@camstack/addon-vision 0.1.1 → 0.1.3

package/dist/chunk-WG66JYYW.mjs

@@ -0,0 +1,116 @@
+import {
+  __commonJS,
+  __require
+} from "./chunk-3IIFBJCD.mjs";
+
+// src/shared/image-utils.js
+var require_image_utils = __commonJS({
+  "src/shared/image-utils.js"(exports) {
+    "use strict";
+    var __importDefault = exports && exports.__importDefault || function(mod) {
+      return mod && mod.__esModule ? mod : { "default": mod };
+    };
+    Object.defineProperty(exports, "__esModule", { value: true });
+    exports.jpegToRgb = jpegToRgb;
+    exports.cropRegion = cropRegion;
+    exports.letterbox = letterbox;
+    exports.resizeAndNormalize = resizeAndNormalize;
+    exports.rgbToGrayscale = rgbToGrayscale;
+    var sharp_1 = __importDefault(__require("sharp"));
+    async function jpegToRgb(jpeg) {
+      const { data, info } = await (0, sharp_1.default)(jpeg).removeAlpha().raw().toBuffer({ resolveWithObject: true });
+      return { data, width: info.width, height: info.height };
+    }
+    async function cropRegion(jpeg, roi) {
+      return (0, sharp_1.default)(jpeg).extract({
+        left: Math.round(roi.x),
+        top: Math.round(roi.y),
+        width: Math.round(roi.w),
+        height: Math.round(roi.h)
+      }).jpeg().toBuffer();
+    }
+    async function letterbox(jpeg, targetSize) {
+      const meta = await (0, sharp_1.default)(jpeg).metadata();
+      const originalWidth = meta.width ?? 0;
+      const originalHeight = meta.height ?? 0;
+      const scale = Math.min(targetSize / originalWidth, targetSize / originalHeight);
+      const scaledWidth = Math.round(originalWidth * scale);
+      const scaledHeight = Math.round(originalHeight * scale);
+      const padX = Math.floor((targetSize - scaledWidth) / 2);
+      const padY = Math.floor((targetSize - scaledHeight) / 2);
+      const { data } = await (0, sharp_1.default)(jpeg).resize(scaledWidth, scaledHeight).extend({
+        top: padY,
+        bottom: targetSize - scaledHeight - padY,
+        left: padX,
+        right: targetSize - scaledWidth - padX,
+        background: { r: 114, g: 114, b: 114 }
+      }).removeAlpha().raw().toBuffer({ resolveWithObject: true });
+      const numPixels = targetSize * targetSize;
+      const float32 = new Float32Array(3 * numPixels);
+      for (let i = 0; i < numPixels; i++) {
+        const srcBase = i * 3;
+        float32[0 * numPixels + i] = data[srcBase] / 255;
+        float32[1 * numPixels + i] = data[srcBase + 1] / 255;
+        float32[2 * numPixels + i] = data[srcBase + 2] / 255;
+      }
+      return { data: float32, scale, padX, padY, originalWidth, originalHeight };
+    }
+    async function resizeAndNormalize(jpeg, targetWidth, targetHeight, normalization, layout) {
+      const { data } = await (0, sharp_1.default)(jpeg).resize(targetWidth, targetHeight, { fit: "fill" }).removeAlpha().raw().toBuffer({ resolveWithObject: true });
+      const numPixels = targetWidth * targetHeight;
+      const float32 = new Float32Array(3 * numPixels);
+      const mean = [0.485, 0.456, 0.406];
+      const std = [0.229, 0.224, 0.225];
+      if (layout === "nchw") {
+        for (let i = 0; i < numPixels; i++) {
+          const srcBase = i * 3;
+          for (let c = 0; c < 3; c++) {
+            const raw = data[srcBase + c] / 255;
+            let val;
+            if (normalization === "zero-one") {
+              val = raw;
+            } else if (normalization === "imagenet") {
+              val = (raw - mean[c]) / std[c];
+            } else {
+              val = data[srcBase + c];
+            }
+            float32[c * numPixels + i] = val;
+          }
+        }
+      } else {
+        for (let i = 0; i < numPixels; i++) {
+          const srcBase = i * 3;
+          for (let c = 0; c < 3; c++) {
+            const raw = data[srcBase + c] / 255;
+            let val;
+            if (normalization === "zero-one") {
+              val = raw;
+            } else if (normalization === "imagenet") {
+              val = (raw - mean[c]) / std[c];
+            } else {
+              val = data[srcBase + c];
+            }
+            float32[i * 3 + c] = val;
+          }
+        }
+      }
+      return float32;
+    }
+    function rgbToGrayscale(rgb, width, height) {
+      const numPixels = width * height;
+      const gray = new Uint8Array(numPixels);
+      for (let i = 0; i < numPixels; i++) {
+        const r = rgb[i * 3];
+        const g = rgb[i * 3 + 1];
+        const b = rgb[i * 3 + 2];
+        gray[i] = Math.round(0.299 * r + 0.587 * g + 0.114 * b);
+      }
+      return gray;
+    }
+  }
+});
+
+export {
+  require_image_utils
+};
+//# sourceMappingURL=chunk-WG66JYYW.mjs.map

package/dist/{chunk-22BHCDT5.mjs.map → chunk-WG66JYYW.mjs.map}

@@ -1 +1 @@
-{"version":3,"sources":["../src/shared/image-utils.ts"],"sourcesContent":["import sharp from 'sharp'\nimport type { BoundingBox } from '@camstack/types'\n\n/** Decode JPEG to raw RGB pixels */\nexport async function jpegToRgb(\n  jpeg: Buffer,\n): Promise<{ data: Buffer; width: number; height: number }> {\n  const { data, info } = await sharp(jpeg)\n    .removeAlpha()\n    .raw()\n    .toBuffer({ resolveWithObject: true })\n  return { data, width: info.width, height: info.height }\n}\n\n/** Crop a region from a JPEG buffer */\nexport async function cropRegion(jpeg: Buffer, roi: BoundingBox): Promise<Buffer> {\n  return sharp(jpeg)\n    .extract({\n      left: Math.round(roi.x),\n      top: Math.round(roi.y),\n      width: Math.round(roi.w),\n      height: Math.round(roi.h),\n    })\n    .jpeg()\n    .toBuffer()\n}\n\n/** Letterbox resize for YOLO: resize preserving aspect ratio, pad to square */\nexport async function letterbox(\n  jpeg: Buffer,\n  targetSize: number,\n): Promise<{\n  data: Float32Array\n  scale: number\n  padX: number\n  padY: number\n  originalWidth: number\n  originalHeight: number\n}> {\n  const meta = await sharp(jpeg).metadata()\n  const originalWidth = meta.width ?? 0\n  const originalHeight = meta.height ?? 0\n\n  const scale = Math.min(targetSize / originalWidth, targetSize / originalHeight)\n  const scaledWidth = Math.round(originalWidth * scale)\n  const scaledHeight = Math.round(originalHeight * scale)\n\n  const padX = Math.floor((targetSize - scaledWidth) / 2)\n  const padY = Math.floor((targetSize - scaledHeight) / 2)\n\n  const { data } = await sharp(jpeg)\n    .resize(scaledWidth, scaledHeight)\n    .extend({\n      top: padY,\n      bottom: targetSize - scaledHeight - padY,\n      left: padX,\n      right: targetSize - scaledWidth - padX,\n      background: { r: 114, g: 114, b: 114 },\n    })\n    .removeAlpha()\n    .raw()\n    .toBuffer({ resolveWithObject: true })\n\n  // Convert HWC uint8 to CHW float [0,1]\n  const numPixels = targetSize * targetSize\n  const float32 = new Float32Array(3 * numPixels)\n  for (let i = 0; i < numPixels; i++) {\n    const srcBase = i * 3\n    float32[0 * numPixels + i] = (data[srcBase]! / 255)\n    float32[1 * numPixels + i] = (data[srcBase + 1]! / 255)\n    float32[2 * numPixels + i] = (data[srcBase + 2]! / 255)\n  }\n\n  return { data: float32, scale, padX, padY, originalWidth, originalHeight }\n}\n\n/** Resize and normalize to Float32Array */\nexport async function resizeAndNormalize(\n  jpeg: Buffer,\n  targetWidth: number,\n  targetHeight: number,\n  normalization: 'zero-one' | 'imagenet' | 'none',\n  layout: 'nchw' | 'nhwc',\n): Promise<Float32Array> {\n  const { data } = await sharp(jpeg)\n    .resize(targetWidth, targetHeight, { fit: 'fill' })\n    .removeAlpha()\n    .raw()\n    .toBuffer({ resolveWithObject: true })\n\n  const numPixels = targetWidth * targetHeight\n  const float32 = new Float32Array(3 * numPixels)\n\n  // ImageNet mean and std per channel\n  const mean = [0.485, 0.456, 0.406]\n  const std = [0.229, 0.224, 0.225]\n\n  if (layout === 'nchw') {\n    for (let i = 0; i < numPixels; i++) {\n      const srcBase = i * 3\n      for (let c = 0; c < 3; c++) {\n        const raw = data[srcBase + c]! / 255\n        let val: number\n        if (normalization === 'zero-one') {\n          val = raw\n        } else if (normalization === 'imagenet') {\n          val = (raw - mean[c]!) / std[c]!\n        } else {\n          val = data[srcBase + c]!\n        }\n        float32[c * numPixels + i] = val\n      }\n    }\n  } else {\n    // nhwc\n    for (let i = 0; i < numPixels; i++) {\n      const srcBase = i * 3\n      for (let c = 0; c < 3; c++) {\n        const raw = data[srcBase + c]! / 255\n        let val: number\n        if (normalization === 'zero-one') {\n          val = raw\n        } else if (normalization === 'imagenet') {\n          val = (raw - mean[c]!) / std[c]!\n        } else {\n          val = data[srcBase + c]!\n        }\n        float32[i * 3 + c] = val\n      }\n    }\n  }\n\n  return float32\n}\n\n/** Convert raw RGB to grayscale Uint8Array */\nexport function rgbToGrayscale(rgb: Buffer, width: number, height: number): Uint8Array {\n  const numPixels = width * height\n  const gray = new Uint8Array(numPixels)\n  for (let i = 0; i < numPixels; i++) {\n    const r = rgb[i * 3]!\n    const g = rgb[i * 3 + 1]!\n    const b = rgb[i * 3 + 2]!\n    // BT.601 luma\n    gray[i] = Math.round(0.299 * r + 0.587 * g + 0.114 * b)\n  }\n  return gray\n}\n"],"mappings":";AAAA,OAAO,WAAW;AAIlB,eAAsB,UACpB,MAC0D;AAC1D,QAAM,EAAE,MAAM,KAAK,IAAI,MAAM,MAAM,IAAI,EACpC,YAAY,EACZ,IAAI,EACJ,SAAS,EAAE,mBAAmB,KAAK,CAAC;AACvC,SAAO,EAAE,MAAM,OAAO,KAAK,OAAO,QAAQ,KAAK,OAAO;AACxD;AAGA,eAAsB,WAAW,MAAc,KAAmC;AAChF,SAAO,MAAM,IAAI,EACd,QAAQ;AAAA,IACP,MAAM,KAAK,MAAM,IAAI,CAAC;AAAA,IACtB,KAAK,KAAK,MAAM,IAAI,CAAC;AAAA,IACrB,OAAO,KAAK,MAAM,IAAI,CAAC;AAAA,IACvB,QAAQ,KAAK,MAAM,IAAI,CAAC;AAAA,EAC1B,CAAC,EACA,KAAK,EACL,SAAS;AACd;AAGA,eAAsB,UACpB,MACA,YAQC;AACD,QAAM,OAAO,MAAM,MAAM,IAAI,EAAE,SAAS;AACxC,QAAM,gBAAgB,KAAK,SAAS;AACpC,QAAM,iBAAiB,KAAK,UAAU;AAEtC,QAAM,QAAQ,KAAK,IAAI,aAAa,eAAe,aAAa,cAAc;AAC9E,QAAM,cAAc,KAAK,MAAM,gBAAgB,KAAK;AACpD,QAAM,eAAe,KAAK,MAAM,iBAAiB,KAAK;AAEtD,QAAM,OAAO,KAAK,OAAO,aAAa,eAAe,CAAC;AACtD,QAAM,OAAO,KAAK,OAAO,aAAa,gBAAgB,CAAC;AAEvD,QAAM,EAAE,KAAK,IAAI,MAAM,MAAM,IAAI,EAC9B,OAAO,aAAa,YAAY,EAChC,OAAO;AAAA,IACN,KAAK;AAAA,IACL,QAAQ,aAAa,eAAe;AAAA,IACpC,MAAM;AAAA,IACN,OAAO,aAAa,cAAc;AAAA,IAClC,YAAY,EAAE,GAAG,KAAK,GAAG,KAAK,GAAG,IAAI;AAAA,EACvC,CAAC,EACA,YAAY,EACZ,IAAI,EACJ,SAAS,EAAE,mBAAmB,KAAK,CAAC;AAGvC,QAAM,YAAY,aAAa;AAC/B,QAAM,UAAU,IAAI,aAAa,IAAI,SAAS;AAC9C,WAAS,IAAI,GAAG,IAAI,WAAW,KAAK;AAClC,UAAM,UAAU,IAAI;AACpB,YAAQ,IAAI,YAAY,CAAC,IAAK,KAAK,OAAO,IAAK;AAC/C,YAAQ,IAAI,YAAY,CAAC,IAAK,KAAK,UAAU,CAAC,IAAK;AACnD,YAAQ,IAAI,YAAY,CAAC,IAAK,KAAK,UAAU,CAAC,IAAK;AAAA,EACrD;AAEA,SAAO,EAAE,MAAM,SAAS,OAAO,MAAM,MAAM,eAAe,eAAe;AAC3E;AAGA,eAAsB,mBACpB,MACA,aACA,cACA,eACA,QACuB;AACvB,QAAM,EAAE,KAAK,IAAI,MAAM,MAAM,IAAI,EAC9B,OAAO,aAAa,cAAc,EAAE,KAAK,OAAO,CAAC,EACjD,YAAY,EACZ,IAAI,EACJ,SAAS,EAAE,mBAAmB,KAAK,CAAC;AAEvC,QAAM,YAAY,cAAc;AAChC,QAAM,UAAU,IAAI,aAAa,IAAI,SAAS;AAG9C,QAAM,OAAO,CAAC,OAAO,OAAO,KAAK;AACjC,QAAM,MAAM,CAAC,OAAO,OAAO,KAAK;AAEhC,MAAI,WAAW,QAAQ;AACrB,aAAS,IAAI,GAAG,IAAI,WAAW,KAAK;AAClC,YAAM,UAAU,IAAI;AACpB,eAAS,IAAI,GAAG,IAAI,GAAG,KAAK;AAC1B,cAAM,MAAM,KAAK,UAAU,CAAC,IAAK;AACjC,YAAI;AACJ,YAAI,kBAAkB,YAAY;AAChC,gBAAM;AAAA,QACR,WAAW,kBAAkB,YAAY;AACvC,iBAAO,MAAM,KAAK,CAAC,KAAM,IAAI,CAAC;AAAA,QAChC,OAAO;AACL,gBAAM,KAAK,UAAU,CAAC;AAAA,QACxB;AACA,gBAAQ,IAAI,YAAY,CAAC,IAAI;AAAA,MAC/B;AAAA,IACF;AAAA,EACF,OAAO;AAEL,aAAS,IAAI,GAAG,IAAI,WAAW,KAAK;AAClC,YAAM,UAAU,IAAI;AACpB,eAAS,IAAI,GAAG,IAAI,GAAG,KAAK;AAC1B,cAAM,MAAM,KAAK,UAAU,CAAC,IAAK;AACjC,YAAI;AACJ,YAAI,kBAAkB,YAAY;AAChC,gBAAM;AAAA,QACR,WAAW,kBAAkB,YAAY;AACvC,iBAAO,MAAM,KAAK,CAAC,KAAM,IAAI,CAAC;AAAA,QAChC,OAAO;AACL,gBAAM,KAAK,UAAU,CAAC;AAAA,QACxB;AACA,gBAAQ,IAAI,IAAI,CAAC,IAAI;AAAA,MACvB;AAAA,IACF;AAAA,EACF;AAEA,SAAO;AACT;AAGO,SAAS,eAAe,KAAa,OAAe,QAA4B;AACrF,QAAM,YAAY,QAAQ;AAC1B,QAAM,OAAO,IAAI,WAAW,SAAS;AACrC,WAAS,IAAI,GAAG,IAAI,WAAW,KAAK;AAClC,UAAM,IAAI,IAAI,IAAI,CAAC;AACnB,UAAM,IAAI,IAAI,IAAI,IAAI,CAAC;AACvB,UAAM,IAAI,IAAI,IAAI,IAAI,CAAC;AAEvB,SAAK,CAAC,IAAI,KAAK,MAAM,QAAQ,IAAI,QAAQ,IAAI,QAAQ,CAAC;AAAA,EACxD;AACA,SAAO;AACT;","names":[]}
+{"version":3,"sources":["../src/shared/image-utils.ts"],"sourcesContent":["import sharp from 'sharp'\nimport type { BoundingBox } from '@camstack/types'\n\n/** Decode JPEG to raw RGB pixels */\nexport async function jpegToRgb(\n  jpeg: Buffer,\n): Promise<{ data: Buffer; width: number; height: number }> {\n  const { data, info } = await sharp(jpeg)\n    .removeAlpha()\n    .raw()\n    .toBuffer({ resolveWithObject: true })\n  return { data, width: info.width, height: info.height }\n}\n\n/** Crop a region from a JPEG buffer */\nexport async function cropRegion(jpeg: Buffer, roi: BoundingBox): Promise<Buffer> {\n  return sharp(jpeg)\n    .extract({\n      left: Math.round(roi.x),\n      top: Math.round(roi.y),\n      width: Math.round(roi.w),\n      height: Math.round(roi.h),\n    })\n    .jpeg()\n    .toBuffer()\n}\n\n/** Letterbox resize for YOLO: resize preserving aspect ratio, pad to square */\nexport async function letterbox(\n  jpeg: Buffer,\n  targetSize: number,\n): Promise<{\n  data: Float32Array\n  scale: number\n  padX: number\n  padY: number\n  originalWidth: number\n  originalHeight: number\n}> {\n  const meta = await sharp(jpeg).metadata()\n  const originalWidth = meta.width ?? 0\n  const originalHeight = meta.height ?? 0\n\n  const scale = Math.min(targetSize / originalWidth, targetSize / originalHeight)\n  const scaledWidth = Math.round(originalWidth * scale)\n  const scaledHeight = Math.round(originalHeight * scale)\n\n  const padX = Math.floor((targetSize - scaledWidth) / 2)\n  const padY = Math.floor((targetSize - scaledHeight) / 2)\n\n  const { data } = await sharp(jpeg)\n    .resize(scaledWidth, scaledHeight)\n    .extend({\n      top: padY,\n      bottom: targetSize - scaledHeight - padY,\n      left: padX,\n      right: targetSize - scaledWidth - padX,\n      background: { r: 114, g: 114, b: 114 },\n    })\n    .removeAlpha()\n    .raw()\n    .toBuffer({ resolveWithObject: true })\n\n  // Convert HWC uint8 to CHW float [0,1]\n  const numPixels = targetSize * targetSize\n  const float32 = new Float32Array(3 * numPixels)\n  for (let i = 0; i < numPixels; i++) {\n    const srcBase = i * 3\n    float32[0 * numPixels + i] = (data[srcBase]! / 255)\n    float32[1 * numPixels + i] = (data[srcBase + 1]! / 255)\n    float32[2 * numPixels + i] = (data[srcBase + 2]! / 255)\n  }\n\n  return { data: float32, scale, padX, padY, originalWidth, originalHeight }\n}\n\n/** Resize and normalize to Float32Array */\nexport async function resizeAndNormalize(\n  jpeg: Buffer,\n  targetWidth: number,\n  targetHeight: number,\n  normalization: 'zero-one' | 'imagenet' | 'none',\n  layout: 'nchw' | 'nhwc',\n): Promise<Float32Array> {\n  const { data } = await sharp(jpeg)\n    .resize(targetWidth, targetHeight, { fit: 'fill' })\n    .removeAlpha()\n    .raw()\n    .toBuffer({ resolveWithObject: true })\n\n  const numPixels = targetWidth * targetHeight\n  const float32 = new Float32Array(3 * numPixels)\n\n  // ImageNet mean and std per channel\n  const mean = [0.485, 0.456, 0.406]\n  const std = [0.229, 0.224, 0.225]\n\n  if (layout === 'nchw') {\n    for (let i = 0; i < numPixels; i++) {\n      const srcBase = i * 3\n      for (let c = 0; c < 3; c++) {\n        const raw = data[srcBase + c]! / 255\n        let val: number\n        if (normalization === 'zero-one') {\n          val = raw\n        } else if (normalization === 'imagenet') {\n          val = (raw - mean[c]!) / std[c]!\n        } else {\n          val = data[srcBase + c]!\n        }\n        float32[c * numPixels + i] = val\n      }\n    }\n  } else {\n    // nhwc\n    for (let i = 0; i < numPixels; i++) {\n      const srcBase = i * 3\n      for (let c = 0; c < 3; c++) {\n        const raw = data[srcBase + c]! / 255\n        let val: number\n        if (normalization === 'zero-one') {\n          val = raw\n        } else if (normalization === 'imagenet') {\n          val = (raw - mean[c]!) / std[c]!\n        } else {\n          val = data[srcBase + c]!\n        }\n        float32[i * 3 + c] = val\n      }\n    }\n  }\n\n  return float32\n}\n\n/** Convert raw RGB to grayscale Uint8Array */\nexport function rgbToGrayscale(rgb: Buffer, width: number, height: number): Uint8Array {\n  const numPixels = width * height\n  const gray = new Uint8Array(numPixels)\n  for (let i = 0; i < numPixels; i++) {\n    const r = rgb[i * 3]!\n    const g = rgb[i * 3 + 1]!\n    const b = rgb[i * 3 + 2]!\n    // BT.601 luma\n    gray[i] = Math.round(0.299 * r + 0.587 * g + 0.114 * b)\n  }\n  return gray\n}\n"],"mappings":";;;;;;;;;;;;;AAIA,YAAA,YAAA;AAWA,YAAA,aAAA;AAaA,YAAA,YAAA;AAiDA,YAAA,qBAAA;AA2DA,YAAA,iBAAA;AAxIA,QAAA,UAAA,gBAAA,UAAA,OAAA,CAAA;AAIO,mBAAe,UACpB,MAAY;AAEZ,YAAM,EAAE,MAAM,KAAI,IAAK,OAAM,GAAA,QAAA,SAAM,IAAI,EACpC,YAAW,EACX,IAAG,EACH,SAAS,EAAE,mBAAmB,KAAI,CAAE;AACvC,aAAO,EAAE,MAAM,OAAO,KAAK,OAAO,QAAQ,KAAK,OAAM;IACvD;AAGO,mBAAe,WAAW,MAAc,KAAgB;AAC7D,cAAO,GAAA,QAAA,SAAM,IAAI,EACd,QAAQ;QACP,MAAM,KAAK,MAAM,IAAI,CAAC;QACtB,KAAK,KAAK,MAAM,IAAI,CAAC;QACrB,OAAO,KAAK,MAAM,IAAI,CAAC;QACvB,QAAQ,KAAK,MAAM,IAAI,CAAC;OACzB,EACA,KAAI,EACJ,SAAQ;IACb;AAGO,mBAAe,UACpB,MACA,YAAkB;AASlB,YAAM,OAAO,OAAM,GAAA,QAAA,SAAM,IAAI,EAAE,SAAQ;AACvC,YAAM,gBAAgB,KAAK,SAAS;AACpC,YAAM,iBAAiB,KAAK,UAAU;AAEtC,YAAM,QAAQ,KAAK,IAAI,aAAa,eAAe,aAAa,cAAc;AAC9E,YAAM,cAAc,KAAK,MAAM,gBAAgB,KAAK;AACpD,YAAM,eAAe,KAAK,MAAM,iBAAiB,KAAK;AAEtD,YAAM,OAAO,KAAK,OAAO,aAAa,eAAe,CAAC;AACtD,YAAM,OAAO,KAAK,OAAO,aAAa,gBAAgB,CAAC;AAEvD,YAAM,EAAE,KAAI,IAAK,OAAM,GAAA,QAAA,SAAM,IAAI,EAC9B,OAAO,aAAa,YAAY,EAChC,OAAO;QACN,KAAK;QACL,QAAQ,aAAa,eAAe;QACpC,MAAM;QACN,OAAO,aAAa,cAAc;QAClC,YAAY,EAAE,GAAG,KAAK,GAAG,KAAK,GAAG,IAAG;OACrC,EACA,YAAW,EACX,IAAG,EACH,SAAS,EAAE,mBAAmB,KAAI,CAAE;AAGvC,YAAM,YAAY,aAAa;AAC/B,YAAM,UAAU,IAAI,aAAa,IAAI,SAAS;AAC9C,eAAS,IAAI,GAAG,IAAI,WAAW,KAAK;AAClC,cAAM,UAAU,IAAI;AACpB,gBAAQ,IAAI,YAAY,CAAC,IAAK,KAAK,OAAO,IAAK;AAC/C,gBAAQ,IAAI,YAAY,CAAC,IAAK,KAAK,UAAU,CAAC,IAAK;AACnD,gBAAQ,IAAI,YAAY,CAAC,IAAK,KAAK,UAAU,CAAC,IAAK;MACrD;AAEA,aAAO,EAAE,MAAM,SAAS,OAAO,MAAM,MAAM,eAAe,eAAc;IAC1E;AAGO,mBAAe,mBACpB,MACA,aACA,cACA,eACA,QAAuB;AAEvB,YAAM,EAAE,KAAI,IAAK,OAAM,GAAA,QAAA,SAAM,IAAI,EAC9B,OAAO,aAAa,cAAc,EAAE,KAAK,OAAM,CAAE,EACjD,YAAW,EACX,IAAG,EACH,SAAS,EAAE,mBAAmB,KAAI,CAAE;AAEvC,YAAM,YAAY,cAAc;AAChC,YAAM,UAAU,IAAI,aAAa,IAAI,SAAS;AAG9C,YAAM,OAAO,CAAC,OAAO,OAAO,KAAK;AACjC,YAAM,MAAM,CAAC,OAAO,OAAO,KAAK;AAEhC,UAAI,WAAW,QAAQ;AACrB,iBAAS,IAAI,GAAG,IAAI,WAAW,KAAK;AAClC,gBAAM,UAAU,IAAI;AACpB,mBAAS,IAAI,GAAG,IAAI,GAAG,KAAK;AAC1B,kBAAM,MAAM,KAAK,UAAU,CAAC,IAAK;AACjC,gBAAI;AACJ,gBAAI,kBAAkB,YAAY;AAChC,oBAAM;YACR,WAAW,kBAAkB,YAAY;AACvC,qBAAO,MAAM,KAAK,CAAC,KAAM,IAAI,CAAC;YAChC,OAAO;AACL,oBAAM,KAAK,UAAU,CAAC;YACxB;AACA,oBAAQ,IAAI,YAAY,CAAC,IAAI;UAC/B;QACF;MACF,OAAO;AAEL,iBAAS,IAAI,GAAG,IAAI,WAAW,KAAK;AAClC,gBAAM,UAAU,IAAI;AACpB,mBAAS,IAAI,GAAG,IAAI,GAAG,KAAK;AAC1B,kBAAM,MAAM,KAAK,UAAU,CAAC,IAAK;AACjC,gBAAI;AACJ,gBAAI,kBAAkB,YAAY;AAChC,oBAAM;YACR,WAAW,kBAAkB,YAAY;AACvC,qBAAO,MAAM,KAAK,CAAC,KAAM,IAAI,CAAC;YAChC,OAAO;AACL,oBAAM,KAAK,UAAU,CAAC;YACxB;AACA,oBAAQ,IAAI,IAAI,CAAC,IAAI;UACvB;QACF;MACF;AAEA,aAAO;IACT;AAGA,aAAgB,eAAe,KAAa,OAAe,QAAc;AACvE,YAAM,YAAY,QAAQ;AAC1B,YAAM,OAAO,IAAI,WAAW,SAAS;AACrC,eAAS,IAAI,GAAG,IAAI,WAAW,KAAK;AAClC,cAAM,IAAI,IAAI,IAAI,CAAC;AACnB,cAAM,IAAI,IAAI,IAAI,IAAI,CAAC;AACvB,cAAM,IAAI,IAAI,IAAI,IAAI,CAAC;AAEvB,aAAK,CAAC,IAAI,KAAK,MAAM,QAAQ,IAAI,QAAQ,IAAI,QAAQ,CAAC;MACxD;AACA,aAAO;IACT;;;","names":[]}

package/dist/chunk-XD7WGXHZ.mjs

@@ -0,0 +1,82 @@
+import {
+  require_object_detection_models
+} from "./chunk-MGT6RUVX.mjs";
+import {
+  __commonJS,
+  __require
+} from "./chunk-3IIFBJCD.mjs";
+
+// src/catalogs/animal-classification-models.js
+var require_animal_classification_models = __commonJS({
+  "src/catalogs/animal-classification-models.js"(exports) {
+    "use strict";
+    Object.defineProperty(exports, "__esModule", { value: true });
+    exports.ANIMAL_TYPE_MODELS = exports.BIRD_NABIRDS_MODELS = exports.BIRD_SPECIES_MODELS = void 0;
+    var types_1 = __require("@camstack/types");
+    var object_detection_models_js_1 = require_object_detection_models();
+    var HF_REPO = "camstack/camstack-models";
+    var hf = (path) => (0, types_1.hfModelUrl)(HF_REPO, path);
+    var BIRD_LABEL = { id: "species", name: "Bird Species" };
+    var ANIMAL_TYPE_LABEL = { id: "animal-type", name: "Animal Type" };
+    exports.BIRD_SPECIES_MODELS = [
+      {
+        id: "bird-species-525",
+        name: "Bird Species (525)",
+        description: "EfficientNet bird species classifier \u2014 525 species, MIT license",
+        inputSize: { width: 224, height: 224 },
+        inputNormalization: "imagenet",
+        labels: [BIRD_LABEL],
+        formats: {
+          onnx: { url: hf("animalClassification/bird-species/onnx/camstack-bird-species-525.onnx"), sizeMB: 32 }
+        },
+        extraFiles: [
+          {
+            url: hf("animalClassification/bird-species/onnx/camstack-bird-species-525-labels.json"),
+            filename: "camstack-bird-species-525-labels.json",
+            sizeMB: 0.02
+          }
+        ]
+      }
+    ];
+    exports.BIRD_NABIRDS_MODELS = [
+      {
+        id: "bird-nabirds-404",
+        name: "NABirds (404 species)",
+        description: "ResNet50 trained on NABirds \u2014 404 North American species with ONNX, CoreML, OpenVINO",
+        inputSize: { width: 224, height: 224 },
+        inputNormalization: "imagenet",
+        labels: [{ id: "species", name: "Bird Species" }],
+        formats: {
+          onnx: { url: hf("animalClassification/bird-nabirds/onnx/camstack-bird-nabirds-404.onnx"), sizeMB: 93 },
+          coreml: { url: hf("animalClassification/bird-nabirds/coreml/camstack-bird-nabirds-404.mlpackage"), sizeMB: 47, isDirectory: true, files: object_detection_models_js_1.MLPACKAGE_FILES, runtimes: ["python"] },
+          openvino: { url: hf("animalClassification/bird-nabirds/openvino/camstack-bird-nabirds-404.xml"), sizeMB: 47, runtimes: ["python"] }
+        },
+        extraFiles: [
+          {
+            url: hf("animalClassification/bird-nabirds/onnx/camstack-bird-nabirds-404-labels.json"),
+            filename: "camstack-bird-nabirds-404-labels.json",
+            sizeMB: 0.02
+          }
+        ]
+      }
+    ];
+    exports.ANIMAL_TYPE_MODELS = [
+      {
+        id: "animals-10",
+        name: "Animal Classifier (10)",
+        description: "ViT-based animal type classifier \u2014 cat, cow, dog, dolphin, eagle, panda, horse, monkey, sheep, spider",
+        inputSize: { width: 224, height: 224 },
+        inputNormalization: "imagenet",
+        labels: [ANIMAL_TYPE_LABEL],
+        formats: {
+          onnx: { url: hf("animalClassification/animals-10/onnx/camstack-animals-10.onnx"), sizeMB: 328 }
+        }
+      }
+    ];
+  }
+});
+
+export {
+  require_animal_classification_models
+};
+//# sourceMappingURL=chunk-XD7WGXHZ.mjs.map

package/dist/{chunk-DUN6XU3N.mjs.map → chunk-XD7WGXHZ.mjs.map}

@@ -1 +1 @@
-{"version":3,"sources":["../src/catalogs/animal-classification-models.ts"],"sourcesContent":["import type { ModelCatalogEntry, LabelDefinition } from '@camstack/types'\nimport { hfModelUrl } from '@camstack/types'\nimport { MLPACKAGE_FILES } from './object-detection-models.js'\n\nconst HF_REPO = 'camstack/camstack-models'\n\nconst hf = (path: string) => hfModelUrl(HF_REPO, path)\n\nconst BIRD_LABEL: LabelDefinition = { id: 'species', name: 'Bird Species' }\nconst ANIMAL_TYPE_LABEL: LabelDefinition = { id: 'animal-type', name: 'Animal Type' }\n\nexport const BIRD_SPECIES_MODELS: readonly ModelCatalogEntry[] = [\n  {\n    id: 'bird-species-525',\n    name: 'Bird Species (525)',\n    description: 'EfficientNet bird species classifier — 525 species, MIT license',\n    inputSize: { width: 224, height: 224 },\n    inputNormalization: 'imagenet',\n    labels: [BIRD_LABEL],\n    formats: {\n      onnx: { url: hf('animalClassification/bird-species/onnx/camstack-bird-species-525.onnx'), sizeMB: 32 },\n    },\n    extraFiles: [\n      {\n        url: hf('animalClassification/bird-species/onnx/camstack-bird-species-525-labels.json'),\n        filename: 'camstack-bird-species-525-labels.json',\n        sizeMB: 0.02,\n      },\n    ],\n  },\n] as const\n\nexport const BIRD_NABIRDS_MODELS: readonly ModelCatalogEntry[] = [\n  {\n    id: 'bird-nabirds-404',\n    name: 'NABirds (404 species)',\n    description: 'ResNet50 trained on NABirds — 404 North American species with ONNX, CoreML, OpenVINO',\n    inputSize: { width: 224, height: 224 },\n    inputNormalization: 'imagenet',\n    labels: [{ id: 'species', name: 'Bird Species' }],\n    formats: {\n      onnx: { url: hf('animalClassification/bird-nabirds/onnx/camstack-bird-nabirds-404.onnx'), sizeMB: 93 },\n      coreml: { url: hf('animalClassification/bird-nabirds/coreml/camstack-bird-nabirds-404.mlpackage'), sizeMB: 47, isDirectory: true, files: MLPACKAGE_FILES, runtimes: ['python'] },\n      openvino: { url: hf('animalClassification/bird-nabirds/openvino/camstack-bird-nabirds-404.xml'), sizeMB: 47, runtimes: ['python'] },\n    },\n    extraFiles: [\n      {\n        url: hf('animalClassification/bird-nabirds/onnx/camstack-bird-nabirds-404-labels.json'),\n        filename: 'camstack-bird-nabirds-404-labels.json',\n        sizeMB: 0.02,\n      },\n    ],\n  },\n] as const\n\nexport const ANIMAL_TYPE_MODELS: readonly ModelCatalogEntry[] = [\n  {\n    id: 'animals-10',\n    name: 'Animal Classifier (10)',\n    description: 'ViT-based animal type classifier — cat, cow, dog, dolphin, eagle, panda, horse, monkey, sheep, spider',\n    inputSize: { width: 224, height: 224 },\n    inputNormalization: 'imagenet',\n    labels: [ANIMAL_TYPE_LABEL],\n    formats: {\n      onnx: { url: hf('animalClassification/animals-10/onnx/camstack-animals-10.onnx'), sizeMB: 328 },\n    },\n  },\n] as const\n"],"mappings":";;;;;AACA,SAAS,kBAAkB;AAG3B,IAAM,UAAU;AAEhB,IAAM,KAAK,CAAC,SAAiB,WAAW,SAAS,IAAI;AAErD,IAAM,aAA8B,EAAE,IAAI,WAAW,MAAM,eAAe;AAC1E,IAAM,oBAAqC,EAAE,IAAI,eAAe,MAAM,cAAc;AAE7E,IAAM,sBAAoD;AAAA,EAC/D;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,aAAa;AAAA,IACb,WAAW,EAAE,OAAO,KAAK,QAAQ,IAAI;AAAA,IACrC,oBAAoB;AAAA,IACpB,QAAQ,CAAC,UAAU;AAAA,IACnB,SAAS;AAAA,MACP,MAAM,EAAE,KAAK,GAAG,uEAAuE,GAAG,QAAQ,GAAG;AAAA,IACvG;AAAA,IACA,YAAY;AAAA,MACV;AAAA,QACE,KAAK,GAAG,8EAA8E;AAAA,QACtF,UAAU;AAAA,QACV,QAAQ;AAAA,MACV;AAAA,IACF;AAAA,EACF;AACF;AAEO,IAAM,sBAAoD;AAAA,EAC/D;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,aAAa;AAAA,IACb,WAAW,EAAE,OAAO,KAAK,QAAQ,IAAI;AAAA,IACrC,oBAAoB;AAAA,IACpB,QAAQ,CAAC,EAAE,IAAI,WAAW,MAAM,eAAe,CAAC;AAAA,IAChD,SAAS;AAAA,MACP,MAAM,EAAE,KAAK,GAAG,uEAAuE,GAAG,QAAQ,GAAG;AAAA,MACrG,QAAQ,EAAE,KAAK,GAAG,8EAA8E,GAAG,QAAQ,IAAI,aAAa,MAAM,OAAO,iBAAiB,UAAU,CAAC,QAAQ,EAAE;AAAA,MAC/K,UAAU,EAAE,KAAK,GAAG,0EAA0E,GAAG,QAAQ,IAAI,UAAU,CAAC,QAAQ,EAAE;AAAA,IACpI;AAAA,IACA,YAAY;AAAA,MACV;AAAA,QACE,KAAK,GAAG,8EAA8E;AAAA,QACtF,UAAU;AAAA,QACV,QAAQ;AAAA,MACV;AAAA,IACF;AAAA,EACF;AACF;AAEO,IAAM,qBAAmD;AAAA,EAC9D;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,aAAa;AAAA,IACb,WAAW,EAAE,OAAO,KAAK,QAAQ,IAAI;AAAA,IACrC,oBAAoB;AAAA,IACpB,QAAQ,CAAC,iBAAiB;AAAA,IAC1B,SAAS;AAAA,MACP,MAAM,EAAE,KAAK,GAAG,+DAA+D,GAAG,QAAQ,IAAI;AAAA,IAChG;AAAA,EACF;AACF;","names":[]}
+{"version":3,"sources":["../src/catalogs/animal-classification-models.ts"],"sourcesContent":["import type { ModelCatalogEntry, LabelDefinition } from '@camstack/types'\nimport { hfModelUrl } from '@camstack/types'\nimport { MLPACKAGE_FILES } from './object-detection-models.js'\n\nconst HF_REPO = 'camstack/camstack-models'\n\nconst hf = (path: string) => hfModelUrl(HF_REPO, path)\n\nconst BIRD_LABEL: LabelDefinition = { id: 'species', name: 'Bird Species' }\nconst ANIMAL_TYPE_LABEL: LabelDefinition = { id: 'animal-type', name: 'Animal Type' }\n\nexport const BIRD_SPECIES_MODELS: readonly ModelCatalogEntry[] = [\n  {\n    id: 'bird-species-525',\n    name: 'Bird Species (525)',\n    description: 'EfficientNet bird species classifier — 525 species, MIT license',\n    inputSize: { width: 224, height: 224 },\n    inputNormalization: 'imagenet',\n    labels: [BIRD_LABEL],\n    formats: {\n      onnx: { url: hf('animalClassification/bird-species/onnx/camstack-bird-species-525.onnx'), sizeMB: 32 },\n    },\n    extraFiles: [\n      {\n        url: hf('animalClassification/bird-species/onnx/camstack-bird-species-525-labels.json'),\n        filename: 'camstack-bird-species-525-labels.json',\n        sizeMB: 0.02,\n      },\n    ],\n  },\n] as const\n\nexport const BIRD_NABIRDS_MODELS: readonly ModelCatalogEntry[] = [\n  {\n    id: 'bird-nabirds-404',\n    name: 'NABirds (404 species)',\n    description: 'ResNet50 trained on NABirds — 404 North American species with ONNX, CoreML, OpenVINO',\n    inputSize: { width: 224, height: 224 },\n    inputNormalization: 'imagenet',\n    labels: [{ id: 'species', name: 'Bird Species' }],\n    formats: {\n      onnx: { url: hf('animalClassification/bird-nabirds/onnx/camstack-bird-nabirds-404.onnx'), sizeMB: 93 },\n      coreml: { url: hf('animalClassification/bird-nabirds/coreml/camstack-bird-nabirds-404.mlpackage'), sizeMB: 47, isDirectory: true, files: MLPACKAGE_FILES, runtimes: ['python'] },\n      openvino: { url: hf('animalClassification/bird-nabirds/openvino/camstack-bird-nabirds-404.xml'), sizeMB: 47, runtimes: ['python'] },\n    },\n    extraFiles: [\n      {\n        url: hf('animalClassification/bird-nabirds/onnx/camstack-bird-nabirds-404-labels.json'),\n        filename: 'camstack-bird-nabirds-404-labels.json',\n        sizeMB: 0.02,\n      },\n    ],\n  },\n] as const\n\nexport const ANIMAL_TYPE_MODELS: readonly ModelCatalogEntry[] = [\n  {\n    id: 'animals-10',\n    name: 'Animal Classifier (10)',\n    description: 'ViT-based animal type classifier — cat, cow, dog, dolphin, eagle, panda, horse, monkey, sheep, spider',\n    inputSize: { width: 224, height: 224 },\n    inputNormalization: 'imagenet',\n    labels: [ANIMAL_TYPE_LABEL],\n    formats: {\n      onnx: { url: hf('animalClassification/animals-10/onnx/camstack-animals-10.onnx'), sizeMB: 328 },\n    },\n  },\n] as const\n"],"mappings":";;;;;;;;;;;;;;AACA,QAAA,UAAA,UAAA,iBAAA;AACA,QAAA,+BAAA;AAEA,QAAM,UAAU;AAEhB,QAAM,KAAK,CAAC,UAAiB,GAAA,QAAA,YAAW,SAAS,IAAI;AAErD,QAAM,aAA8B,EAAE,IAAI,WAAW,MAAM,eAAc;AACzE,QAAM,oBAAqC,EAAE,IAAI,eAAe,MAAM,cAAa;AAEtE,YAAA,sBAAoD;MAC/D;QACE,IAAI;QACJ,MAAM;QACN,aAAa;QACb,WAAW,EAAE,OAAO,KAAK,QAAQ,IAAG;QACpC,oBAAoB;QACpB,QAAQ,CAAC,UAAU;QACnB,SAAS;UACP,MAAM,EAAE,KAAK,GAAG,uEAAuE,GAAG,QAAQ,GAAE;;QAEtG,YAAY;UACV;YACE,KAAK,GAAG,8EAA8E;YACtF,UAAU;YACV,QAAQ;;;;;AAMH,YAAA,sBAAoD;MAC/D;QACE,IAAI;QACJ,MAAM;QACN,aAAa;QACb,WAAW,EAAE,OAAO,KAAK,QAAQ,IAAG;QACpC,oBAAoB;QACpB,QAAQ,CAAC,EAAE,IAAI,WAAW,MAAM,eAAc,CAAE;QAChD,SAAS;UACP,MAAM,EAAE,KAAK,GAAG,uEAAuE,GAAG,QAAQ,GAAE;UACpG,QAAQ,EAAE,KAAK,GAAG,8EAA8E,GAAG,QAAQ,IAAI,aAAa,MAAM,OAAO,6BAAA,iBAAiB,UAAU,CAAC,QAAQ,EAAC;UAC9K,UAAU,EAAE,KAAK,GAAG,0EAA0E,GAAG,QAAQ,IAAI,UAAU,CAAC,QAAQ,EAAC;;QAEnI,YAAY;UACV;YACE,KAAK,GAAG,8EAA8E;YACtF,UAAU;YACV,QAAQ;;;;;AAMH,YAAA,qBAAmD;MAC9D;QACE,IAAI;QACJ,MAAM;QACN,aAAa;QACb,WAAW,EAAE,OAAO,KAAK,QAAQ,IAAG;QACpC,oBAAoB;QACpB,QAAQ,CAAC,iBAAiB;QAC1B,SAAS;UACP,MAAM,EAAE,KAAK,GAAG,+DAA+D,GAAG,QAAQ,IAAG;;;;;;","names":[]}

package/dist/chunk-YYDM6V2F.mjs

@@ -0,0 +1,113 @@
+import {
+  __commonJS
+} from "./chunk-3IIFBJCD.mjs";
+
+// src/addons/motion-detection/frame-diff.js
+var require_frame_diff = __commonJS({
+  "src/addons/motion-detection/frame-diff.js"(exports) {
+    "use strict";
+    Object.defineProperty(exports, "__esModule", { value: true });
+    exports.detectMotion = detectMotion;
+    function detectMotion(current, previous, width, height, threshold, minArea) {
+      const numPixels = width * height;
+      const mask = new Uint8Array(numPixels);
+      for (let i = 0; i < numPixels; i++) {
+        mask[i] = Math.abs((current[i] ?? 0) - (previous[i] ?? 0)) > threshold ? 1 : 0;
+      }
+      const labels = new Int32Array(numPixels).fill(0);
+      const parent = new Int32Array(numPixels + 1).fill(0);
+      let nextLabel = 1;
+      function findRoot(x) {
+        while (parent[x] !== x) {
+          parent[x] = parent[parent[x]];
+          x = parent[x];
+        }
+        return x;
+      }
+      function union(a, b) {
+        const ra = findRoot(a);
+        const rb = findRoot(b);
+        if (ra !== rb)
+          parent[rb] = ra;
+        return ra;
+      }
+      for (let i = 0; i <= numPixels; i++) {
+        parent[i] = i;
+      }
+      for (let y = 0; y < height; y++) {
+        for (let x = 0; x < width; x++) {
+          const idx = y * width + x;
+          if (!mask[idx])
+            continue;
+          const above = y > 0 ? labels[(y - 1) * width + x] ?? 0 : 0;
+          const left = x > 0 ? labels[y * width + (x - 1)] ?? 0 : 0;
+          if (above === 0 && left === 0) {
+            labels[idx] = nextLabel;
+            parent[nextLabel] = nextLabel;
+            nextLabel++;
+          } else if (above !== 0 && left === 0) {
+            labels[idx] = above;
+          } else if (above === 0 && left !== 0) {
+            labels[idx] = left;
+          } else {
+            labels[idx] = union(above, left);
+          }
+        }
+      }
+      for (let i = 0; i < numPixels; i++) {
+        if (labels[i]) {
+          labels[i] = findRoot(labels[i]);
+        }
+      }
+      const bboxMap = /* @__PURE__ */ new Map();
+      for (let y = 0; y < height; y++) {
+        for (let x = 0; x < width; x++) {
+          const idx = y * width + x;
+          const label = labels[idx];
+          if (!label)
+            continue;
+          const diff = Math.abs((current[idx] ?? 0) - (previous[idx] ?? 0));
+          const existing = bboxMap.get(label);
+          if (existing) {
+            existing.minX = Math.min(existing.minX, x);
+            existing.minY = Math.min(existing.minY, y);
+            existing.maxX = Math.max(existing.maxX, x);
+            existing.maxY = Math.max(existing.maxY, y);
+            existing.count++;
+            existing.intensitySum += diff;
+          } else {
+            bboxMap.set(label, {
+              minX: x,
+              minY: y,
+              maxX: x,
+              maxY: y,
+              count: 1,
+              intensitySum: diff
+            });
+          }
+        }
+      }
+      const regions = [];
+      for (const [, info] of bboxMap) {
+        if (info.count < minArea)
+          continue;
+        regions.push({
+          bbox: {
+            x: info.minX,
+            y: info.minY,
+            w: info.maxX - info.minX + 1,
+            h: info.maxY - info.minY + 1
+          },
+          pixelCount: info.count,
+          intensity: info.intensitySum / info.count
+        });
+      }
+      return regions;
+    }
+  }
+});
+
+export {
+  require_frame_diff
+};
+//# sourceMappingURL=chunk-YYDM6V2F.mjs.map

package/dist/{chunk-BR2FPGOX.mjs.map → chunk-YYDM6V2F.mjs.map}

@@ -1 +1 @@
-{"version":3,"sources":["../src/addons/motion-detection/frame-diff.ts"],"sourcesContent":["import type { BoundingBox } from '@camstack/types'\n\nexport interface MotionRegion {\n  readonly bbox: BoundingBox\n  readonly pixelCount: number\n  readonly intensity: number\n}\n\n/**\n * Detect motion by frame differencing.\n *\n * @param current   - Grayscale pixel array for the current frame (Uint8Array, length = width * height)\n * @param previous  - Grayscale pixel array for the previous frame\n * @param width     - Frame width in pixels\n * @param height    - Frame height in pixels\n * @param threshold - Pixel diff threshold 0-255; differences below this are ignored\n * @param minArea   - Minimum number of changed pixels for a region to be reported\n */\nexport function detectMotion(\n  current: Uint8Array,\n  previous: Uint8Array,\n  width: number,\n  height: number,\n  threshold: number,\n  minArea: number,\n): MotionRegion[] {\n  const numPixels = width * height\n\n  // Step 1: Compute binary mask — 1 where abs(current - previous) > threshold\n  const mask = new Uint8Array(numPixels)\n  for (let i = 0; i < numPixels; i++) {\n    mask[i] = Math.abs((current[i] ?? 0) - (previous[i] ?? 0)) > threshold ? 1 : 0\n  }\n\n  // Step 2: Two-pass connected component labeling\n  const labels = new Int32Array(numPixels).fill(0)\n  const parent = new Int32Array(numPixels + 1).fill(0)\n  let nextLabel = 1\n\n  // Union-Find helpers\n  function findRoot(x: number): number {\n    while (parent[x] !== x) {\n      parent[x] = parent[parent[x]!]! // path compression\n      x = parent[x]!\n    }\n    return x\n  }\n\n  function union(a: number, b: number): number {\n    const ra = findRoot(a)\n    const rb = findRoot(b)\n    if (ra !== rb) parent[rb] = ra\n    return ra\n  }\n\n  // Initialize parent array as identity\n  for (let i = 0; i <= numPixels; i++) {\n    parent[i] = i\n  }\n\n  // First pass: assign provisional labels\n  for (let y = 0; y < height; y++) {\n    for (let x = 0; x < width; x++) {\n      const idx = y * width + x\n      if (!mask[idx]) continue\n\n      const above = y > 0 ? labels[(y - 1) * width + x] ?? 0 : 0\n      const left = x > 0 ? labels[y * width + (x - 1)] ?? 0 : 0\n\n      if (above === 0 && left === 0) {\n        labels[idx] = nextLabel\n        parent[nextLabel] = nextLabel\n        nextLabel++\n      } else if (above !== 0 && left === 0) {\n        labels[idx] = above\n      } else if (above === 0 && left !== 0) {\n        labels[idx] = left\n      } else {\n        // Both neighbors — merge\n        labels[idx] = union(above, left)\n      }\n    }\n  }\n\n  // Second pass: resolve all labels to roots\n  for (let i = 0; i < numPixels; i++) {\n    if (labels[i]) {\n      labels[i] = findRoot(labels[i]!)\n    }\n  }\n\n  // Step 3: Collect bounding boxes and pixel counts per root label\n  const bboxMap = new Map<\n    number,\n    { minX: number; minY: number; maxX: number; maxY: number; count: number; intensitySum: number }\n  >()\n\n  for (let y = 0; y < height; y++) {\n    for (let x = 0; x < width; x++) {\n      const idx = y * width + x\n      const label = labels[idx]\n      if (!label) continue\n\n      const diff = Math.abs((current[idx] ?? 0) - (previous[idx] ?? 0))\n      const existing = bboxMap.get(label)\n      if (existing) {\n        existing.minX = Math.min(existing.minX, x)\n        existing.minY = Math.min(existing.minY, y)\n        existing.maxX = Math.max(existing.maxX, x)\n        existing.maxY = Math.max(existing.maxY, y)\n        existing.count++\n        existing.intensitySum += diff\n      } else {\n        bboxMap.set(label, {\n          minX: x,\n          minY: y,\n          maxX: x,\n          maxY: y,\n          count: 1,\n          intensitySum: diff,\n        })\n      }\n    }\n  }\n\n  // Step 4: Filter by minimum area and build result\n  const regions: MotionRegion[] = []\n  for (const [, info] of bboxMap) {\n    if (info.count < minArea) continue\n    regions.push({\n      bbox: {\n        x: info.minX,\n        y: info.minY,\n        w: info.maxX - info.minX + 1,\n        h: info.maxY - info.minY + 1,\n      },\n      pixelCount: info.count,\n      intensity: info.intensitySum / info.count,\n    })\n  }\n\n  return regions\n}\n"],"mappings":";AAkBO,SAAS,aACd,SACA,UACA,OACA,QACA,WACA,SACgB;AAChB,QAAM,YAAY,QAAQ;AAG1B,QAAM,OAAO,IAAI,WAAW,SAAS;AACrC,WAAS,IAAI,GAAG,IAAI,WAAW,KAAK;AAClC,SAAK,CAAC,IAAI,KAAK,KAAK,QAAQ,CAAC,KAAK,MAAM,SAAS,CAAC,KAAK,EAAE,IAAI,YAAY,IAAI;AAAA,EAC/E;AAGA,QAAM,SAAS,IAAI,WAAW,SAAS,EAAE,KAAK,CAAC;AAC/C,QAAM,SAAS,IAAI,WAAW,YAAY,CAAC,EAAE,KAAK,CAAC;AACnD,MAAI,YAAY;AAGhB,WAAS,SAAS,GAAmB;AACnC,WAAO,OAAO,CAAC,MAAM,GAAG;AACtB,aAAO,CAAC,IAAI,OAAO,OAAO,CAAC,CAAE;AAC7B,UAAI,OAAO,CAAC;AAAA,IACd;AACA,WAAO;AAAA,EACT;AAEA,WAAS,MAAM,GAAW,GAAmB;AAC3C,UAAM,KAAK,SAAS,CAAC;AACrB,UAAM,KAAK,SAAS,CAAC;AACrB,QAAI,OAAO,GAAI,QAAO,EAAE,IAAI;AAC5B,WAAO;AAAA,EACT;AAGA,WAAS,IAAI,GAAG,KAAK,WAAW,KAAK;AACnC,WAAO,CAAC,IAAI;AAAA,EACd;AAGA,WAAS,IAAI,GAAG,IAAI,QAAQ,KAAK;AAC/B,aAAS,IAAI,GAAG,IAAI,OAAO,KAAK;AAC9B,YAAM,MAAM,IAAI,QAAQ;AACxB,UAAI,CAAC,KAAK,GAAG,EAAG;AAEhB,YAAM,QAAQ,IAAI,IAAI,QAAQ,IAAI,KAAK,QAAQ,CAAC,KAAK,IAAI;AACzD,YAAM,OAAO,IAAI,IAAI,OAAO,IAAI,SAAS,IAAI,EAAE,KAAK,IAAI;AAExD,UAAI,UAAU,KAAK,SAAS,GAAG;AAC7B,eAAO,GAAG,IAAI;AACd,eAAO,SAAS,IAAI;AACpB;AAAA,MACF,WAAW,UAAU,KAAK,SAAS,GAAG;AACpC,eAAO,GAAG,IAAI;AAAA,MAChB,WAAW,UAAU,KAAK,SAAS,GAAG;AACpC,eAAO,GAAG,IAAI;AAAA,MAChB,OAAO;AAEL,eAAO,GAAG,IAAI,MAAM,OAAO,IAAI;AAAA,MACjC;AAAA,IACF;AAAA,EACF;AAGA,WAAS,IAAI,GAAG,IAAI,WAAW,KAAK;AAClC,QAAI,OAAO,CAAC,GAAG;AACb,aAAO,CAAC,IAAI,SAAS,OAAO,CAAC,CAAE;AAAA,IACjC;AAAA,EACF;AAGA,QAAM,UAAU,oBAAI,IAGlB;AAEF,WAAS,IAAI,GAAG,IAAI,QAAQ,KAAK;AAC/B,aAAS,IAAI,GAAG,IAAI,OAAO,KAAK;AAC9B,YAAM,MAAM,IAAI,QAAQ;AACxB,YAAM,QAAQ,OAAO,GAAG;AACxB,UAAI,CAAC,MAAO;AAEZ,YAAM,OAAO,KAAK,KAAK,QAAQ,GAAG,KAAK,MAAM,SAAS,GAAG,KAAK,EAAE;AAChE,YAAM,WAAW,QAAQ,IAAI,KAAK;AAClC,UAAI,UAAU;AACZ,iBAAS,OAAO,KAAK,IAAI,SAAS,MAAM,CAAC;AACzC,iBAAS,OAAO,KAAK,IAAI,SAAS,MAAM,CAAC;AACzC,iBAAS,OAAO,KAAK,IAAI,SAAS,MAAM,CAAC;AACzC,iBAAS,OAAO,KAAK,IAAI,SAAS,MAAM,CAAC;AACzC,iBAAS;AACT,iBAAS,gBAAgB;AAAA,MAC3B,OAAO;AACL,gBAAQ,IAAI,OAAO;AAAA,UACjB,MAAM;AAAA,UACN,MAAM;AAAA,UACN,MAAM;AAAA,UACN,MAAM;AAAA,UACN,OAAO;AAAA,UACP,cAAc;AAAA,QAChB,CAAC;AAAA,MACH;AAAA,IACF;AAAA,EACF;AAGA,QAAM,UAA0B,CAAC;AACjC,aAAW,CAAC,EAAE,IAAI,KAAK,SAAS;AAC9B,QAAI,KAAK,QAAQ,QAAS;AAC1B,YAAQ,KAAK;AAAA,MACX,MAAM;AAAA,QACJ,GAAG,KAAK;AAAA,QACR,GAAG,KAAK;AAAA,QACR,GAAG,KAAK,OAAO,KAAK,OAAO;AAAA,QAC3B,GAAG,KAAK,OAAO,KAAK,OAAO;AAAA,MAC7B;AAAA,MACA,YAAY,KAAK;AAAA,MACjB,WAAW,KAAK,eAAe,KAAK;AAAA,IACtC,CAAC;AAAA,EACH;AAEA,SAAO;AACT;","names":[]}
+{"version":3,"sources":["../src/addons/motion-detection/frame-diff.ts"],"sourcesContent":["import type { BoundingBox } from '@camstack/types'\n\nexport interface MotionRegion {\n  readonly bbox: BoundingBox\n  readonly pixelCount: number\n  readonly intensity: number\n}\n\n/**\n * Detect motion by frame differencing.\n *\n * @param current   - Grayscale pixel array for the current frame (Uint8Array, length = width * height)\n * @param previous  - Grayscale pixel array for the previous frame\n * @param width     - Frame width in pixels\n * @param height    - Frame height in pixels\n * @param threshold - Pixel diff threshold 0-255; differences below this are ignored\n * @param minArea   - Minimum number of changed pixels for a region to be reported\n */\nexport function detectMotion(\n  current: Uint8Array,\n  previous: Uint8Array,\n  width: number,\n  height: number,\n  threshold: number,\n  minArea: number,\n): MotionRegion[] {\n  const numPixels = width * height\n\n  // Step 1: Compute binary mask — 1 where abs(current - previous) > threshold\n  const mask = new Uint8Array(numPixels)\n  for (let i = 0; i < numPixels; i++) {\n    mask[i] = Math.abs((current[i] ?? 0) - (previous[i] ?? 0)) > threshold ? 1 : 0\n  }\n\n  // Step 2: Two-pass connected component labeling\n  const labels = new Int32Array(numPixels).fill(0)\n  const parent = new Int32Array(numPixels + 1).fill(0)\n  let nextLabel = 1\n\n  // Union-Find helpers\n  function findRoot(x: number): number {\n    while (parent[x] !== x) {\n      parent[x] = parent[parent[x]!]! // path compression\n      x = parent[x]!\n    }\n    return x\n  }\n\n  function union(a: number, b: number): number {\n    const ra = findRoot(a)\n    const rb = findRoot(b)\n    if (ra !== rb) parent[rb] = ra\n    return ra\n  }\n\n  // Initialize parent array as identity\n  for (let i = 0; i <= numPixels; i++) {\n    parent[i] = i\n  }\n\n  // First pass: assign provisional labels\n  for (let y = 0; y < height; y++) {\n    for (let x = 0; x < width; x++) {\n      const idx = y * width + x\n      if (!mask[idx]) continue\n\n      const above = y > 0 ? labels[(y - 1) * width + x] ?? 0 : 0\n      const left = x > 0 ? labels[y * width + (x - 1)] ?? 0 : 0\n\n      if (above === 0 && left === 0) {\n        labels[idx] = nextLabel\n        parent[nextLabel] = nextLabel\n        nextLabel++\n      } else if (above !== 0 && left === 0) {\n        labels[idx] = above\n      } else if (above === 0 && left !== 0) {\n        labels[idx] = left\n      } else {\n        // Both neighbors — merge\n        labels[idx] = union(above, left)\n      }\n    }\n  }\n\n  // Second pass: resolve all labels to roots\n  for (let i = 0; i < numPixels; i++) {\n    if (labels[i]) {\n      labels[i] = findRoot(labels[i]!)\n    }\n  }\n\n  // Step 3: Collect bounding boxes and pixel counts per root label\n  const bboxMap = new Map<\n    number,\n    { minX: number; minY: number; maxX: number; maxY: number; count: number; intensitySum: number }\n  >()\n\n  for (let y = 0; y < height; y++) {\n    for (let x = 0; x < width; x++) {\n      const idx = y * width + x\n      const label = labels[idx]\n      if (!label) continue\n\n      const diff = Math.abs((current[idx] ?? 0) - (previous[idx] ?? 0))\n      const existing = bboxMap.get(label)\n      if (existing) {\n        existing.minX = Math.min(existing.minX, x)\n        existing.minY = Math.min(existing.minY, y)\n        existing.maxX = Math.max(existing.maxX, x)\n        existing.maxY = Math.max(existing.maxY, y)\n        existing.count++\n        existing.intensitySum += diff\n      } else {\n        bboxMap.set(label, {\n          minX: x,\n          minY: y,\n          maxX: x,\n          maxY: y,\n          count: 1,\n          intensitySum: diff,\n        })\n      }\n    }\n  }\n\n  // Step 4: Filter by minimum area and build result\n  const regions: MotionRegion[] = []\n  for (const [, info] of bboxMap) {\n    if (info.count < minArea) continue\n    regions.push({\n      bbox: {\n        x: info.minX,\n        y: info.minY,\n        w: info.maxX - info.minX + 1,\n        h: info.maxY - info.minY + 1,\n      },\n      pixelCount: info.count,\n      intensity: info.intensitySum / info.count,\n    })\n  }\n\n  return regions\n}\n"],"mappings":";;;;;;;;;AAkBA,YAAA,eAAA;AAAA,aAAgB,aACd,SACA,UACA,OACA,QACA,WACA,SAAe;AAEf,YAAM,YAAY,QAAQ;AAG1B,YAAM,OAAO,IAAI,WAAW,SAAS;AACrC,eAAS,IAAI,GAAG,IAAI,WAAW,KAAK;AAClC,aAAK,CAAC,IAAI,KAAK,KAAK,QAAQ,CAAC,KAAK,MAAM,SAAS,CAAC,KAAK,EAAE,IAAI,YAAY,IAAI;MAC/E;AAGA,YAAM,SAAS,IAAI,WAAW,SAAS,EAAE,KAAK,CAAC;AAC/C,YAAM,SAAS,IAAI,WAAW,YAAY,CAAC,EAAE,KAAK,CAAC;AACnD,UAAI,YAAY;AAGhB,eAAS,SAAS,GAAS;AACzB,eAAO,OAAO,CAAC,MAAM,GAAG;AACtB,iBAAO,CAAC,IAAI,OAAO,OAAO,CAAC,CAAE;AAC7B,cAAI,OAAO,CAAC;QACd;AACA,eAAO;MACT;AAEA,eAAS,MAAM,GAAW,GAAS;AACjC,cAAM,KAAK,SAAS,CAAC;AACrB,cAAM,KAAK,SAAS,CAAC;AACrB,YAAI,OAAO;AAAI,iBAAO,EAAE,IAAI;AAC5B,eAAO;MACT;AAGA,eAAS,IAAI,GAAG,KAAK,WAAW,KAAK;AACnC,eAAO,CAAC,IAAI;MACd;AAGA,eAAS,IAAI,GAAG,IAAI,QAAQ,KAAK;AAC/B,iBAAS,IAAI,GAAG,IAAI,OAAO,KAAK;AAC9B,gBAAM,MAAM,IAAI,QAAQ;AACxB,cAAI,CAAC,KAAK,GAAG;AAAG;AAEhB,gBAAM,QAAQ,IAAI,IAAI,QAAQ,IAAI,KAAK,QAAQ,CAAC,KAAK,IAAI;AACzD,gBAAM,OAAO,IAAI,IAAI,OAAO,IAAI,SAAS,IAAI,EAAE,KAAK,IAAI;AAExD,cAAI,UAAU,KAAK,SAAS,GAAG;AAC7B,mBAAO,GAAG,IAAI;AACd,mBAAO,SAAS,IAAI;AACpB;UACF,WAAW,UAAU,KAAK,SAAS,GAAG;AACpC,mBAAO,GAAG,IAAI;UAChB,WAAW,UAAU,KAAK,SAAS,GAAG;AACpC,mBAAO,GAAG,IAAI;UAChB,OAAO;AAEL,mBAAO,GAAG,IAAI,MAAM,OAAO,IAAI;UACjC;QACF;MACF;AAGA,eAAS,IAAI,GAAG,IAAI,WAAW,KAAK;AAClC,YAAI,OAAO,CAAC,GAAG;AACb,iBAAO,CAAC,IAAI,SAAS,OAAO,CAAC,CAAE;QACjC;MACF;AAGA,YAAM,UAAU,oBAAI,IAAG;AAKvB,eAAS,IAAI,GAAG,IAAI,QAAQ,KAAK;AAC/B,iBAAS,IAAI,GAAG,IAAI,OAAO,KAAK;AAC9B,gBAAM,MAAM,IAAI,QAAQ;AACxB,gBAAM,QAAQ,OAAO,GAAG;AACxB,cAAI,CAAC;AAAO;AAEZ,gBAAM,OAAO,KAAK,KAAK,QAAQ,GAAG,KAAK,MAAM,SAAS,GAAG,KAAK,EAAE;AAChE,gBAAM,WAAW,QAAQ,IAAI,KAAK;AAClC,cAAI,UAAU;AACZ,qBAAS,OAAO,KAAK,IAAI,SAAS,MAAM,CAAC;AACzC,qBAAS,OAAO,KAAK,IAAI,SAAS,MAAM,CAAC;AACzC,qBAAS,OAAO,KAAK,IAAI,SAAS,MAAM,CAAC;AACzC,qBAAS,OAAO,KAAK,IAAI,SAAS,MAAM,CAAC;AACzC,qBAAS;AACT,qBAAS,gBAAgB;UAC3B,OAAO;AACL,oBAAQ,IAAI,OAAO;cACjB,MAAM;cACN,MAAM;cACN,MAAM;cACN,MAAM;cACN,OAAO;cACP,cAAc;aACf;UACH;QACF;MACF;AAGA,YAAM,UAA0B,CAAA;AAChC,iBAAW,CAAC,EAAE,IAAI,KAAK,SAAS;AAC9B,YAAI,KAAK,QAAQ;AAAS;AAC1B,gBAAQ,KAAK;UACX,MAAM;YACJ,GAAG,KAAK;YACR,GAAG,KAAK;YACR,GAAG,KAAK,OAAO,KAAK,OAAO;YAC3B,GAAG,KAAK,OAAO,KAAK,OAAO;;UAE7B,YAAY,KAAK;UACjB,WAAW,KAAK,eAAe,KAAK;SACrC;MACH;AAEA,aAAO;IACT;;;","names":[]}