@camstack/addon-vision 0.1.0

package/dist/chunk-5AIQSN32.mjs.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../src/catalogs/audio-classification-models.ts","../src/shared/postprocess/yamnet.ts","../src/addons/audio-classification/index.ts"],"sourcesContent":["import type { ModelCatalogEntry, LabelDefinition } from '@camstack/types'\nimport { hfModelUrl } from '@camstack/types'\n\nconst HF_REPO = 'camstack/camstack-models'\n\nconst AUDIO_LABELS: readonly LabelDefinition[] = [\n  { id: 'audio', name: 'Audio Event' },\n] as const\n\nexport const AUDIO_CLASSIFICATION_MODELS: readonly ModelCatalogEntry[] = [\n  {\n    id: 'yamnet',\n    name: 'YAMNet',\n    description: 'YAMNet — audio event classification from raw waveform',\n    inputSize: { width: 1, height: 16000 },\n    labels: AUDIO_LABELS,\n    formats: {\n      onnx: {\n        url: hfModelUrl(HF_REPO, 'audioClassification/yamnet/onnx/camstack-yamnet.onnx'),\n        sizeMB: 15,\n      },\n      openvino: {\n        url: hfModelUrl(HF_REPO, 'audioClassification/yamnet/openvino/camstack-yamnet.xml'),\n        sizeMB: 8,\n      },\n    },\n  },\n] as const\n","export interface AudioClassification {\n  readonly className: string\n  readonly score: number\n}\n\n/** Average YAMNET scores across frames, return top classes above threshold */\nexport function yamnetPostprocess(\n  output: Float32Array,\n  numFrames: number,\n  numClasses: number,\n  classNames: readonly string[],\n  minScore: number,\n): AudioClassification[] {\n  // Average across frames\n  const avgScores = new Float32Array(numClasses)\n  for (let f = 0; f < numFrames; f++) {\n    for (let c = 0; c < numClasses; c++) {\n      const prev = avgScores[c] ?? 0\n      avgScores[c] = prev + (output[f * numClasses + c] ?? 0)\n    }\n  }\n  if (numFrames > 0) {\n    for (let c = 0; c < numClasses; c++) {\n      const val = avgScores[c] ?? 0\n      avgScores[c] = val / numFrames\n    }\n  }\n\n  // Collect classes above threshold\n  const results: AudioClassification[] = []\n  for (let c = 0; c < numClasses; c++) {\n    const score = avgScores[c]!\n    if (score >= minScore) {\n      results.push({\n        className: classNames[c] ?? String(c),\n        score,\n      })\n    }\n  }\n\n  // Sort descending by score\n  return results.sort((a, b) => b.score - a.score)\n}\n","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 { AUDIO_CLASSIFICATION_MODELS } from '../../catalogs/audio-classification-models.js'\nimport { yamnetPostprocess } from '../../shared/postprocess/yamnet.js'\nimport { resolveEngine } from '../../shared/engine-resolver.js'\n\n// YAMNet recognizes 521 audio classes from the AudioSet ontology.\n// This is the top-level subset used for filtering. Full class list lives in the model catalog.\nconst YAMNET_NUM_CLASSES = 521\n\nconst AUDIO_EVENT_LABEL: LabelDefinition = { id: 'audio-event', name: 'Audio Event' }\nconst AUDIO_LABELS: readonly LabelDefinition[] = [AUDIO_EVENT_LABEL]\nconst AUDIO_CLASS_MAP: ClassMapDefinition = { mapping: {}, preserveOriginal: true }\n\nexport default class AudioClassificationAddon implements IClassifierProvider, IDetectionAddon {\n  readonly id = 'audio-classification'\n  readonly slot = 'classifier' as const\n  readonly inputClasses: readonly string[] | null = null\n  readonly outputClasses = ['audio-event:*'] as const\n  readonly slotPriority = 0\n  readonly manifest: AddonManifest = {\n    id: 'audio-classification',\n    name: 'Audio Classification',\n    version: '0.1.0',\n    description: 'YAMNet-based audio event classification from audio waveform',\n    packageName: '@camstack/addon-vision',\n    slot: 'classifier',\n    inputClasses: undefined,\n    outputClasses: ['audio-event:*'],\n    supportsCustomModels: false,\n    mayRequirePython: false,\n    defaultConfig: {\n      modelId: 'yamnet',\n      runtime: 'auto',\n      backend: 'cpu',\n      minScore: 0.3,\n    },\n  }\n\n  private engine!: IInferenceEngine\n  private modelEntry!: ModelCatalogEntry\n  private minScore = 0.3\n\n  async initialize(ctx: AddonContext): Promise<void> {\n    const cfg = ctx.addonConfig\n    const modelId = (cfg['modelId'] as string | undefined) ?? 'yamnet'\n    const runtime = (cfg['runtime'] as string | undefined) ?? 'auto'\n    const backend = (cfg['backend'] as string | undefined) ?? 'cpu'\n    this.minScore = (cfg['minScore'] as number | undefined) ?? 0.3\n\n    const entry = AUDIO_CLASSIFICATION_MODELS.find((m) => m.id === modelId)\n    if (!entry) {\n      throw new Error(`AudioClassificationAddon: unknown modelId \"${modelId}\"`)\n    }\n    this.modelEntry = entry\n\n    const resolved = await resolveEngine({\n      runtime: runtime as 'auto',\n      backend,\n      modelEntry: entry,\n      modelsDir: ctx.locationPaths.models,\n    })\n    this.engine = resolved.engine\n  }\n\n  /**\n   * classify() receives a CropInput but internally treats input.frame.data as raw audio context.\n   * For audio, the actual audio chunk data should be stored in frame.data as a Float32Array\n   * serialized into a Buffer (little-endian float32 samples at 16 kHz).\n   *\n   * The CropInput.roi is not used for audio — it is ignored.\n   */\n  async classify(input: CropInput): Promise<ClassifierOutput> {\n    const start = Date.now()\n\n    // Extract raw float32 audio samples from the buffer\n    const buf = input.frame.data\n    const numSamples = Math.floor(buf.length / 4)\n    const audioData = new Float32Array(numSamples)\n    for (let i = 0; i < numSamples; i++) {\n      audioData[i] = buf.readFloatLE(i * 4)\n    }\n\n    // YAMNet expects 1D waveform at 16 kHz\n    const output = await this.engine.run(audioData, [numSamples])\n\n    // YAMNet output shape: [numFrames, numClasses]\n    const numFrames = output.length / YAMNET_NUM_CLASSES\n\n    // Use model label ids as class names (or index strings if catalog is sparse)\n    const classNames: string[] = this.modelEntry.labels.map((l) => l.id)\n    // Pad to full 521 classes if the catalog only has a subset\n    while (classNames.length < YAMNET_NUM_CLASSES) {\n      classNames.push(`class_${classNames.length}`)\n    }\n\n    const results = yamnetPostprocess(\n      output,\n      Math.round(numFrames),\n      YAMNET_NUM_CLASSES,\n      classNames,\n      this.minScore,\n    )\n\n    const classifications = results.map((r) => ({\n      class: `audio-event:${r.className}`,\n      score: r.score,\n    }))\n\n    return {\n      classifications,\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: '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: 'openvino', label: 'OpenVINO (Intel)' },\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: 'cuda', label: 'CUDA (NVIDIA)' },\n              ],\n            },\n          ],\n        },\n        {\n          id: 'thresholds',\n          title: 'Classification Settings',\n          columns: 1,\n          fields: [\n            {\n              key: 'minScore',\n              label: 'Minimum Score',\n              type: 'slider',\n              min: 0.05,\n              max: 1.0,\n              step: 0.05,\n              default: 0.3,\n            },\n          ],\n        },\n      ],\n    }\n  }\n\n  getClassMap(): ClassMapDefinition {\n    return AUDIO_CLASS_MAP\n  }\n\n  getModelCatalog(): ModelCatalogEntry[] {\n    return [...AUDIO_CLASSIFICATION_MODELS]\n  }\n\n  getAvailableModels(): DetectionModel[] {\n    return []\n  }\n\n  getActiveLabels(): readonly LabelDefinition[] {\n    return AUDIO_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":";;;;;AACA,SAAS,kBAAkB;AAE3B,IAAM,UAAU;AAEhB,IAAM,eAA2C;AAAA,EAC/C,EAAE,IAAI,SAAS,MAAM,cAAc;AACrC;AAEO,IAAM,8BAA4D;AAAA,EACvE;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,aAAa;AAAA,IACb,WAAW,EAAE,OAAO,GAAG,QAAQ,KAAM;AAAA,IACrC,QAAQ;AAAA,IACR,SAAS;AAAA,MACP,MAAM;AAAA,QACJ,KAAK,WAAW,SAAS,sDAAsD;AAAA,QAC/E,QAAQ;AAAA,MACV;AAAA,MACA,UAAU;AAAA,QACR,KAAK,WAAW,SAAS,yDAAyD;AAAA,QAClF,QAAQ;AAAA,MACV;AAAA,IACF;AAAA,EACF;AACF;;;ACrBO,SAAS,kBACd,QACA,WACA,YACA,YACA,UACuB;AAEvB,QAAM,YAAY,IAAI,aAAa,UAAU;AAC7C,WAAS,IAAI,GAAG,IAAI,WAAW,KAAK;AAClC,aAAS,IAAI,GAAG,IAAI,YAAY,KAAK;AACnC,YAAM,OAAO,UAAU,CAAC,KAAK;AAC7B,gBAAU,CAAC,IAAI,QAAQ,OAAO,IAAI,aAAa,CAAC,KAAK;AAAA,IACvD;AAAA,EACF;AACA,MAAI,YAAY,GAAG;AACjB,aAAS,IAAI,GAAG,IAAI,YAAY,KAAK;AACnC,YAAM,MAAM,UAAU,CAAC,KAAK;AAC5B,gBAAU,CAAC,IAAI,MAAM;AAAA,IACvB;AAAA,EACF;AAGA,QAAM,UAAiC,CAAC;AACxC,WAAS,IAAI,GAAG,IAAI,YAAY,KAAK;AACnC,UAAM,QAAQ,UAAU,CAAC;AACzB,QAAI,SAAS,UAAU;AACrB,cAAQ,KAAK;AAAA,QACX,WAAW,WAAW,CAAC,KAAK,OAAO,CAAC;AAAA,QACpC;AAAA,MACF,CAAC;AAAA,IACH;AAAA,EACF;AAGA,SAAO,QAAQ,KAAK,CAAC,GAAG,MAAM,EAAE,QAAQ,EAAE,KAAK;AACjD;;;ACrBA,IAAM,qBAAqB;AAE3B,IAAM,oBAAqC,EAAE,IAAI,eAAe,MAAM,cAAc;AACpF,IAAMA,gBAA2C,CAAC,iBAAiB;AACnE,IAAM,kBAAsC,EAAE,SAAS,CAAC,GAAG,kBAAkB,KAAK;AAElF,IAAqB,2BAArB,MAA8F;AAAA,EACnF,KAAK;AAAA,EACL,OAAO;AAAA,EACP,eAAyC;AAAA,EACzC,gBAAgB,CAAC,eAAe;AAAA,EAChC,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;AAAA,IACd,eAAe,CAAC,eAAe;AAAA,IAC/B,sBAAsB;AAAA,IACtB,kBAAkB;AAAA,IAClB,eAAe;AAAA,MACb,SAAS;AAAA,MACT,SAAS;AAAA,MACT,SAAS;AAAA,MACT,UAAU;AAAA,IACZ;AAAA,EACF;AAAA,EAEQ;AAAA,EACA;AAAA,EACA,WAAW;AAAA,EAEnB,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,WAAY,IAAI,UAAU,KAA4B;AAE3D,UAAM,QAAQ,4BAA4B,KAAK,CAAC,MAAM,EAAE,OAAO,OAAO;AACtE,QAAI,CAAC,OAAO;AACV,YAAM,IAAI,MAAM,8CAA8C,OAAO,GAAG;AAAA,IAC1E;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;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EASA,MAAM,SAAS,OAA6C;AAC1D,UAAM,QAAQ,KAAK,IAAI;AAGvB,UAAM,MAAM,MAAM,MAAM;AACxB,UAAM,aAAa,KAAK,MAAM,IAAI,SAAS,CAAC;AAC5C,UAAM,YAAY,IAAI,aAAa,UAAU;AAC7C,aAAS,IAAI,GAAG,IAAI,YAAY,KAAK;AACnC,gBAAU,CAAC,IAAI,IAAI,YAAY,IAAI,CAAC;AAAA,IACtC;AAGA,UAAM,SAAS,MAAM,KAAK,OAAO,IAAI,WAAW,CAAC,UAAU,CAAC;AAG5D,UAAM,YAAY,OAAO,SAAS;AAGlC,UAAM,aAAuB,KAAK,WAAW,OAAO,IAAI,CAAC,MAAM,EAAE,EAAE;AAEnE,WAAO,WAAW,SAAS,oBAAoB;AAC7C,iBAAW,KAAK,SAAS,WAAW,MAAM,EAAE;AAAA,IAC9C;AAEA,UAAM,UAAU;AAAA,MACd;AAAA,MACA,KAAK,MAAM,SAAS;AAAA,MACpB;AAAA,MACA;AAAA,MACA,KAAK;AAAA,IACP;AAEA,UAAM,kBAAkB,QAAQ,IAAI,CAAC,OAAO;AAAA,MAC1C,OAAO,eAAe,EAAE,SAAS;AAAA,MACjC,OAAO,EAAE;AAAA,IACX,EAAE;AAEF,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;AAAA,gBACP,EAAE,OAAO,QAAQ,OAAO,qBAAqB;AAAA,gBAC7C,EAAE,OAAO,QAAQ,OAAO,eAAe;AAAA,gBACvC,EAAE,OAAO,YAAY,OAAO,mBAAmB;AAAA,cACjD;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,QAAQ,OAAO,gBAAgB;AAAA,cAC1C;AAAA,YACF;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,2BAA2B;AAAA,EACxC;AAAA,EAEA,qBAAuC;AACrC,WAAO,CAAC;AAAA,EACV;AAAA,EAEA,kBAA8C;AAC5C,WAAOA;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":["AUDIO_LABELS"]}

package/dist/chunk-5JJZGKL7.mjs

@@ -0,0 +1,186 @@
+import {
+  yoloPostprocess
+} from "./chunk-KUO2BVFY.mjs";
+import {
+  cropRegion,
+  letterbox
+} from "./chunk-6OR5TE7A.mjs";
+import {
+  resolveEngine
+} from "./chunk-LPI42WL6.mjs";
+
+// src/catalogs/plate-detection-models.ts
+import { hfModelUrl } from "@camstack/types";
+var HF_REPO = "camstack/camstack-models";
+var PLATE_LABELS = [
+  { id: "plate", name: "License Plate" }
+];
+var PLATE_DETECTION_MODELS = [
+  {
+    id: "yolov8n-plate",
+    name: "YOLOv8 Nano \u2014 License Plate",
+    description: "YOLOv8 Nano fine-tuned for license plate detection",
+    inputSize: { width: 640, height: 640 },
+    labels: PLATE_LABELS,
+    formats: {
+      onnx: {
+        url: hfModelUrl(HF_REPO, "plateDetection/yolov8-plate/onnx/camstack-yolov8n-plate.onnx"),
+        sizeMB: 12
+      },
+      coreml: {
+        url: hfModelUrl(HF_REPO, "plateDetection/yolov8-plate/coreml/camstack-yolov8n-plate.mlpackage"),
+        sizeMB: 5.9
+      },
+      openvino: {
+        url: hfModelUrl(HF_REPO, "plateDetection/yolov8-plate/openvino/camstack-yolov8n-plate.xml"),
+        sizeMB: 6.1
+      },
+      tflite: {
+        url: hfModelUrl(HF_REPO, "plateDetection/yolov8-plate/tflite/camstack-yolov8n-plate_float32.tflite"),
+        sizeMB: 12
+      }
+    }
+  }
+];
+
+// src/addons/plate-detection/index.ts
+var PLATE_LABEL = { id: "plate", name: "License Plate" };
+var PLATE_LABELS2 = [PLATE_LABEL];
+var PLATE_CLASS_MAP = { mapping: {}, preserveOriginal: true };
+var PlateDetectionAddon = class {
+  id = "plate-detection";
+  slot = "cropper";
+  inputClasses = ["vehicle"];
+  outputClasses = ["plate"];
+  slotPriority = 0;
+  manifest = {
+    id: "plate-detection",
+    name: "License Plate Detection",
+    version: "0.1.0",
+    description: "YOLO-based license plate detector \u2014 crops plate regions from vehicle detections",
+    packageName: "@camstack/addon-vision",
+    slot: "cropper",
+    inputClasses: ["vehicle"],
+    outputClasses: ["plate"],
+    supportsCustomModels: false,
+    mayRequirePython: false,
+    defaultConfig: {
+      modelId: "yolov8n-plate",
+      runtime: "auto",
+      backend: "cpu",
+      confidence: 0.5,
+      iouThreshold: 0.45
+    }
+  };
+  engine;
+  modelEntry;
+  confidence = 0.5;
+  iouThreshold = 0.45;
+  async initialize(ctx) {
+    const cfg = ctx.addonConfig;
+    const modelId = cfg["modelId"] ?? "yolov8n-plate";
+    const runtime = cfg["runtime"] ?? "auto";
+    const backend = cfg["backend"] ?? "cpu";
+    this.confidence = cfg["confidence"] ?? 0.5;
+    this.iouThreshold = cfg["iouThreshold"] ?? 0.45;
+    const entry = PLATE_DETECTION_MODELS.find((m) => m.id === modelId);
+    if (!entry) {
+      throw new Error(`PlateDetectionAddon: 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 vehicleCrop = await cropRegion(input.frame.data, input.roi);
+    const lb = await letterbox(vehicleCrop, targetSize);
+    const output = await this.engine.run(lb.data, [1, 3, targetSize, targetSize]);
+    const numClasses = this.modelEntry.labels.length;
+    const numBoxes = output.length / (4 + numClasses);
+    const labels = this.modelEntry.labels.map((l) => l.id);
+    const plates = yoloPostprocess(output, numClasses, numBoxes, {
+      confidence: this.confidence,
+      iouThreshold: this.iouThreshold,
+      labels,
+      scale: lb.scale,
+      padX: lb.padX,
+      padY: lb.padY,
+      originalWidth: lb.originalWidth,
+      originalHeight: lb.originalHeight
+    });
+    const crops = plates.map((p) => ({ ...p, class: "plate", originalClass: p.originalClass }));
+    return {
+      crops,
+      inferenceMs: Date.now() - start,
+      modelId: this.modelEntry.id
+    };
+  }
+  async shutdown() {
+    await this.engine?.dispose();
+  }
+  getConfigSchema() {
+    return {
+      sections: [
+        {
+          id: "thresholds",
+          title: "Detection Thresholds",
+          columns: 2,
+          fields: [
+            {
+              key: "confidence",
+              label: "Confidence Threshold",
+              type: "slider",
+              min: 0.1,
+              max: 1,
+              step: 0.05,
+              default: 0.5
+            },
+            {
+              key: "iouThreshold",
+              label: "IoU Threshold (NMS)",
+              type: "slider",
+              min: 0.1,
+              max: 1,
+              step: 0.05,
+              default: 0.45
+            }
+          ]
+        }
+      ]
+    };
+  }
+  getClassMap() {
+    return PLATE_CLASS_MAP;
+  }
+  getModelCatalog() {
+    return [...PLATE_DETECTION_MODELS];
+  }
+  getAvailableModels() {
+    return [];
+  }
+  getActiveLabels() {
+    return PLATE_LABELS2;
+  }
+  async probe() {
+    return {
+      available: true,
+      runtime: this.engine?.runtime ?? "onnx",
+      device: this.engine?.device ?? "cpu",
+      capabilities: ["fp32"]
+    };
+  }
+};
+
+export {
+  PLATE_DETECTION_MODELS,
+  PlateDetectionAddon
+};
+//# sourceMappingURL=chunk-5JJZGKL7.mjs.map

package/dist/chunk-5JJZGKL7.mjs.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../src/catalogs/plate-detection-models.ts","../src/addons/plate-detection/index.ts"],"sourcesContent":["import type { ModelCatalogEntry, LabelDefinition } from '@camstack/types'\nimport { hfModelUrl } from '@camstack/types'\n\nconst HF_REPO = 'camstack/camstack-models'\n\nconst PLATE_LABELS: readonly LabelDefinition[] = [\n  { id: 'plate', name: 'License Plate' },\n] as const\n\nexport const PLATE_DETECTION_MODELS: readonly ModelCatalogEntry[] = [\n  {\n    id: 'yolov8n-plate',\n    name: 'YOLOv8 Nano — License Plate',\n    description: 'YOLOv8 Nano fine-tuned for license plate detection',\n    inputSize: { width: 640, height: 640 },\n    labels: PLATE_LABELS,\n    formats: {\n      onnx: {\n        url: hfModelUrl(HF_REPO, 'plateDetection/yolov8-plate/onnx/camstack-yolov8n-plate.onnx'),\n        sizeMB: 12,\n      },\n      coreml: {\n        url: hfModelUrl(HF_REPO, 'plateDetection/yolov8-plate/coreml/camstack-yolov8n-plate.mlpackage'),\n        sizeMB: 5.9,\n      },\n      openvino: {\n        url: hfModelUrl(HF_REPO, 'plateDetection/yolov8-plate/openvino/camstack-yolov8n-plate.xml'),\n        sizeMB: 6.1,\n      },\n      tflite: {\n        url: hfModelUrl(HF_REPO, 'plateDetection/yolov8-plate/tflite/camstack-yolov8n-plate_float32.tflite'),\n        sizeMB: 12,\n      },\n    },\n  },\n] as const\n","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 { PLATE_DETECTION_MODELS } from '../../catalogs/plate-detection-models.js'\nimport { cropRegion, letterbox } from '../../shared/image-utils.js'\nimport { yoloPostprocess } from '../../shared/postprocess/yolo.js'\nimport { resolveEngine } from '../../shared/engine-resolver.js'\n\nconst PLATE_LABEL: LabelDefinition = { id: 'plate', name: 'License Plate' }\nconst PLATE_LABELS: readonly LabelDefinition[] = [PLATE_LABEL]\nconst PLATE_CLASS_MAP: ClassMapDefinition = { mapping: {}, preserveOriginal: true }\n\nexport default class PlateDetectionAddon implements ICropperProvider, IDetectionAddon {\n  readonly id = 'plate-detection'\n  readonly slot = 'cropper' as const\n  readonly inputClasses = ['vehicle'] as const\n  readonly outputClasses = ['plate'] as const\n  readonly slotPriority = 0\n  readonly manifest: AddonManifest = {\n    id: 'plate-detection',\n    name: 'License Plate Detection',\n    version: '0.1.0',\n    description: 'YOLO-based license plate detector — crops plate regions from vehicle detections',\n    packageName: '@camstack/addon-vision',\n    slot: 'cropper',\n    inputClasses: ['vehicle'],\n    outputClasses: ['plate'],\n    supportsCustomModels: false,\n    mayRequirePython: false,\n    defaultConfig: {\n      modelId: 'yolov8n-plate',\n      runtime: 'auto',\n      backend: 'cpu',\n      confidence: 0.5,\n      iouThreshold: 0.45,\n    },\n  }\n\n  private engine!: IInferenceEngine\n  private modelEntry!: ModelCatalogEntry\n  private confidence = 0.5\n  private iouThreshold = 0.45\n\n  async initialize(ctx: AddonContext): Promise<void> {\n    const cfg = ctx.addonConfig\n    const modelId = (cfg['modelId'] as string | undefined) ?? 'yolov8n-plate'\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    this.iouThreshold = (cfg['iouThreshold'] as number | undefined) ?? 0.45\n\n    const entry = PLATE_DETECTION_MODELS.find((m) => m.id === modelId)\n    if (!entry) {\n      throw new Error(`PlateDetectionAddon: 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 vehicle region from the full frame\n    const vehicleCrop = await cropRegion(input.frame.data, input.roi)\n\n    const lb = await letterbox(vehicleCrop, targetSize)\n    const output = await this.engine.run(lb.data, [1, 3, targetSize, targetSize])\n\n    const numClasses = this.modelEntry.labels.length\n    const numBoxes = output.length / (4 + numClasses)\n    const labels = this.modelEntry.labels.map((l) => l.id)\n\n    const plates = yoloPostprocess(output, numClasses, numBoxes, {\n      confidence: this.confidence,\n      iouThreshold: this.iouThreshold,\n      labels,\n      scale: lb.scale,\n      padX: lb.padX,\n      padY: lb.padY,\n      originalWidth: lb.originalWidth,\n      originalHeight: lb.originalHeight,\n    })\n\n    // Override class to 'plate'\n    const crops = plates.map((p) => ({ ...p, class: 'plate', originalClass: p.originalClass }))\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: 'thresholds',\n          title: 'Detection Thresholds',\n          columns: 2,\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              key: 'iouThreshold',\n              label: 'IoU Threshold (NMS)',\n              type: 'slider',\n              min: 0.1,\n              max: 1.0,\n              step: 0.05,\n              default: 0.45,\n            },\n          ],\n        },\n      ],\n    }\n  }\n\n  getClassMap(): ClassMapDefinition {\n    return PLATE_CLASS_MAP\n  }\n\n  getModelCatalog(): ModelCatalogEntry[] {\n    return [...PLATE_DETECTION_MODELS]\n  }\n\n  getAvailableModels(): DetectionModel[] {\n    return []\n  }\n\n  getActiveLabels(): readonly LabelDefinition[] {\n    return PLATE_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":";;;;;;;;;;;;AACA,SAAS,kBAAkB;AAE3B,IAAM,UAAU;AAEhB,IAAM,eAA2C;AAAA,EAC/C,EAAE,IAAI,SAAS,MAAM,gBAAgB;AACvC;AAEO,IAAM,yBAAuD;AAAA,EAClE;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,aAAa;AAAA,IACb,WAAW,EAAE,OAAO,KAAK,QAAQ,IAAI;AAAA,IACrC,QAAQ;AAAA,IACR,SAAS;AAAA,MACP,MAAM;AAAA,QACJ,KAAK,WAAW,SAAS,8DAA8D;AAAA,QACvF,QAAQ;AAAA,MACV;AAAA,MACA,QAAQ;AAAA,QACN,KAAK,WAAW,SAAS,qEAAqE;AAAA,QAC9F,QAAQ;AAAA,MACV;AAAA,MACA,UAAU;AAAA,QACR,KAAK,WAAW,SAAS,iEAAiE;AAAA,QAC1F,QAAQ;AAAA,MACV;AAAA,MACA,QAAQ;AAAA,QACN,KAAK,WAAW,SAAS,0EAA0E;AAAA,QACnG,QAAQ;AAAA,MACV;AAAA,IACF;AAAA,EACF;AACF;;;ACfA,IAAM,cAA+B,EAAE,IAAI,SAAS,MAAM,gBAAgB;AAC1E,IAAMA,gBAA2C,CAAC,WAAW;AAC7D,IAAM,kBAAsC,EAAE,SAAS,CAAC,GAAG,kBAAkB,KAAK;AAElF,IAAqB,sBAArB,MAAsF;AAAA,EAC3E,KAAK;AAAA,EACL,OAAO;AAAA,EACP,eAAe,CAAC,SAAS;AAAA,EACzB,gBAAgB,CAAC,OAAO;AAAA,EACxB,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,SAAS;AAAA,IACxB,eAAe,CAAC,OAAO;AAAA,IACvB,sBAAsB;AAAA,IACtB,kBAAkB;AAAA,IAClB,eAAe;AAAA,MACb,SAAS;AAAA,MACT,SAAS;AAAA,MACT,SAAS;AAAA,MACT,YAAY;AAAA,MACZ,cAAc;AAAA,IAChB;AAAA,EACF;AAAA,EAEQ;AAAA,EACA;AAAA,EACA,aAAa;AAAA,EACb,eAAe;AAAA,EAEvB,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;AAC/D,SAAK,eAAgB,IAAI,cAAc,KAA4B;AAEnE,UAAM,QAAQ,uBAAuB,KAAK,CAAC,MAAM,EAAE,OAAO,OAAO;AACjE,QAAI,CAAC,OAAO;AACV,YAAM,IAAI,MAAM,yCAAyC,OAAO,GAAG;AAAA,IACrE;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,cAAc,MAAM,WAAW,MAAM,MAAM,MAAM,MAAM,GAAG;AAEhE,UAAM,KAAK,MAAM,UAAU,aAAa,UAAU;AAClD,UAAM,SAAS,MAAM,KAAK,OAAO,IAAI,GAAG,MAAM,CAAC,GAAG,GAAG,YAAY,UAAU,CAAC;AAE5E,UAAM,aAAa,KAAK,WAAW,OAAO;AAC1C,UAAM,WAAW,OAAO,UAAU,IAAI;AACtC,UAAM,SAAS,KAAK,WAAW,OAAO,IAAI,CAAC,MAAM,EAAE,EAAE;AAErD,UAAM,SAAS,gBAAgB,QAAQ,YAAY,UAAU;AAAA,MAC3D,YAAY,KAAK;AAAA,MACjB,cAAc,KAAK;AAAA,MACnB;AAAA,MACA,OAAO,GAAG;AAAA,MACV,MAAM,GAAG;AAAA,MACT,MAAM,GAAG;AAAA,MACT,eAAe,GAAG;AAAA,MAClB,gBAAgB,GAAG;AAAA,IACrB,CAAC;AAGD,UAAM,QAAQ,OAAO,IAAI,CAAC,OAAO,EAAE,GAAG,GAAG,OAAO,SAAS,eAAe,EAAE,cAAc,EAAE;AAE1F,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,KAAK;AAAA,cACL,KAAK;AAAA,cACL,MAAM;AAAA,cACN,SAAS;AAAA,YACX;AAAA,YACA;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,sBAAsB;AAAA,EACnC;AAAA,EAEA,qBAAuC;AACrC,WAAO,CAAC;AAAA,EACV;AAAA,EAEA,kBAA8C;AAC5C,WAAOA;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":["PLATE_LABELS"]}

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":[]}