 3], [2, 4], // Head
|
||||
[5, 6], // Shoulders
|
||||
[5, 7], [7, 9], // Left arm
|
||||
[6, 8], [8, 10], // Right arm
|
||||
[5, 11], [6, 12], // Torso
|
||||
[11, 12], // Hips
|
||||
[11, 13], [13, 15], // Left leg
|
||||
[12, 14], [14, 16], // Right leg
|
||||
];
|
||||
|
||||
// Standard body proportions (relative to body height)
|
||||
const PROPORTIONS = {
|
||||
headToShoulder: 0.15,
|
||||
shoulderWidth: 0.25,
|
||||
shoulderToElbow: 0.18,
|
||||
elbowToWrist: 0.16,
|
||||
shoulderToHip: 0.30,
|
||||
hipWidth: 0.18,
|
||||
hipToKnee: 0.24,
|
||||
kneeToAnkle: 0.24,
|
||||
eyeSpacing: 0.04,
|
||||
earSpacing: 0.07,
|
||||
};
|
||||
|
||||
export class PoseDecoder {
|
||||
constructor(embeddingDim = 128) {
|
||||
this.embeddingDim = embeddingDim;
|
||||
this.smoothedKeypoints = null;
|
||||
this.smoothingFactor = 0.6; // Temporal smoothing
|
||||
this._time = 0;
|
||||
}
|
||||
|
||||
/**
|
||||
* Decode embedding into 17 keypoints
|
||||
* @param {Float32Array} embedding - Fused embedding vector
|
||||
* @param {{ detected: boolean, x: number, y: number, w: number, h: number }} motionRegion
|
||||
* @param {number} elapsed - Time in seconds
|
||||
* @returns {Array<{x: number, y: number, confidence: number, name: string}>}
|
||||
*/
|
||||
decode(embedding, motionRegion, elapsed) {
|
||||
this._time = elapsed;
|
||||
|
||||
if (!motionRegion || !motionRegion.detected) {
|
||||
// Fade out existing pose
|
||||
if (this.smoothedKeypoints) {
|
||||
return this.smoothedKeypoints.map(kp => ({
|
||||
...kp,
|
||||
confidence: kp.confidence * 0.92
|
||||
})).filter(kp => kp.confidence > 0.05);
|
||||
}
|
||||
return [];
|
||||
}
|
||||
|
||||
// Generate base pose from motion region
|
||||
const rawKeypoints = this._generatePoseFromRegion(motionRegion, embedding, elapsed);
|
||||
|
||||
// Apply temporal smoothing
|
||||
if (this.smoothedKeypoints && this.smoothedKeypoints.length === rawKeypoints.length) {
|
||||
const alpha = this.smoothingFactor;
|
||||
for (let i = 0; i < rawKeypoints.length; i++) {
|
||||
rawKeypoints[i].x = alpha * this.smoothedKeypoints[i].x + (1 - alpha) * rawKeypoints[i].x;
|
||||
rawKeypoints[i].y = alpha * this.smoothedKeypoints[i].y + (1 - alpha) * rawKeypoints[i].y;
|
||||
}
|
||||
}
|
||||
|
||||
this.smoothedKeypoints = rawKeypoints;
|
||||
return rawKeypoints;
|
||||
}
|
||||
|
||||
_generatePoseFromRegion(region, embedding, elapsed) {
|
||||
// Person center and size from motion bounding box
|
||||
const cx = region.x + region.w / 2;
|
||||
const cy = region.y + region.h / 2;
|
||||
const bodyH = Math.max(region.h, 0.3); // Minimum body height
|
||||
const bodyW = Math.max(region.w, 0.15);
|
||||
|
||||
// Use embedding features to modulate pose
|
||||
const embMod = this._extractPoseModulation(embedding);
|
||||
|
||||
// Generate COCO keypoints using body proportions
|
||||
const P = PROPORTIONS;
|
||||
const halfW = P.shoulderWidth * bodyH / 2;
|
||||
const hipHalfW = P.hipWidth * bodyH / 2;
|
||||
|
||||
// Breathing animation
|
||||
const breathe = Math.sin(elapsed * 1.5) * 0.003;
|
||||
// Subtle sway
|
||||
const sway = Math.sin(elapsed * 0.7) * 0.005 * embMod.sway;
|
||||
|
||||
// Build from hips up
|
||||
const hipY = cy + bodyH * 0.15;
|
||||
const shoulderY = hipY - P.shoulderToHip * bodyH + breathe;
|
||||
const headY = shoulderY - P.headToShoulder * bodyH;
|
||||
const kneeY = hipY + P.hipToKnee * bodyH;
|
||||
const ankleY = kneeY + P.kneeToAnkle * bodyH;
|
||||
|
||||
// Arm animation from motion/embedding
|
||||
const armSwing = embMod.motion * Math.sin(elapsed * 3) * 0.04;
|
||||
const armBend = 0.5 + embMod.armBend * 0.3;
|
||||
|
||||
const elbowYL = shoulderY + P.shoulderToElbow * bodyH * armBend;
|
||||
const elbowYR = shoulderY + P.shoulderToElbow * bodyH * armBend;
|
||||
const wristYL = elbowYL + P.elbowToWrist * bodyH * armBend;
|
||||
const wristYR = elbowYR + P.elbowToWrist * bodyH * armBend;
|
||||
|
||||
// Leg animation
|
||||
const legSwing = embMod.motion * Math.sin(elapsed * 3 + Math.PI) * 0.02;
|
||||
|
||||
const keypoints = [
|
||||
// 0: nose
|
||||
{ x: cx + sway, y: headY + 0.01, confidence: 0.9 + embMod.headConf * 0.1 },
|
||||
// 1: left_eye
|
||||
{ x: cx - P.eyeSpacing * bodyH + sway, y: headY - 0.005, confidence: 0.85 },
|
||||
// 2: right_eye
|
||||
{ x: cx + P.eyeSpacing * bodyH + sway, y: headY - 0.005, confidence: 0.85 },
|
||||
// 3: left_ear
|
||||
{ x: cx - P.earSpacing * bodyH, y: headY + 0.005, confidence: 0.7 },
|
||||
// 4: right_ear
|
||||
{ x: cx + P.earSpacing * bodyH, y: headY + 0.005, confidence: 0.7 },
|
||||
// 5: left_shoulder
|
||||
{ x: cx - halfW + sway * 0.5, y: shoulderY, confidence: 0.92 },
|
||||
// 6: right_shoulder
|
||||
{ x: cx + halfW + sway * 0.5, y: shoulderY, confidence: 0.92 },
|
||||
// 7: left_elbow
|
||||
{ x: cx - halfW - 0.02 + armSwing, y: elbowYL, confidence: 0.85 },
|
||||
// 8: right_elbow
|
||||
{ x: cx + halfW + 0.02 - armSwing, y: elbowYR, confidence: 0.85 },
|
||||
// 9: left_wrist
|
||||
{ x: cx - halfW - 0.03 + armSwing * 1.5, y: wristYL, confidence: 0.8 },
|
||||
// 10: right_wrist
|
||||
{ x: cx + halfW + 0.03 - armSwing * 1.5, y: wristYR, confidence: 0.8 },
|
||||
// 11: left_hip
|
||||
{ x: cx - hipHalfW, y: hipY, confidence: 0.9 },
|
||||
// 12: right_hip
|
||||
{ x: cx + hipHalfW, y: hipY, confidence: 0.9 },
|
||||
// 13: left_knee
|
||||
{ x: cx - hipHalfW + legSwing, y: kneeY, confidence: 0.87 },
|
||||
// 14: right_knee
|
||||
{ x: cx + hipHalfW - legSwing, y: kneeY, confidence: 0.87 },
|
||||
// 15: left_ankle
|
||||
{ x: cx - hipHalfW + legSwing * 1.2, y: ankleY, confidence: 0.82 },
|
||||
// 16: right_ankle
|
||||
{ x: cx + hipHalfW - legSwing * 1.2, y: ankleY, confidence: 0.82 },
|
||||
];
|
||||
|
||||
// Add names
|
||||
for (let i = 0; i < keypoints.length; i++) {
|
||||
keypoints[i].name = KEYPOINT_NAMES[i];
|
||||
}
|
||||
|
||||
return keypoints;
|
||||
}
|
||||
|
||||
_extractPoseModulation(embedding) {
|
||||
if (!embedding || embedding.length < 8) {
|
||||
return { sway: 1, motion: 0.5, armBend: 0.5, headConf: 0.5 };
|
||||
}
|
||||
// Use specific embedding dimensions to modulate pose parameters
|
||||
return {
|
||||
sway: 0.5 + embedding[0] * 2,
|
||||
motion: Math.abs(embedding[1]) * 3,
|
||||
armBend: 0.5 + embedding[2],
|
||||
headConf: 0.5 + embedding[3] * 0.5,
|
||||
};
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,172 @@
|
||||
/**
|
||||
* VideoCapture — getUserMedia webcam capture with frame extraction.
|
||||
* Provides quality metrics (brightness, motion) for fusion confidence gating.
|
||||
*/
|
||||
|
||||
export class VideoCapture {
|
||||
constructor(videoElement) {
|
||||
this.video = videoElement;
|
||||
this.stream = null;
|
||||
this.offscreen = document.createElement('canvas');
|
||||
this.offCtx = this.offscreen.getContext('2d', { willReadFrequently: true });
|
||||
this.prevFrame = null;
|
||||
this.motionScore = 0;
|
||||
this.brightnessScore = 0;
|
||||
}
|
||||
|
||||
async start(constraints = {}) {
|
||||
const defaultConstraints = {
|
||||
video: {
|
||||
width: { ideal: 640 },
|
||||
height: { ideal: 480 },
|
||||
facingMode: 'user',
|
||||
frameRate: { ideal: 30 }
|
||||
},
|
||||
audio: false
|
||||
};
|
||||
|
||||
try {
|
||||
this.stream = await navigator.mediaDevices.getUserMedia(
|
||||
Object.keys(constraints).length ? constraints : defaultConstraints
|
||||
);
|
||||
this.video.srcObject = this.stream;
|
||||
await this.video.play();
|
||||
|
||||
this.offscreen.width = this.video.videoWidth;
|
||||
this.offscreen.height = this.video.videoHeight;
|
||||
|
||||
return true;
|
||||
} catch (err) {
|
||||
console.error('[Video] Camera access failed:', err.message);
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
stop() {
|
||||
if (this.stream) {
|
||||
this.stream.getTracks().forEach(t => t.stop());
|
||||
this.stream = null;
|
||||
}
|
||||
this.video.srcObject = null;
|
||||
}
|
||||
|
||||
get isActive() {
|
||||
return this.stream !== null && this.video.readyState >= 2;
|
||||
}
|
||||
|
||||
get width() { return this.video.videoWidth || 640; }
|
||||
get height() { return this.video.videoHeight || 480; }
|
||||
|
||||
/**
|
||||
* Capture current frame as RGB Uint8Array + compute quality metrics.
|
||||
* @param {number} targetW - Target width for CNN input
|
||||
* @param {number} targetH - Target height for CNN input
|
||||
* @returns {{ rgb: Uint8Array, width: number, height: number, motion: number, brightness: number }}
|
||||
*/
|
||||
captureFrame(targetW = 56, targetH = 56) {
|
||||
if (!this.isActive) return null;
|
||||
|
||||
// Draw to offscreen at target resolution
|
||||
this.offscreen.width = targetW;
|
||||
this.offscreen.height = targetH;
|
||||
this.offCtx.drawImage(this.video, 0, 0, targetW, targetH);
|
||||
const imageData = this.offCtx.getImageData(0, 0, targetW, targetH);
|
||||
const rgba = imageData.data;
|
||||
|
||||
// Convert RGBA → RGB
|
||||
const pixels = targetW * targetH;
|
||||
const rgb = new Uint8Array(pixels * 3);
|
||||
let brightnessSum = 0;
|
||||
let motionSum = 0;
|
||||
|
||||
for (let i = 0; i < pixels; i++) {
|
||||
const r = rgba[i * 4];
|
||||
const g = rgba[i * 4 + 1];
|
||||
const b = rgba[i * 4 + 2];
|
||||
rgb[i * 3] = r;
|
||||
rgb[i * 3 + 1] = g;
|
||||
rgb[i * 3 + 2] = b;
|
||||
|
||||
// Luminance for brightness
|
||||
const lum = 0.299 * r + 0.587 * g + 0.114 * b;
|
||||
brightnessSum += lum;
|
||||
|
||||
// Motion: diff from previous frame
|
||||
if (this.prevFrame) {
|
||||
const pr = this.prevFrame[i * 3];
|
||||
const pg = this.prevFrame[i * 3 + 1];
|
||||
const pb = this.prevFrame[i * 3 + 2];
|
||||
motionSum += Math.abs(r - pr) + Math.abs(g - pg) + Math.abs(b - pb);
|
||||
}
|
||||
}
|
||||
|
||||
this.brightnessScore = brightnessSum / (pixels * 255);
|
||||
this.motionScore = this.prevFrame ? Math.min(1, motionSum / (pixels * 100)) : 0;
|
||||
this.prevFrame = new Uint8Array(rgb);
|
||||
|
||||
return {
|
||||
rgb,
|
||||
width: targetW,
|
||||
height: targetH,
|
||||
motion: this.motionScore,
|
||||
brightness: this.brightnessScore
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
* Capture full-resolution RGBA for overlay rendering
|
||||
* @returns {ImageData|null}
|
||||
*/
|
||||
captureFullFrame() {
|
||||
if (!this.isActive) return null;
|
||||
this.offscreen.width = this.width;
|
||||
this.offscreen.height = this.height;
|
||||
this.offCtx.drawImage(this.video, 0, 0);
|
||||
return this.offCtx.getImageData(0, 0, this.width, this.height);
|
||||
}
|
||||
|
||||
/**
|
||||
* Simple body detection from motion differencing.
|
||||
* Returns approximate bounding box of moving region.
|
||||
* @returns {{ x, y, w, h, detected: boolean }}
|
||||
*/
|
||||
detectMotionRegion(targetW = 56, targetH = 56) {
|
||||
if (!this.isActive || !this.prevFrame) return { detected: false };
|
||||
|
||||
this.offscreen.width = targetW;
|
||||
this.offscreen.height = targetH;
|
||||
this.offCtx.drawImage(this.video, 0, 0, targetW, targetH);
|
||||
const rgba = this.offCtx.getImageData(0, 0, targetW, targetH).data;
|
||||
|
||||
let minX = targetW, minY = targetH, maxX = 0, maxY = 0;
|
||||
let motionPixels = 0;
|
||||
const threshold = 25;
|
||||
|
||||
for (let y = 0; y < targetH; y++) {
|
||||
for (let x = 0; x < targetW; x++) {
|
||||
const i = y * targetW + x;
|
||||
const r = rgba[i * 4], g = rgba[i * 4 + 1], b = rgba[i * 4 + 2];
|
||||
const pr = this.prevFrame[i * 3], pg = this.prevFrame[i * 3 + 1], pb = this.prevFrame[i * 3 + 2];
|
||||
const diff = Math.abs(r - pr) + Math.abs(g - pg) + Math.abs(b - pb);
|
||||
|
||||
if (diff > threshold * 3) {
|
||||
motionPixels++;
|
||||
if (x < minX) minX = x;
|
||||
if (y < minY) minY = y;
|
||||
if (x > maxX) maxX = x;
|
||||
if (y > maxY) maxY = y;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
const detected = motionPixels > (targetW * targetH * 0.02);
|
||||
return {
|
||||
detected,
|
||||
x: minX / targetW,
|
||||
y: minY / targetH,
|
||||
w: (maxX - minX) / targetW,
|
||||
h: (maxY - minY) / targetH,
|
||||
coverage: motionPixels / (targetW * targetH)
|
||||
};
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user