@camstack/vision 0.1.0

package/dist/chunk-6OR5TE7A.mjs

@@ -0,0 +1,101 @@
+// src/shared/image-utils.ts
+import sharp from "sharp";
+async function jpegToRgb(jpeg) {
+  const { data, info } = await sharp(jpeg).removeAlpha().raw().toBuffer({ resolveWithObject: true });
+  return { data, width: info.width, height: info.height };
+}
+async function cropRegion(jpeg, roi) {
+  return sharp(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 sharp(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 sharp(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 sharp(jpeg).resize(targetWidth, targetHeight).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 {
+  jpegToRgb,
+  cropRegion,
+  letterbox,
+  resizeAndNormalize,
+  rgbToGrayscale
+};
+//# sourceMappingURL=chunk-6OR5TE7A.mjs.map

package/dist/chunk-6OR5TE7A.mjs.map

@@ -0,0 +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)\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,YAAY,EAChC,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":[]}

package/dist/chunk-7SZAISGP.mjs

@@ -0,0 +1,210 @@
+import {
+  cropRegion,
+  resizeAndNormalize
+} from "./chunk-6OR5TE7A.mjs";
+import {
+  resolveEngine
+} from "./chunk-J3IUBPRE.mjs";
+
+// src/addons/animal-classifier/index.ts
+import { ANIMAL_TYPE_MODELS } from "@camstack/types";
+var ANIMAL_TYPE_LABEL = { id: "animal-type", name: "Animal Type" };
+var ANIMAL_TYPE_LABELS = [ANIMAL_TYPE_LABEL];
+var ANIMAL_CLASS_MAP = { mapping: {}, preserveOriginal: true };
+var ANIMAL_10_CLASSES = [
+  "cat",
+  "cow",
+  "dog",
+  "dolphin",
+  "eagle",
+  "giant panda",
+  "horse",
+  "monkey",
+  "sheep",
+  "spider"
+];
+function softmax(logits) {
+  const max = logits.reduce((a, b) => Math.max(a, b), -Infinity);
+  const exps = logits.map((v) => Math.exp(v - max));
+  const sum = exps.reduce((a, b) => a + b, 0);
+  return exps.map((v) => v / sum);
+}
+var AnimalClassifierAddon = class {
+  id = "animal-classifier";
+  slot = "classifier";
+  inputClasses = ["animal"];
+  outputClasses = ["animal-type:*"];
+  slotPriority = 0;
+  requiredSteps = [];
+  manifest = {
+    id: "animal-classifier",
+    name: "Animal Classifier",
+    version: "0.1.0",
+    description: "ViT-based animal type classifier \u2014 10 common species",
+    packageName: "@camstack/vision",
+    slot: "classifier",
+    inputClasses: ["animal"],
+    outputClasses: ["animal-type:*"],
+    supportsCustomModels: false,
+    mayRequirePython: false,
+    defaultConfig: {
+      modelId: "animals-10",
+      runtime: "auto",
+      backend: "cpu",
+      minConfidence: 0.3
+    }
+  };
+  engine;
+  modelEntry;
+  minConfidence = 0.3;
+  async initialize(ctx) {
+    const cfg = ctx.addonConfig;
+    const modelId = cfg["modelId"] ?? "animals-10";
+    const runtime = cfg["runtime"] ?? "auto";
+    const backend = cfg["backend"] ?? "cpu";
+    this.minConfidence = cfg["minConfidence"] ?? 0.3;
+    const entry = ANIMAL_TYPE_MODELS.find((m) => m.id === modelId);
+    if (!entry) {
+      throw new Error(`AnimalClassifierAddon: unknown modelId "${modelId}"`);
+    }
+    this.modelEntry = entry;
+    const resolved = await resolveEngine({
+      runtime,
+      backend,
+      modelEntry: entry,
+      modelsDir: ctx.locationPaths.models
+    });
+    this.engine = resolved.engine;
+  }
+  async classify(input) {
+    const start = Date.now();
+    const { width: inputW, height: inputH } = this.modelEntry.inputSize;
+    const animalCrop = await cropRegion(input.frame.data, input.roi);
+    const normalized = await resizeAndNormalize(animalCrop, inputW, inputH, "imagenet", "nchw");
+    const rawOutput = await this.engine.run(normalized, [1, 3, inputH, inputW]);
+    const probs = softmax(rawOutput);
+    let maxIdx = 0;
+    let maxScore = probs[0] ?? 0;
+    for (let i = 1; i < probs.length; i++) {
+      const score = probs[i] ?? 0;
+      if (score > maxScore) {
+        maxScore = score;
+        maxIdx = i;
+      }
+    }
+    if (maxScore < this.minConfidence) {
+      return {
+        classifications: [],
+        inferenceMs: Date.now() - start,
+        modelId: this.modelEntry.id
+      };
+    }
+    const label = ANIMAL_10_CLASSES[maxIdx] ?? `animal_${maxIdx}`;
+    return {
+      classifications: [
+        {
+          class: label,
+          score: maxScore
+        }
+      ],
+      inferenceMs: Date.now() - start,
+      modelId: this.modelEntry.id
+    };
+  }
+  async shutdown() {
+    await this.engine?.dispose();
+  }
+  getConfigSchema() {
+    return {
+      sections: [
+        {
+          id: "model",
+          title: "Model",
+          columns: 1,
+          fields: [
+            {
+              key: "modelId",
+              label: "Model",
+              type: "model-selector",
+              catalog: [...ANIMAL_TYPE_MODELS],
+              allowCustom: false,
+              allowConversion: false,
+              acceptFormats: ["onnx", "coreml", "openvino"],
+              requiredMetadata: ["inputSize", "labels"],
+              outputFormatHint: "classification"
+            }
+          ]
+        },
+        {
+          id: "thresholds",
+          title: "Classification Settings",
+          columns: 1,
+          fields: [
+            {
+              key: "minConfidence",
+              label: "Minimum Confidence",
+              type: "slider",
+              min: 0.05,
+              max: 1,
+              step: 0.05,
+              default: 0.3
+            }
+          ]
+        },
+        {
+          id: "runtime",
+          title: "Runtime",
+          columns: 2,
+          fields: [
+            {
+              key: "runtime",
+              label: "Runtime",
+              type: "select",
+              options: [
+                { value: "auto", label: "Auto (recommended)" },
+                { value: "onnx", label: "ONNX Runtime" },
+                { value: "coreml", label: "CoreML (Apple)" }
+              ]
+            },
+            {
+              key: "backend",
+              label: "Backend",
+              type: "select",
+              dependsOn: { runtime: "onnx" },
+              options: [
+                { value: "cpu", label: "CPU" },
+                { value: "coreml", label: "CoreML" },
+                { value: "cuda", label: "CUDA (NVIDIA)" }
+              ]
+            }
+          ]
+        }
+      ]
+    };
+  }
+  getClassMap() {
+    return ANIMAL_CLASS_MAP;
+  }
+  getModelCatalog() {
+    return [...ANIMAL_TYPE_MODELS];
+  }
+  getAvailableModels() {
+    return [];
+  }
+  getActiveLabels() {
+    return ANIMAL_TYPE_LABELS;
+  }
+  async probe() {
+    return {
+      available: true,
+      runtime: this.engine?.runtime ?? "onnx",
+      device: this.engine?.device ?? "cpu",
+      capabilities: ["fp32"]
+    };
+  }
+};
+
+export {
+  AnimalClassifierAddon
+};
+//# sourceMappingURL=chunk-7SZAISGP.mjs.map

package/dist/chunk-7SZAISGP.mjs.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../src/addons/animal-classifier/index.ts"],"sourcesContent":["import type {\n  IClassifierProvider,\n  IDetectionAddon,\n  AddonManifest,\n  AddonContext,\n  CropInput,\n  ClassifierOutput,\n  ConfigUISchema,\n  ClassMapDefinition,\n  ProbeResult,\n  ModelCatalogEntry,\n  DetectionModel,\n  LabelDefinition,\n  IInferenceEngine,\n} from '@camstack/types'\nimport { ANIMAL_TYPE_MODELS } from '@camstack/types'\nimport { cropRegion, resizeAndNormalize } from '../../shared/image-utils.js'\nimport { resolveEngine } from '../../shared/engine-resolver.js'\n\nconst ANIMAL_TYPE_LABEL: LabelDefinition = { id: 'animal-type', name: 'Animal Type' }\nconst ANIMAL_TYPE_LABELS: readonly LabelDefinition[] = [ANIMAL_TYPE_LABEL]\nconst ANIMAL_CLASS_MAP: ClassMapDefinition = { mapping: {}, preserveOriginal: true }\n\nconst ANIMAL_10_CLASSES = [\n  'cat',\n  'cow',\n  'dog',\n  'dolphin',\n  'eagle',\n  'giant panda',\n  'horse',\n  'monkey',\n  'sheep',\n  'spider',\n] as const\n\nfunction softmax(logits: Float32Array): Float32Array {\n  const max = logits.reduce((a, b) => Math.max(a, b), -Infinity)\n  const exps = logits.map((v) => Math.exp(v - max))\n  const sum = exps.reduce((a, b) => a + b, 0)\n  return exps.map((v) => v / sum) as unknown as Float32Array\n}\n\nexport default class AnimalClassifierAddon implements IClassifierProvider, IDetectionAddon {\n  readonly id = 'animal-classifier'\n  readonly slot = 'classifier' as const\n  readonly inputClasses = ['animal'] as const\n  readonly outputClasses = ['animal-type:*'] as const\n  readonly slotPriority = 0\n  readonly requiredSteps = [] as const\n  readonly manifest: AddonManifest = {\n    id: 'animal-classifier',\n    name: 'Animal Classifier',\n    version: '0.1.0',\n    description: 'ViT-based animal type classifier — 10 common species',\n    packageName: '@camstack/vision',\n    slot: 'classifier',\n    inputClasses: ['animal'],\n    outputClasses: ['animal-type:*'],\n    supportsCustomModels: false,\n    mayRequirePython: false,\n    defaultConfig: {\n      modelId: 'animals-10',\n      runtime: 'auto',\n      backend: 'cpu',\n      minConfidence: 0.3,\n    },\n  }\n\n  private engine!: IInferenceEngine\n  private modelEntry!: ModelCatalogEntry\n  private minConfidence = 0.3\n\n  async initialize(ctx: AddonContext): Promise<void> {\n    const cfg = ctx.addonConfig\n    const modelId = (cfg['modelId'] as string | undefined) ?? 'animals-10'\n    const runtime = (cfg['runtime'] as string | undefined) ?? 'auto'\n    const backend = (cfg['backend'] as string | undefined) ?? 'cpu'\n    this.minConfidence = (cfg['minConfidence'] as number | undefined) ?? 0.3\n\n    const entry = ANIMAL_TYPE_MODELS.find((m) => m.id === modelId)\n    if (!entry) {\n      throw new Error(`AnimalClassifierAddon: unknown modelId \"${modelId}\"`)\n    }\n    this.modelEntry = entry\n\n    const resolved = await resolveEngine({\n      runtime: runtime as 'auto',\n      backend,\n      modelEntry: entry,\n      modelsDir: ctx.locationPaths.models,\n    })\n    this.engine = resolved.engine\n  }\n\n  async classify(input: CropInput): Promise<ClassifierOutput> {\n    const start = Date.now()\n    const { width: inputW, height: inputH } = this.modelEntry.inputSize\n\n    // Crop the animal region\n    const animalCrop = await cropRegion(input.frame.data, input.roi)\n\n    // Resize to 224x224, ImageNet normalization, NCHW\n    const normalized = await resizeAndNormalize(animalCrop, inputW, inputH, 'imagenet', 'nchw')\n\n    // Run inference — output shape: [1, 10]\n    const rawOutput = await this.engine.run(normalized, [1, 3, inputH, inputW])\n\n    // Softmax to get probabilities\n    const probs = softmax(rawOutput)\n\n    // Find argmax\n    let maxIdx = 0\n    let maxScore = probs[0] ?? 0\n    for (let i = 1; i < probs.length; i++) {\n      const score = probs[i] ?? 0\n      if (score > maxScore) {\n        maxScore = score\n        maxIdx = i\n      }\n    }\n\n    if (maxScore < this.minConfidence) {\n      return {\n        classifications: [],\n        inferenceMs: Date.now() - start,\n        modelId: this.modelEntry.id,\n      }\n    }\n\n    const label = ANIMAL_10_CLASSES[maxIdx] ?? `animal_${maxIdx}`\n\n    return {\n      classifications: [\n        {\n          class: label,\n          score: maxScore,\n        },\n      ],\n      inferenceMs: Date.now() - start,\n      modelId: this.modelEntry.id,\n    }\n  }\n\n  async shutdown(): Promise<void> {\n    await this.engine?.dispose()\n  }\n\n  getConfigSchema(): ConfigUISchema {\n    return {\n      sections: [\n        {\n          id: 'model',\n          title: 'Model',\n          columns: 1,\n          fields: [\n            {\n              key: 'modelId',\n              label: 'Model',\n              type: 'model-selector',\n              catalog: [...ANIMAL_TYPE_MODELS],\n              allowCustom: false,\n              allowConversion: false,\n              acceptFormats: ['onnx', 'coreml', 'openvino'],\n              requiredMetadata: ['inputSize', 'labels'],\n              outputFormatHint: 'classification',\n            },\n          ],\n        },\n        {\n          id: 'thresholds',\n          title: 'Classification Settings',\n          columns: 1,\n          fields: [\n            {\n              key: 'minConfidence',\n              label: 'Minimum Confidence',\n              type: 'slider',\n              min: 0.05,\n              max: 1.0,\n              step: 0.05,\n              default: 0.3,\n            },\n          ],\n        },\n        {\n          id: 'runtime',\n          title: 'Runtime',\n          columns: 2,\n          fields: [\n            {\n              key: 'runtime',\n              label: 'Runtime',\n              type: 'select',\n              options: [\n                { value: 'auto', label: 'Auto (recommended)' },\n                { value: 'onnx', label: 'ONNX Runtime' },\n                { value: 'coreml', label: 'CoreML (Apple)' },\n              ],\n            },\n            {\n              key: 'backend',\n              label: 'Backend',\n              type: 'select',\n              dependsOn: { runtime: 'onnx' },\n              options: [\n                { value: 'cpu', label: 'CPU' },\n                { value: 'coreml', label: 'CoreML' },\n                { value: 'cuda', label: 'CUDA (NVIDIA)' },\n              ],\n            },\n          ],\n        },\n      ],\n    }\n  }\n\n  getClassMap(): ClassMapDefinition {\n    return ANIMAL_CLASS_MAP\n  }\n\n  getModelCatalog(): ModelCatalogEntry[] {\n    return [...ANIMAL_TYPE_MODELS]\n  }\n\n  getAvailableModels(): DetectionModel[] {\n    return []\n  }\n\n  getActiveLabels(): readonly LabelDefinition[] {\n    return ANIMAL_TYPE_LABELS\n  }\n\n  async probe(): Promise<ProbeResult> {\n    return {\n      available: true,\n      runtime: this.engine?.runtime ?? 'onnx',\n      device: this.engine?.device ?? 'cpu',\n      capabilities: ['fp32'],\n    }\n  }\n}\n"],"mappings":";;;;;;;;;AAeA,SAAS,0BAA0B;AAInC,IAAM,oBAAqC,EAAE,IAAI,eAAe,MAAM,cAAc;AACpF,IAAM,qBAAiD,CAAC,iBAAiB;AACzE,IAAM,mBAAuC,EAAE,SAAS,CAAC,GAAG,kBAAkB,KAAK;AAEnF,IAAM,oBAAoB;AAAA,EACxB;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AACF;AAEA,SAAS,QAAQ,QAAoC;AACnD,QAAM,MAAM,OAAO,OAAO,CAAC,GAAG,MAAM,KAAK,IAAI,GAAG,CAAC,GAAG,SAAS;AAC7D,QAAM,OAAO,OAAO,IAAI,CAAC,MAAM,KAAK,IAAI,IAAI,GAAG,CAAC;AAChD,QAAM,MAAM,KAAK,OAAO,CAAC,GAAG,MAAM,IAAI,GAAG,CAAC;AAC1C,SAAO,KAAK,IAAI,CAAC,MAAM,IAAI,GAAG;AAChC;AAEA,IAAqB,wBAArB,MAA2F;AAAA,EAChF,KAAK;AAAA,EACL,OAAO;AAAA,EACP,eAAe,CAAC,QAAQ;AAAA,EACxB,gBAAgB,CAAC,eAAe;AAAA,EAChC,eAAe;AAAA,EACf,gBAAgB,CAAC;AAAA,EACjB,WAA0B;AAAA,IACjC,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,SAAS;AAAA,IACT,aAAa;AAAA,IACb,aAAa;AAAA,IACb,MAAM;AAAA,IACN,cAAc,CAAC,QAAQ;AAAA,IACvB,eAAe,CAAC,eAAe;AAAA,IAC/B,sBAAsB;AAAA,IACtB,kBAAkB;AAAA,IAClB,eAAe;AAAA,MACb,SAAS;AAAA,MACT,SAAS;AAAA,MACT,SAAS;AAAA,MACT,eAAe;AAAA,IACjB;AAAA,EACF;AAAA,EAEQ;AAAA,EACA;AAAA,EACA,gBAAgB;AAAA,EAExB,MAAM,WAAW,KAAkC;AACjD,UAAM,MAAM,IAAI;AAChB,UAAM,UAAW,IAAI,SAAS,KAA4B;AAC1D,UAAM,UAAW,IAAI,SAAS,KAA4B;AAC1D,UAAM,UAAW,IAAI,SAAS,KAA4B;AAC1D,SAAK,gBAAiB,IAAI,eAAe,KAA4B;AAErE,UAAM,QAAQ,mBAAmB,KAAK,CAAC,MAAM,EAAE,OAAO,OAAO;AAC7D,QAAI,CAAC,OAAO;AACV,YAAM,IAAI,MAAM,2CAA2C,OAAO,GAAG;AAAA,IACvE;AACA,SAAK,aAAa;AAElB,UAAM,WAAW,MAAM,cAAc;AAAA,MACnC;AAAA,MACA;AAAA,MACA,YAAY;AAAA,MACZ,WAAW,IAAI,cAAc;AAAA,IAC/B,CAAC;AACD,SAAK,SAAS,SAAS;AAAA,EACzB;AAAA,EAEA,MAAM,SAAS,OAA6C;AAC1D,UAAM,QAAQ,KAAK,IAAI;AACvB,UAAM,EAAE,OAAO,QAAQ,QAAQ,OAAO,IAAI,KAAK,WAAW;AAG1D,UAAM,aAAa,MAAM,WAAW,MAAM,MAAM,MAAM,MAAM,GAAG;AAG/D,UAAM,aAAa,MAAM,mBAAmB,YAAY,QAAQ,QAAQ,YAAY,MAAM;AAG1F,UAAM,YAAY,MAAM,KAAK,OAAO,IAAI,YAAY,CAAC,GAAG,GAAG,QAAQ,MAAM,CAAC;AAG1E,UAAM,QAAQ,QAAQ,SAAS;AAG/B,QAAI,SAAS;AACb,QAAI,WAAW,MAAM,CAAC,KAAK;AAC3B,aAAS,IAAI,GAAG,IAAI,MAAM,QAAQ,KAAK;AACrC,YAAM,QAAQ,MAAM,CAAC,KAAK;AAC1B,UAAI,QAAQ,UAAU;AACpB,mBAAW;AACX,iBAAS;AAAA,MACX;AAAA,IACF;AAEA,QAAI,WAAW,KAAK,eAAe;AACjC,aAAO;AAAA,QACL,iBAAiB,CAAC;AAAA,QAClB,aAAa,KAAK,IAAI,IAAI;AAAA,QAC1B,SAAS,KAAK,WAAW;AAAA,MAC3B;AAAA,IACF;AAEA,UAAM,QAAQ,kBAAkB,MAAM,KAAK,UAAU,MAAM;AAE3D,WAAO;AAAA,MACL,iBAAiB;AAAA,QACf;AAAA,UACE,OAAO;AAAA,UACP,OAAO;AAAA,QACT;AAAA,MACF;AAAA,MACA,aAAa,KAAK,IAAI,IAAI;AAAA,MAC1B,SAAS,KAAK,WAAW;AAAA,IAC3B;AAAA,EACF;AAAA,EAEA,MAAM,WAA0B;AAC9B,UAAM,KAAK,QAAQ,QAAQ;AAAA,EAC7B;AAAA,EAEA,kBAAkC;AAChC,WAAO;AAAA,MACL,UAAU;AAAA,QACR;AAAA,UACE,IAAI;AAAA,UACJ,OAAO;AAAA,UACP,SAAS;AAAA,UACT,QAAQ;AAAA,YACN;AAAA,cACE,KAAK;AAAA,cACL,OAAO;AAAA,cACP,MAAM;AAAA,cACN,SAAS,CAAC,GAAG,kBAAkB;AAAA,cAC/B,aAAa;AAAA,cACb,iBAAiB;AAAA,cACjB,eAAe,CAAC,QAAQ,UAAU,UAAU;AAAA,cAC5C,kBAAkB,CAAC,aAAa,QAAQ;AAAA,cACxC,kBAAkB;AAAA,YACpB;AAAA,UACF;AAAA,QACF;AAAA,QACA;AAAA,UACE,IAAI;AAAA,UACJ,OAAO;AAAA,UACP,SAAS;AAAA,UACT,QAAQ;AAAA,YACN;AAAA,cACE,KAAK;AAAA,cACL,OAAO;AAAA,cACP,MAAM;AAAA,cACN,KAAK;AAAA,cACL,KAAK;AAAA,cACL,MAAM;AAAA,cACN,SAAS;AAAA,YACX;AAAA,UACF;AAAA,QACF;AAAA,QACA;AAAA,UACE,IAAI;AAAA,UACJ,OAAO;AAAA,UACP,SAAS;AAAA,UACT,QAAQ;AAAA,YACN;AAAA,cACE,KAAK;AAAA,cACL,OAAO;AAAA,cACP,MAAM;AAAA,cACN,SAAS;AAAA,gBACP,EAAE,OAAO,QAAQ,OAAO,qBAAqB;AAAA,gBAC7C,EAAE,OAAO,QAAQ,OAAO,eAAe;AAAA,gBACvC,EAAE,OAAO,UAAU,OAAO,iBAAiB;AAAA,cAC7C;AAAA,YACF;AAAA,YACA;AAAA,cACE,KAAK;AAAA,cACL,OAAO;AAAA,cACP,MAAM;AAAA,cACN,WAAW,EAAE,SAAS,OAAO;AAAA,cAC7B,SAAS;AAAA,gBACP,EAAE,OAAO,OAAO,OAAO,MAAM;AAAA,gBAC7B,EAAE,OAAO,UAAU,OAAO,SAAS;AAAA,gBACnC,EAAE,OAAO,QAAQ,OAAO,gBAAgB;AAAA,cAC1C;AAAA,YACF;AAAA,UACF;AAAA,QACF;AAAA,MACF;AAAA,IACF;AAAA,EACF;AAAA,EAEA,cAAkC;AAChC,WAAO;AAAA,EACT;AAAA,EAEA,kBAAuC;AACrC,WAAO,CAAC,GAAG,kBAAkB;AAAA,EAC/B;AAAA,EAEA,qBAAuC;AACrC,WAAO,CAAC;AAAA,EACV;AAAA,EAEA,kBAA8C;AAC5C,WAAO;AAAA,EACT;AAAA,EAEA,MAAM,QAA8B;AAClC,WAAO;AAAA,MACL,WAAW;AAAA,MACX,SAAS,KAAK,QAAQ,WAAW;AAAA,MACjC,QAAQ,KAAK,QAAQ,UAAU;AAAA,MAC/B,cAAc,CAAC,MAAM;AAAA,IACvB;AAAA,EACF;AACF;","names":[]}

package/dist/chunk-AD2TFYZA.mjs

@@ -0,0 +1,235 @@
+import {
+  nms
+} from "./chunk-KUO2BVFY.mjs";
+import {
+  cropRegion,
+  letterbox
+} from "./chunk-6OR5TE7A.mjs";
+import {
+  resolveEngine
+} from "./chunk-J3IUBPRE.mjs";
+
+// src/addons/face-detection/index.ts
+import { FACE_DETECTION_MODELS } from "@camstack/types";
+
+// src/shared/postprocess/scrfd.ts
+var STRIDES = [8, 16, 32];
+var NUM_ANCHORS_PER_STRIDE = 2;
+function generateAnchors(stride, inputSize) {
+  const featureSize = Math.ceil(inputSize / stride);
+  const anchors = [];
+  for (let y = 0; y < featureSize; y++) {
+    for (let x = 0; x < featureSize; x++) {
+      for (let k = 0; k < NUM_ANCHORS_PER_STRIDE; k++) {
+        anchors.push({
+          cx: (x + 0.5) * stride,
+          cy: (y + 0.5) * stride
+        });
+      }
+    }
+  }
+  return anchors;
+}
+function scrfdPostprocess(outputs, confidence, inputSize, originalWidth, originalHeight) {
+  const scaleX = originalWidth / inputSize;
+  const scaleY = originalHeight / inputSize;
+  const candidates = [];
+  for (const stride of STRIDES) {
+    const scoreKey = Object.keys(outputs).find((k) => k.includes(`score_${stride}`) || k.includes(`_${stride}_score`));
+    const bboxKey = Object.keys(outputs).find((k) => k.includes(`bbox_${stride}`) || k.includes(`_${stride}_bbox`));
+    const kpsKey = Object.keys(outputs).find((k) => k.includes(`kps_${stride}`) || k.includes(`_${stride}_kps`));
+    if (!scoreKey || !bboxKey) continue;
+    const scores = outputs[scoreKey];
+    const bboxes = outputs[bboxKey];
+    const kps = kpsKey ? outputs[kpsKey] : void 0;
+    const anchors = generateAnchors(stride, inputSize);
+    const n = anchors.length;
+    for (let i = 0; i < n; i++) {
+      const score = scores[i];
+      if (score < confidence) continue;
+      const anchor = anchors[i];
+      const x1 = anchor.cx - bboxes[i * 4] * stride;
+      const y1 = anchor.cy - bboxes[i * 4 + 1] * stride;
+      const x2 = anchor.cx + bboxes[i * 4 + 2] * stride;
+      const y2 = anchor.cy + bboxes[i * 4 + 3] * stride;
+      const bbox = {
+        x: x1 * scaleX,
+        y: y1 * scaleY,
+        w: (x2 - x1) * scaleX,
+        h: (y2 - y1) * scaleY
+      };
+      let landmarks;
+      if (kps) {
+        const pts = [];
+        for (let p = 0; p < 5; p++) {
+          pts.push({
+            x: (anchor.cx + kps[i * 10 + p * 2] * stride) * scaleX,
+            y: (anchor.cy + kps[i * 10 + p * 2 + 1] * stride) * scaleY
+          });
+        }
+        landmarks = pts;
+      }
+      candidates.push({ bbox, score, landmarks });
+    }
+  }
+  if (candidates.length === 0) return [];
+  const keptIndices = nms(candidates, 0.45);
+  return keptIndices.map((idx) => {
+    const { bbox, score, landmarks } = candidates[idx];
+    return {
+      class: "face",
+      originalClass: "face",
+      score,
+      bbox,
+      ...landmarks ? { landmarks } : {}
+    };
+  });
+}
+
+// src/addons/face-detection/index.ts
+var FACE_LABEL = { id: "face", name: "Face" };
+var FACE_LABELS = [FACE_LABEL];
+var FACE_CLASS_MAP = { mapping: {}, preserveOriginal: true };
+var FaceDetectionAddon = class {
+  id = "face-detection";
+  slot = "cropper";
+  inputClasses = ["person"];
+  outputClasses = ["face"];
+  slotPriority = 0;
+  manifest = {
+    id: "face-detection",
+    name: "Face Detection",
+    version: "0.1.0",
+    description: "SCRFD-based face detector \u2014 crops face regions from person detections",
+    packageName: "@camstack/vision",
+    slot: "cropper",
+    inputClasses: ["person"],
+    outputClasses: ["face"],
+    supportsCustomModels: false,
+    mayRequirePython: false,
+    defaultConfig: {
+      modelId: "scrfd-500m",
+      runtime: "auto",
+      backend: "cpu",
+      confidence: 0.5
+    }
+  };
+  engine;
+  modelEntry;
+  confidence = 0.5;
+  async initialize(ctx) {
+    const cfg = ctx.addonConfig;
+    const modelId = cfg["modelId"] ?? "scrfd-500m";
+    const runtime = cfg["runtime"] ?? "auto";
+    const backend = cfg["backend"] ?? "cpu";
+    this.confidence = cfg["confidence"] ?? 0.5;
+    const entry = FACE_DETECTION_MODELS.find((m) => m.id === modelId);
+    if (!entry) {
+      throw new Error(`FaceDetectionAddon: unknown modelId "${modelId}"`);
+    }
+    this.modelEntry = entry;
+    const resolved = await resolveEngine({
+      runtime,
+      backend,
+      modelEntry: entry,
+      modelsDir: ctx.locationPaths.models
+    });
+    this.engine = resolved.engine;
+  }
+  async crop(input) {
+    const start = Date.now();
+    const { width: inputW, height: inputH } = this.modelEntry.inputSize;
+    const targetSize = Math.max(inputW, inputH);
+    const personCrop = await cropRegion(input.frame.data, input.roi);
+    const lb = await letterbox(personCrop, targetSize);
+    const engineWithMulti = this.engine;
+    let outputs;
+    if (typeof engineWithMulti.runMultiOutput === "function") {
+      outputs = await engineWithMulti.runMultiOutput(lb.data, [1, 3, targetSize, targetSize]);
+    } else {
+      const single = await this.engine.run(lb.data, [1, 3, targetSize, targetSize]);
+      outputs = { output0: single };
+    }
+    const crops = scrfdPostprocess(
+      outputs,
+      this.confidence,
+      targetSize,
+      lb.originalWidth,
+      lb.originalHeight
+    );
+    return {
+      crops,
+      inferenceMs: Date.now() - start,
+      modelId: this.modelEntry.id
+    };
+  }
+  async shutdown() {
+    await this.engine?.dispose();
+  }
+  getConfigSchema() {
+    return {
+      sections: [
+        {
+          id: "model",
+          title: "Model",
+          columns: 1,
+          fields: [
+            {
+              key: "modelId",
+              label: "Model",
+              type: "model-selector",
+              catalog: [...FACE_DETECTION_MODELS],
+              allowCustom: false,
+              allowConversion: false,
+              acceptFormats: ["onnx", "coreml", "openvino"],
+              requiredMetadata: ["inputSize", "labels", "outputFormat"],
+              outputFormatHint: "ssd"
+            }
+          ]
+        },
+        {
+          id: "thresholds",
+          title: "Detection Thresholds",
+          columns: 1,
+          fields: [
+            {
+              key: "confidence",
+              label: "Confidence Threshold",
+              type: "slider",
+              min: 0.1,
+              max: 1,
+              step: 0.05,
+              default: 0.5
+            }
+          ]
+        }
+      ]
+    };
+  }
+  getClassMap() {
+    return FACE_CLASS_MAP;
+  }
+  getModelCatalog() {
+    return [...FACE_DETECTION_MODELS];
+  }
+  getAvailableModels() {
+    return [];
+  }
+  getActiveLabels() {
+    return FACE_LABELS;
+  }
+  async probe() {
+    return {
+      available: true,
+      runtime: this.engine?.runtime ?? "onnx",
+      device: this.engine?.device ?? "cpu",
+      capabilities: ["fp32"]
+    };
+  }
+};
+
+export {
+  scrfdPostprocess,
+  FaceDetectionAddon
+};
+//# sourceMappingURL=chunk-AD2TFYZA.mjs.map

package/dist/chunk-AD2TFYZA.mjs.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../src/addons/face-detection/index.ts","../src/shared/postprocess/scrfd.ts"],"sourcesContent":["import type {\n  ICropperProvider,\n  IDetectionAddon,\n  AddonManifest,\n  AddonContext,\n  CropInput,\n  CropperOutput,\n  ConfigUISchema,\n  ClassMapDefinition,\n  ProbeResult,\n  ModelCatalogEntry,\n  DetectionModel,\n  LabelDefinition,\n  IInferenceEngine,\n} from '@camstack/types'\nimport { FACE_DETECTION_MODELS } from '@camstack/types'\nimport { cropRegion, letterbox } from '../../shared/image-utils.js'\nimport { scrfdPostprocess } from '../../shared/postprocess/scrfd.js'\nimport { resolveEngine } from '../../shared/engine-resolver.js'\n\nconst FACE_LABEL: LabelDefinition = { id: 'face', name: 'Face' }\nconst FACE_LABELS: readonly LabelDefinition[] = [FACE_LABEL]\nconst FACE_CLASS_MAP: ClassMapDefinition = { mapping: {}, preserveOriginal: true }\n\nexport default class FaceDetectionAddon implements ICropperProvider, IDetectionAddon {\n  readonly id = 'face-detection'\n  readonly slot = 'cropper' as const\n  readonly inputClasses = ['person'] as const\n  readonly outputClasses = ['face'] as const\n  readonly slotPriority = 0\n  readonly manifest: AddonManifest = {\n    id: 'face-detection',\n    name: 'Face Detection',\n    version: '0.1.0',\n    description: 'SCRFD-based face detector — crops face regions from person detections',\n    packageName: '@camstack/vision',\n    slot: 'cropper',\n    inputClasses: ['person'],\n    outputClasses: ['face'],\n    supportsCustomModels: false,\n    mayRequirePython: false,\n    defaultConfig: {\n      modelId: 'scrfd-500m',\n      runtime: 'auto',\n      backend: 'cpu',\n      confidence: 0.5,\n    },\n  }\n\n  private engine!: IInferenceEngine\n  private modelEntry!: ModelCatalogEntry\n  private confidence = 0.5\n\n  async initialize(ctx: AddonContext): Promise<void> {\n    const cfg = ctx.addonConfig\n    const modelId = (cfg['modelId'] as string | undefined) ?? 'scrfd-500m'\n    const runtime = (cfg['runtime'] as string | undefined) ?? 'auto'\n    const backend = (cfg['backend'] as string | undefined) ?? 'cpu'\n    this.confidence = (cfg['confidence'] as number | undefined) ?? 0.5\n\n    const entry = FACE_DETECTION_MODELS.find((m) => m.id === modelId)\n    if (!entry) {\n      throw new Error(`FaceDetectionAddon: unknown modelId \"${modelId}\"`)\n    }\n    this.modelEntry = entry\n\n    const resolved = await resolveEngine({\n      runtime: runtime as 'auto',\n      backend,\n      modelEntry: entry,\n      modelsDir: ctx.locationPaths.models,\n    })\n    this.engine = resolved.engine\n  }\n\n  async crop(input: CropInput): Promise<CropperOutput> {\n    const start = Date.now()\n    const { width: inputW, height: inputH } = this.modelEntry.inputSize\n    const targetSize = Math.max(inputW, inputH)\n\n    // Crop the person region from the full frame\n    const personCrop = await cropRegion(input.frame.data, input.roi)\n\n    // Letterbox resize to model input size\n    const lb = await letterbox(personCrop, targetSize)\n\n    // SCRFD has multiple output tensors\n    const engineWithMulti = this.engine as IInferenceEngine & {\n      runMultiOutput?: (input: Float32Array, shape: readonly number[]) => Promise<Record<string, Float32Array>>\n    }\n\n    let outputs: Record<string, Float32Array>\n    if (typeof engineWithMulti.runMultiOutput === 'function') {\n      outputs = await engineWithMulti.runMultiOutput(lb.data, [1, 3, targetSize, targetSize])\n    } else {\n      // Fallback: wrap single output\n      const single = await this.engine.run(lb.data, [1, 3, targetSize, targetSize])\n      outputs = { output0: single }\n    }\n\n    const crops = scrfdPostprocess(\n      outputs,\n      this.confidence,\n      targetSize,\n      lb.originalWidth,\n      lb.originalHeight,\n    )\n\n    return {\n      crops,\n      inferenceMs: Date.now() - start,\n      modelId: this.modelEntry.id,\n    }\n  }\n\n  async shutdown(): Promise<void> {\n    await this.engine?.dispose()\n  }\n\n  getConfigSchema(): ConfigUISchema {\n    return {\n      sections: [\n        {\n          id: 'model',\n          title: 'Model',\n          columns: 1,\n          fields: [\n            {\n              key: 'modelId',\n              label: 'Model',\n              type: 'model-selector',\n              catalog: [...FACE_DETECTION_MODELS],\n              allowCustom: false,\n              allowConversion: false,\n              acceptFormats: ['onnx', 'coreml', 'openvino'],\n              requiredMetadata: ['inputSize', 'labels', 'outputFormat'],\n              outputFormatHint: 'ssd',\n            },\n          ],\n        },\n        {\n          id: 'thresholds',\n          title: 'Detection Thresholds',\n          columns: 1,\n          fields: [\n            {\n              key: 'confidence',\n              label: 'Confidence Threshold',\n              type: 'slider',\n              min: 0.1,\n              max: 1.0,\n              step: 0.05,\n              default: 0.5,\n            },\n          ],\n        },\n      ],\n    }\n  }\n\n  getClassMap(): ClassMapDefinition {\n    return FACE_CLASS_MAP\n  }\n\n  getModelCatalog(): ModelCatalogEntry[] {\n    return [...FACE_DETECTION_MODELS]\n  }\n\n  getAvailableModels(): DetectionModel[] {\n    return []\n  }\n\n  getActiveLabels(): readonly LabelDefinition[] {\n    return FACE_LABELS\n  }\n\n  async probe(): Promise<ProbeResult> {\n    return {\n      available: true,\n      runtime: this.engine?.runtime ?? 'onnx',\n      device: this.engine?.device ?? 'cpu',\n      capabilities: ['fp32'],\n    }\n  }\n}\n","import type { SpatialDetection, BoundingBox, Landmark } from '@camstack/types'\nimport { iou, nms } from './yolo.js'\n\nexport interface ScrfdRawOutputs {\n  readonly [key: string]: Float32Array\n}\n\nconst STRIDES = [8, 16, 32] as const\nconst NUM_ANCHORS_PER_STRIDE = 2\n\n/** Generate anchor points for a given stride and input size */\nfunction generateAnchors(stride: number, inputSize: number): Array<{ cx: number; cy: number }> {\n  const featureSize = Math.ceil(inputSize / stride)\n  const anchors: Array<{ cx: number; cy: number }> = []\n  for (let y = 0; y < featureSize; y++) {\n    for (let x = 0; x < featureSize; x++) {\n      for (let k = 0; k < NUM_ANCHORS_PER_STRIDE; k++) {\n        anchors.push({\n          cx: (x + 0.5) * stride,\n          cy: (y + 0.5) * stride,\n        })\n      }\n    }\n  }\n  return anchors\n}\n\nexport function scrfdPostprocess(\n  outputs: ScrfdRawOutputs,\n  confidence: number,\n  inputSize: number,\n  originalWidth: number,\n  originalHeight: number,\n): SpatialDetection[] {\n  // Scale factor from letterbox (assume square crop, so same scale both axes)\n  const scaleX = originalWidth / inputSize\n  const scaleY = originalHeight / inputSize\n\n  interface Candidate {\n    readonly bbox: BoundingBox\n    readonly score: number\n    readonly landmarks?: readonly Landmark[]\n  }\n\n  const candidates: Candidate[] = []\n\n  for (const stride of STRIDES) {\n    const scoreKey = Object.keys(outputs).find((k) => k.includes(`score_${stride}`) || k.includes(`_${stride}_score`))\n    const bboxKey = Object.keys(outputs).find((k) => k.includes(`bbox_${stride}`) || k.includes(`_${stride}_bbox`))\n    const kpsKey = Object.keys(outputs).find((k) => k.includes(`kps_${stride}`) || k.includes(`_${stride}_kps`))\n\n    if (!scoreKey || !bboxKey) continue\n\n    const scores = outputs[scoreKey]!\n    const bboxes = outputs[bboxKey]!\n    const kps = kpsKey ? outputs[kpsKey] : undefined\n    const anchors = generateAnchors(stride, inputSize)\n\n    const n = anchors.length\n\n    for (let i = 0; i < n; i++) {\n      const score = scores[i]!\n      if (score < confidence) continue\n\n      const anchor = anchors[i]!\n\n      // Bboxes are relative to the anchor center in stride units, scaled by stride\n      const x1 = anchor.cx - bboxes[i * 4]! * stride\n      const y1 = anchor.cy - bboxes[i * 4 + 1]! * stride\n      const x2 = anchor.cx + bboxes[i * 4 + 2]! * stride\n      const y2 = anchor.cy + bboxes[i * 4 + 3]! * stride\n\n      const bbox: BoundingBox = {\n        x: x1 * scaleX,\n        y: y1 * scaleY,\n        w: (x2 - x1) * scaleX,\n        h: (y2 - y1) * scaleY,\n      }\n\n      let landmarks: readonly Landmark[] | undefined\n      if (kps) {\n        const pts: Landmark[] = []\n        for (let p = 0; p < 5; p++) {\n          pts.push({\n            x: (anchor.cx + kps[i * 10 + p * 2]! * stride) * scaleX,\n            y: (anchor.cy + kps[i * 10 + p * 2 + 1]! * stride) * scaleY,\n          })\n        }\n        landmarks = pts\n      }\n\n      candidates.push({ bbox, score, landmarks })\n    }\n  }\n\n  if (candidates.length === 0) return []\n\n  const keptIndices = nms(candidates, 0.45)\n\n  return keptIndices.map((idx) => {\n    const { bbox, score, landmarks } = candidates[idx]!\n    return {\n      class: 'face',\n      originalClass: 'face',\n      score,\n      bbox,\n      ...(landmarks ? { landmarks } : {}),\n    } satisfies SpatialDetection\n  })\n}\n"],"mappings":";;;;;;;;;;;;AAeA,SAAS,6BAA6B;;;ACRtC,IAAM,UAAU,CAAC,GAAG,IAAI,EAAE;AAC1B,IAAM,yBAAyB;AAG/B,SAAS,gBAAgB,QAAgB,WAAsD;AAC7F,QAAM,cAAc,KAAK,KAAK,YAAY,MAAM;AAChD,QAAM,UAA6C,CAAC;AACpD,WAAS,IAAI,GAAG,IAAI,aAAa,KAAK;AACpC,aAAS,IAAI,GAAG,IAAI,aAAa,KAAK;AACpC,eAAS,IAAI,GAAG,IAAI,wBAAwB,KAAK;AAC/C,gBAAQ,KAAK;AAAA,UACX,KAAK,IAAI,OAAO;AAAA,UAChB,KAAK,IAAI,OAAO;AAAA,QAClB,CAAC;AAAA,MACH;AAAA,IACF;AAAA,EACF;AACA,SAAO;AACT;AAEO,SAAS,iBACd,SACA,YACA,WACA,eACA,gBACoB;AAEpB,QAAM,SAAS,gBAAgB;AAC/B,QAAM,SAAS,iBAAiB;AAQhC,QAAM,aAA0B,CAAC;AAEjC,aAAW,UAAU,SAAS;AAC5B,UAAM,WAAW,OAAO,KAAK,OAAO,EAAE,KAAK,CAAC,MAAM,EAAE,SAAS,SAAS,MAAM,EAAE,KAAK,EAAE,SAAS,IAAI,MAAM,QAAQ,CAAC;AACjH,UAAM,UAAU,OAAO,KAAK,OAAO,EAAE,KAAK,CAAC,MAAM,EAAE,SAAS,QAAQ,MAAM,EAAE,KAAK,EAAE,SAAS,IAAI,MAAM,OAAO,CAAC;AAC9G,UAAM,SAAS,OAAO,KAAK,OAAO,EAAE,KAAK,CAAC,MAAM,EAAE,SAAS,OAAO,MAAM,EAAE,KAAK,EAAE,SAAS,IAAI,MAAM,MAAM,CAAC;AAE3G,QAAI,CAAC,YAAY,CAAC,QAAS;AAE3B,UAAM,SAAS,QAAQ,QAAQ;AAC/B,UAAM,SAAS,QAAQ,OAAO;AAC9B,UAAM,MAAM,SAAS,QAAQ,MAAM,IAAI;AACvC,UAAM,UAAU,gBAAgB,QAAQ,SAAS;AAEjD,UAAM,IAAI,QAAQ;AAElB,aAAS,IAAI,GAAG,IAAI,GAAG,KAAK;AAC1B,YAAM,QAAQ,OAAO,CAAC;AACtB,UAAI,QAAQ,WAAY;AAExB,YAAM,SAAS,QAAQ,CAAC;AAGxB,YAAM,KAAK,OAAO,KAAK,OAAO,IAAI,CAAC,IAAK;AACxC,YAAM,KAAK,OAAO,KAAK,OAAO,IAAI,IAAI,CAAC,IAAK;AAC5C,YAAM,KAAK,OAAO,KAAK,OAAO,IAAI,IAAI,CAAC,IAAK;AAC5C,YAAM,KAAK,OAAO,KAAK,OAAO,IAAI,IAAI,CAAC,IAAK;AAE5C,YAAM,OAAoB;AAAA,QACxB,GAAG,KAAK;AAAA,QACR,GAAG,KAAK;AAAA,QACR,IAAI,KAAK,MAAM;AAAA,QACf,IAAI,KAAK,MAAM;AAAA,MACjB;AAEA,UAAI;AACJ,UAAI,KAAK;AACP,cAAM,MAAkB,CAAC;AACzB,iBAAS,IAAI,GAAG,IAAI,GAAG,KAAK;AAC1B,cAAI,KAAK;AAAA,YACP,IAAI,OAAO,KAAK,IAAI,IAAI,KAAK,IAAI,CAAC,IAAK,UAAU;AAAA,YACjD,IAAI,OAAO,KAAK,IAAI,IAAI,KAAK,IAAI,IAAI,CAAC,IAAK,UAAU;AAAA,UACvD,CAAC;AAAA,QACH;AACA,oBAAY;AAAA,MACd;AAEA,iBAAW,KAAK,EAAE,MAAM,OAAO,UAAU,CAAC;AAAA,IAC5C;AAAA,EACF;AAEA,MAAI,WAAW,WAAW,EAAG,QAAO,CAAC;AAErC,QAAM,cAAc,IAAI,YAAY,IAAI;AAExC,SAAO,YAAY,IAAI,CAAC,QAAQ;AAC9B,UAAM,EAAE,MAAM,OAAO,UAAU,IAAI,WAAW,GAAG;AACjD,WAAO;AAAA,MACL,OAAO;AAAA,MACP,eAAe;AAAA,MACf;AAAA,MACA;AAAA,MACA,GAAI,YAAY,EAAE,UAAU,IAAI,CAAC;AAAA,IACnC;AAAA,EACF,CAAC;AACH;;;ADzFA,IAAM,aAA8B,EAAE,IAAI,QAAQ,MAAM,OAAO;AAC/D,IAAM,cAA0C,CAAC,UAAU;AAC3D,IAAM,iBAAqC,EAAE,SAAS,CAAC,GAAG,kBAAkB,KAAK;AAEjF,IAAqB,qBAArB,MAAqF;AAAA,EAC1E,KAAK;AAAA,EACL,OAAO;AAAA,EACP,eAAe,CAAC,QAAQ;AAAA,EACxB,gBAAgB,CAAC,MAAM;AAAA,EACvB,eAAe;AAAA,EACf,WAA0B;AAAA,IACjC,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,SAAS;AAAA,IACT,aAAa;AAAA,IACb,aAAa;AAAA,IACb,MAAM;AAAA,IACN,cAAc,CAAC,QAAQ;AAAA,IACvB,eAAe,CAAC,MAAM;AAAA,IACtB,sBAAsB;AAAA,IACtB,kBAAkB;AAAA,IAClB,eAAe;AAAA,MACb,SAAS;AAAA,MACT,SAAS;AAAA,MACT,SAAS;AAAA,MACT,YAAY;AAAA,IACd;AAAA,EACF;AAAA,EAEQ;AAAA,EACA;AAAA,EACA,aAAa;AAAA,EAErB,MAAM,WAAW,KAAkC;AACjD,UAAM,MAAM,IAAI;AAChB,UAAM,UAAW,IAAI,SAAS,KAA4B;AAC1D,UAAM,UAAW,IAAI,SAAS,KAA4B;AAC1D,UAAM,UAAW,IAAI,SAAS,KAA4B;AAC1D,SAAK,aAAc,IAAI,YAAY,KAA4B;AAE/D,UAAM,QAAQ,sBAAsB,KAAK,CAAC,MAAM,EAAE,OAAO,OAAO;AAChE,QAAI,CAAC,OAAO;AACV,YAAM,IAAI,MAAM,wCAAwC,OAAO,GAAG;AAAA,IACpE;AACA,SAAK,aAAa;AAElB,UAAM,WAAW,MAAM,cAAc;AAAA,MACnC;AAAA,MACA;AAAA,MACA,YAAY;AAAA,MACZ,WAAW,IAAI,cAAc;AAAA,IAC/B,CAAC;AACD,SAAK,SAAS,SAAS;AAAA,EACzB;AAAA,EAEA,MAAM,KAAK,OAA0C;AACnD,UAAM,QAAQ,KAAK,IAAI;AACvB,UAAM,EAAE,OAAO,QAAQ,QAAQ,OAAO,IAAI,KAAK,WAAW;AAC1D,UAAM,aAAa,KAAK,IAAI,QAAQ,MAAM;AAG1C,UAAM,aAAa,MAAM,WAAW,MAAM,MAAM,MAAM,MAAM,GAAG;AAG/D,UAAM,KAAK,MAAM,UAAU,YAAY,UAAU;AAGjD,UAAM,kBAAkB,KAAK;AAI7B,QAAI;AACJ,QAAI,OAAO,gBAAgB,mBAAmB,YAAY;AACxD,gBAAU,MAAM,gBAAgB,eAAe,GAAG,MAAM,CAAC,GAAG,GAAG,YAAY,UAAU,CAAC;AAAA,IACxF,OAAO;AAEL,YAAM,SAAS,MAAM,KAAK,OAAO,IAAI,GAAG,MAAM,CAAC,GAAG,GAAG,YAAY,UAAU,CAAC;AAC5E,gBAAU,EAAE,SAAS,OAAO;AAAA,IAC9B;AAEA,UAAM,QAAQ;AAAA,MACZ;AAAA,MACA,KAAK;AAAA,MACL;AAAA,MACA,GAAG;AAAA,MACH,GAAG;AAAA,IACL;AAEA,WAAO;AAAA,MACL;AAAA,MACA,aAAa,KAAK,IAAI,IAAI;AAAA,MAC1B,SAAS,KAAK,WAAW;AAAA,IAC3B;AAAA,EACF;AAAA,EAEA,MAAM,WAA0B;AAC9B,UAAM,KAAK,QAAQ,QAAQ;AAAA,EAC7B;AAAA,EAEA,kBAAkC;AAChC,WAAO;AAAA,MACL,UAAU;AAAA,QACR;AAAA,UACE,IAAI;AAAA,UACJ,OAAO;AAAA,UACP,SAAS;AAAA,UACT,QAAQ;AAAA,YACN;AAAA,cACE,KAAK;AAAA,cACL,OAAO;AAAA,cACP,MAAM;AAAA,cACN,SAAS,CAAC,GAAG,qBAAqB;AAAA,cAClC,aAAa;AAAA,cACb,iBAAiB;AAAA,cACjB,eAAe,CAAC,QAAQ,UAAU,UAAU;AAAA,cAC5C,kBAAkB,CAAC,aAAa,UAAU,cAAc;AAAA,cACxD,kBAAkB;AAAA,YACpB;AAAA,UACF;AAAA,QACF;AAAA,QACA;AAAA,UACE,IAAI;AAAA,UACJ,OAAO;AAAA,UACP,SAAS;AAAA,UACT,QAAQ;AAAA,YACN;AAAA,cACE,KAAK;AAAA,cACL,OAAO;AAAA,cACP,MAAM;AAAA,cACN,KAAK;AAAA,cACL,KAAK;AAAA,cACL,MAAM;AAAA,cACN,SAAS;AAAA,YACX;AAAA,UACF;AAAA,QACF;AAAA,MACF;AAAA,IACF;AAAA,EACF;AAAA,EAEA,cAAkC;AAChC,WAAO;AAAA,EACT;AAAA,EAEA,kBAAuC;AACrC,WAAO,CAAC,GAAG,qBAAqB;AAAA,EAClC;AAAA,EAEA,qBAAuC;AACrC,WAAO,CAAC;AAAA,EACV;AAAA,EAEA,kBAA8C;AAC5C,WAAO;AAAA,EACT;AAAA,EAEA,MAAM,QAA8B;AAClC,WAAO;AAAA,MACL,WAAW;AAAA,MACX,SAAS,KAAK,QAAQ,WAAW;AAAA,MACjC,QAAQ,KAAK,QAAQ,UAAU;AAAA,MAC/B,cAAc,CAAC,MAAM;AAAA,IACvB;AAAA,EACF;AACF;","names":[]}