@camstack/vision 0.1.0

package/dist/chunk-CGYSSHHM.mjs

@@ -0,0 +1,363 @@
+import {
+  nms,
+  yoloPostprocess
+} from "./chunk-KUO2BVFY.mjs";
+import {
+  letterbox
+} from "./chunk-6OR5TE7A.mjs";
+import {
+  resolveEngine
+} from "./chunk-J3IUBPRE.mjs";
+
+// src/addons/object-detection/index.ts
+import {
+  OBJECT_DETECTION_MODELS,
+  SEGMENTATION_MODELS,
+  COCO_TO_MACRO,
+  MACRO_LABELS
+} from "@camstack/types";
+
+// src/shared/postprocess/yolo-seg.ts
+function sigmoid(x) {
+  return 1 / (1 + Math.exp(-x));
+}
+function computeRawMask(coeffs, protos, numMaskCoeffs, maskH, maskW) {
+  const maskSize = maskH * maskW;
+  const rawMask = new Float32Array(maskSize);
+  for (let px = 0; px < maskSize; px++) {
+    let val = 0;
+    for (let k = 0; k < numMaskCoeffs; k++) {
+      val += (coeffs[k] ?? 0) * (protos[k * maskSize + px] ?? 0);
+    }
+    rawMask[px] = sigmoid(val);
+  }
+  return rawMask;
+}
+function cropAndThresholdMask(rawMask, maskH, maskW, bbox, maskThreshold, maskScale) {
+  const cropX1 = Math.max(0, Math.floor(bbox.x * maskScale));
+  const cropY1 = Math.max(0, Math.floor(bbox.y * maskScale));
+  const cropX2 = Math.min(maskW, Math.ceil((bbox.x + bbox.w) * maskScale));
+  const cropY2 = Math.min(maskH, Math.ceil((bbox.y + bbox.h) * maskScale));
+  const cropW = Math.max(1, cropX2 - cropX1);
+  const cropH = Math.max(1, cropY2 - cropY1);
+  const data = new Uint8Array(cropW * cropH);
+  for (let row = 0; row < cropH; row++) {
+    const srcRow = cropY1 + row;
+    for (let col = 0; col < cropW; col++) {
+      const srcCol = cropX1 + col;
+      const srcIdx = srcRow * maskW + srcCol;
+      data[row * cropW + col] = (rawMask[srcIdx] ?? 0) > maskThreshold ? 255 : 0;
+    }
+  }
+  return { data, width: cropW, height: cropH };
+}
+function yoloSegPostprocess(segOutput, options) {
+  const {
+    detectionOutput,
+    protoOutput,
+    numClasses,
+    numBoxes,
+    numMaskCoeffs,
+    maskHeight,
+    maskWidth
+  } = segOutput;
+  const {
+    confidence,
+    iouThreshold,
+    labels,
+    scale,
+    padX,
+    padY,
+    originalWidth,
+    originalHeight,
+    maskThreshold = 0.5
+  } = options;
+  const yoloInputSize = 640;
+  const maskScale = maskHeight / yoloInputSize;
+  const candidates = [];
+  for (let i = 0; i < numBoxes; i++) {
+    const cx = detectionOutput[0 * numBoxes + i] ?? 0;
+    const cy = detectionOutput[1 * numBoxes + i] ?? 0;
+    const w = detectionOutput[2 * numBoxes + i] ?? 0;
+    const h = detectionOutput[3 * numBoxes + i] ?? 0;
+    let bestScore = -Infinity;
+    let bestClass = 0;
+    for (let j = 0; j < numClasses; j++) {
+      const score = detectionOutput[(4 + j) * numBoxes + i] ?? 0;
+      if (score > bestScore) {
+        bestScore = score;
+        bestClass = j;
+      }
+    }
+    if (bestScore < confidence) continue;
+    const bbox = {
+      x: cx - w / 2,
+      y: cy - h / 2,
+      w,
+      h
+    };
+    const coeffs = new Float32Array(numMaskCoeffs);
+    for (let k = 0; k < numMaskCoeffs; k++) {
+      coeffs[k] = detectionOutput[(4 + numClasses + k) * numBoxes + i] ?? 0;
+    }
+    candidates.push({ bbox, score: bestScore, classIdx: bestClass, coeffs });
+  }
+  if (candidates.length === 0) return [];
+  const keptIndices = nms(candidates, iouThreshold);
+  return keptIndices.map((idx) => {
+    const { bbox, score, classIdx, coeffs } = candidates[idx];
+    const label = labels[classIdx] ?? String(classIdx);
+    const x = Math.max(0, Math.min(originalWidth, (bbox.x - padX) / scale));
+    const y = Math.max(0, Math.min(originalHeight, (bbox.y - padY) / scale));
+    const x2 = Math.max(0, Math.min(originalWidth, (bbox.x + bbox.w - padX) / scale));
+    const y2 = Math.max(0, Math.min(originalHeight, (bbox.y + bbox.h - padY) / scale));
+    const finalBbox = { x, y, w: x2 - x, h: y2 - y };
+    const rawMask = computeRawMask(coeffs, protoOutput, numMaskCoeffs, maskHeight, maskWidth);
+    const { data: maskData, width: mW, height: mH } = cropAndThresholdMask(
+      rawMask,
+      maskHeight,
+      maskWidth,
+      bbox,
+      maskThreshold,
+      maskScale
+    );
+    return {
+      class: label,
+      originalClass: label,
+      score,
+      bbox: finalBbox,
+      mask: maskData,
+      maskWidth: mW,
+      maskHeight: mH
+    };
+  });
+}
+
+// src/addons/object-detection/index.ts
+function isSegModel(modelId) {
+  return modelId.includes("-seg");
+}
+var ALL_DETECTION_MODELS = [
+  ...OBJECT_DETECTION_MODELS,
+  ...SEGMENTATION_MODELS
+];
+function applyClassMap(detections, classMap) {
+  return detections.filter((d) => classMap.mapping[d.class] !== void 0).map((d) => ({
+    ...d,
+    originalClass: d.class,
+    class: classMap.mapping[d.class]
+  }));
+}
+var ObjectDetectionAddon = class {
+  id = "object-detection";
+  slot = "detector";
+  inputClasses = null;
+  outputClasses = ["person", "vehicle", "animal"];
+  slotPriority = 0;
+  manifest = {
+    id: "object-detection",
+    name: "Object Detection",
+    version: "0.1.0",
+    description: "YOLO-based object detection \u2014 detects persons, vehicles, and animals",
+    packageName: "@camstack/vision",
+    slot: "detector",
+    inputClasses: void 0,
+    outputClasses: ["person", "vehicle", "animal"],
+    supportsCustomModels: true,
+    mayRequirePython: false,
+    defaultConfig: {
+      modelId: "yolov8n",
+      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";
+    const runtime = cfg["runtime"] ?? "auto";
+    const backend = cfg["backend"] ?? "cpu";
+    this.confidence = cfg["confidence"] ?? 0.5;
+    this.iouThreshold = cfg["iouThreshold"] ?? 0.45;
+    const entry = ALL_DETECTION_MODELS.find((m) => m.id === modelId);
+    if (!entry) {
+      throw new Error(`ObjectDetectionAddon: unknown modelId "${modelId}"`);
+    }
+    this.modelEntry = entry;
+    const resolved = await resolveEngine({
+      runtime,
+      backend,
+      modelEntry: entry,
+      modelsDir: ctx.locationPaths.models
+    });
+    this.engine = resolved.engine;
+  }
+  async detect(frame) {
+    const start = Date.now();
+    const { width: inputW, height: inputH } = this.modelEntry.inputSize;
+    const targetSize = Math.max(inputW, inputH);
+    const lb = await letterbox(frame.data, targetSize);
+    const numClasses = this.modelEntry.labels.length;
+    const labels = this.modelEntry.labels.map((l) => l.id);
+    const postprocessOpts = {
+      confidence: this.confidence,
+      iouThreshold: this.iouThreshold,
+      labels,
+      scale: lb.scale,
+      padX: lb.padX,
+      padY: lb.padY,
+      originalWidth: lb.originalWidth,
+      originalHeight: lb.originalHeight
+    };
+    let rawDetections;
+    if (isSegModel(this.modelEntry.id)) {
+      const outputs = await this.engine.runMultiOutput(lb.data, [1, 3, targetSize, targetSize]);
+      const outputNames = Object.keys(outputs);
+      if (outputNames.length < 2) {
+        throw new Error(
+          `ObjectDetectionAddon: seg model "${this.modelEntry.id}" returned ${outputNames.length} output(s); expected 2`
+        );
+      }
+      const detectionOutput = outputs[outputNames[0]];
+      const protoOutput = outputs[outputNames[1]];
+      const numMaskCoeffs = 32;
+      const numBoxes = detectionOutput.length / (4 + numClasses + numMaskCoeffs);
+      const maskHeight = 160;
+      const maskWidth = 160;
+      rawDetections = yoloSegPostprocess(
+        {
+          detectionOutput,
+          protoOutput,
+          numClasses,
+          numBoxes,
+          numMaskCoeffs,
+          maskHeight,
+          maskWidth
+        },
+        postprocessOpts
+      );
+    } else {
+      const output = await this.engine.run(lb.data, [1, 3, targetSize, targetSize]);
+      const numBoxes = output.length / (4 + numClasses);
+      rawDetections = yoloPostprocess(output, numClasses, numBoxes, postprocessOpts);
+    }
+    const detections = applyClassMap(rawDetections, COCO_TO_MACRO);
+    return {
+      detections,
+      inferenceMs: Date.now() - start,
+      modelId: this.modelEntry.id
+    };
+  }
+  async shutdown() {
+    await this.engine?.dispose();
+  }
+  getConfigSchema() {
+    return {
+      sections: [
+        {
+          id: "model",
+          title: "Model",
+          columns: 2,
+          fields: [
+            {
+              key: "modelId",
+              label: "Model",
+              type: "model-selector",
+              catalog: [...ALL_DETECTION_MODELS],
+              allowCustom: true,
+              allowConversion: true,
+              acceptFormats: ["onnx", "coreml", "openvino", "tflite"],
+              requiredMetadata: ["inputSize", "labels", "outputFormat"],
+              outputFormatHint: "yolo"
+            }
+          ]
+        },
+        {
+          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)" },
+                { value: "openvino", label: "OpenVINO (Intel)" }
+              ]
+            },
+            {
+              key: "backend",
+              label: "Backend",
+              type: "select",
+              dependsOn: { runtime: "onnx" },
+              options: [
+                { value: "cpu", label: "CPU" },
+                { value: "coreml", label: "CoreML" },
+                { value: "cuda", label: "CUDA (NVIDIA)" },
+                { value: "tensorrt", label: "TensorRT (NVIDIA)" }
+              ]
+            }
+          ]
+        },
+        {
+          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 COCO_TO_MACRO;
+  }
+  getModelCatalog() {
+    return [...ALL_DETECTION_MODELS];
+  }
+  getAvailableModels() {
+    return [];
+  }
+  getActiveLabels() {
+    return MACRO_LABELS;
+  }
+  async probe() {
+    return {
+      available: true,
+      runtime: this.engine?.runtime ?? "onnx",
+      device: this.engine?.device ?? "cpu",
+      capabilities: ["fp32"]
+    };
+  }
+};
+
+export {
+  ObjectDetectionAddon
+};
+//# sourceMappingURL=chunk-CGYSSHHM.mjs.map

package/dist/chunk-CGYSSHHM.mjs.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../src/addons/object-detection/index.ts","../src/shared/postprocess/yolo-seg.ts"],"sourcesContent":["import type {\n  IDetectorProvider,\n  IDetectionAddon,\n  AddonManifest,\n  AddonContext,\n  FrameInput,\n  DetectorOutput,\n  SpatialDetection,\n  ConfigUISchema,\n  ClassMapDefinition,\n  ProbeResult,\n  ModelCatalogEntry,\n  DetectionModel,\n  LabelDefinition,\n  IInferenceEngine,\n} from '@camstack/types'\nimport {\n  OBJECT_DETECTION_MODELS,\n  SEGMENTATION_MODELS,\n  COCO_TO_MACRO,\n  MACRO_LABELS,\n} from '@camstack/types'\nimport { letterbox } from '../../shared/image-utils.js'\nimport { yoloPostprocess } from '../../shared/postprocess/yolo.js'\nimport { yoloSegPostprocess } from '../../shared/postprocess/yolo-seg.js'\nimport { resolveEngine } from '../../shared/engine-resolver.js'\n\n/** Returns true when the model id identifies a YOLO segmentation model (e.g. yolov8n-seg, yolo11m-seg) */\nfunction isSegModel(modelId: string): boolean {\n  return modelId.includes('-seg')\n}\n\n/** Combined catalog: regular detection models + segmentation models */\nconst ALL_DETECTION_MODELS: readonly ModelCatalogEntry[] = [\n  ...OBJECT_DETECTION_MODELS,\n  ...SEGMENTATION_MODELS,\n]\n\n/** Map COCO-class detections to macro categories (person/vehicle/animal) */\nfunction applyClassMap(\n  detections: SpatialDetection[],\n  classMap: ClassMapDefinition,\n): SpatialDetection[] {\n  return detections\n    .filter((d) => classMap.mapping[d.class] !== undefined)\n    .map((d) => ({\n      ...d,\n      originalClass: d.class,\n      class: classMap.mapping[d.class]!,\n    }))\n}\n\nexport default class ObjectDetectionAddon implements IDetectorProvider, IDetectionAddon {\n  readonly id = 'object-detection'\n  readonly slot = 'detector' as const\n  readonly inputClasses: readonly string[] | null = null\n  readonly outputClasses = ['person', 'vehicle', 'animal'] as const\n  readonly slotPriority = 0\n  readonly manifest: AddonManifest = {\n    id: 'object-detection',\n    name: 'Object Detection',\n    version: '0.1.0',\n    description: 'YOLO-based object detection — detects persons, vehicles, and animals',\n    packageName: '@camstack/vision',\n    slot: 'detector',\n    inputClasses: undefined,\n    outputClasses: ['person', 'vehicle', 'animal'],\n    supportsCustomModels: true,\n    mayRequirePython: false,\n    defaultConfig: {\n      modelId: 'yolov8n',\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'\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 = ALL_DETECTION_MODELS.find((m) => m.id === modelId)\n    if (!entry) {\n      throw new Error(`ObjectDetectionAddon: unknown modelId \"${modelId}\"`)\n    }\n    this.modelEntry = entry\n\n    const resolved = await resolveEngine({\n      runtime: runtime as 'auto',\n      backend,\n      modelEntry: entry,\n      modelsDir: ctx.locationPaths.models,\n    })\n    this.engine = resolved.engine\n  }\n\n  async detect(frame: FrameInput): Promise<DetectorOutput> {\n    const start = Date.now()\n    const { width: inputW, height: inputH } = this.modelEntry.inputSize\n    const targetSize = Math.max(inputW, inputH)\n\n    const lb = await letterbox(frame.data, targetSize)\n\n    const numClasses = this.modelEntry.labels.length\n    const labels = this.modelEntry.labels.map((l) => l.id)\n    const postprocessOpts = {\n      confidence: this.confidence,\n      iouThreshold: this.iouThreshold,\n      labels,\n      scale: lb.scale,\n      padX: lb.padX,\n      padY: lb.padY,\n      originalWidth: lb.originalWidth,\n      originalHeight: lb.originalHeight,\n    }\n\n    let rawDetections: SpatialDetection[]\n\n    if (isSegModel(this.modelEntry.id)) {\n      // YOLO-seg models produce two outputs:\n      //   output0: [1, 4 + numClasses + 32, numBoxes]  (detection + mask coefficients)\n      //   output1: [1, 32, 160, 160]                   (prototype masks)\n      const outputs = await this.engine.runMultiOutput(lb.data, [1, 3, targetSize, targetSize])\n      const outputNames = Object.keys(outputs)\n\n      if (outputNames.length < 2) {\n        throw new Error(\n          `ObjectDetectionAddon: seg model \"${this.modelEntry.id}\" returned ${outputNames.length} output(s); expected 2`,\n        )\n      }\n\n      // ONNX output order is deterministic; first output is the detection tensor, second is protos\n      const detectionOutput = outputs[outputNames[0]!]!\n      const protoOutput = outputs[outputNames[1]!]!\n\n      // Infer dims from tensor sizes\n      const numMaskCoeffs = 32\n      const numBoxes = detectionOutput.length / (4 + numClasses + numMaskCoeffs)\n      const maskHeight = 160\n      const maskWidth = 160\n\n      rawDetections = yoloSegPostprocess(\n        {\n          detectionOutput,\n          protoOutput,\n          numClasses,\n          numBoxes,\n          numMaskCoeffs,\n          maskHeight,\n          maskWidth,\n        },\n        postprocessOpts,\n      )\n    } else {\n      // Standard YOLO output: [1, 4+numClasses, numBoxes]\n      const output = await this.engine.run(lb.data, [1, 3, targetSize, targetSize])\n      const numBoxes = output.length / (4 + numClasses)\n      rawDetections = yoloPostprocess(output, numClasses, numBoxes, postprocessOpts)\n    }\n\n    const detections = applyClassMap(rawDetections, COCO_TO_MACRO)\n\n    return {\n      detections,\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: 2,\n          fields: [\n            {\n              key: 'modelId',\n              label: 'Model',\n              type: 'model-selector',\n              catalog: [...ALL_DETECTION_MODELS],\n              allowCustom: true,\n              allowConversion: true,\n              acceptFormats: ['onnx', 'coreml', 'openvino', 'tflite'],\n              requiredMetadata: ['inputSize', 'labels', 'outputFormat'],\n              outputFormatHint: 'yolo',\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                { 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: 'coreml', label: 'CoreML' },\n                { value: 'cuda', label: 'CUDA (NVIDIA)' },\n                { value: 'tensorrt', label: 'TensorRT (NVIDIA)' },\n              ],\n            },\n          ],\n        },\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 COCO_TO_MACRO\n  }\n\n  getModelCatalog(): ModelCatalogEntry[] {\n    return [...ALL_DETECTION_MODELS]\n  }\n\n  getAvailableModels(): DetectionModel[] {\n    // TODO: check downloaded models in modelsDir\n    return []\n  }\n\n  getActiveLabels(): readonly LabelDefinition[] {\n    return MACRO_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 } from '@camstack/types'\nimport { nms, iou as _iou } from './yolo.js'\nimport type { YoloPostprocessOptions } from './yolo.js'\n\nexport interface YoloSegOutput {\n  /** Detection output: [1, 4 + numClasses + numMaskCoeffs, numBoxes] (row-major, batch dim stripped) */\n  readonly detectionOutput: Float32Array\n  /** Prototype masks: [1, numMaskCoeffs, maskH, maskW] (batch dim stripped) */\n  readonly protoOutput: Float32Array\n  readonly numClasses: number\n  readonly numBoxes: number\n  /** Number of mask prototype coefficients per detection (typically 32) */\n  readonly numMaskCoeffs: number\n  /** Height of prototype mask grid (typically 160) */\n  readonly maskHeight: number\n  /** Width of prototype mask grid (typically 160) */\n  readonly maskWidth: number\n}\n\nexport interface YoloSegPostprocessOptions extends YoloPostprocessOptions {\n  /** Binary mask threshold — pixels above this value become 255, others 0 (default: 0.5) */\n  readonly maskThreshold?: number\n}\n\n/** Sigmoid activation: σ(x) = 1 / (1 + e^-x) */\nexport function sigmoid(x: number): number {\n  return 1 / (1 + Math.exp(-x))\n}\n\n/**\n * Compute instance segmentation mask for a single detection.\n *\n * @param coeffs   [numMaskCoeffs] mask coefficients for this detection\n * @param protos   [numMaskCoeffs × maskH × maskW] prototype masks (flat, row-major)\n * @param numMaskCoeffs  number of prototype channels (e.g. 32)\n * @param maskH    prototype grid height (e.g. 160)\n * @param maskW    prototype grid width  (e.g. 160)\n * @returns        [maskH × maskW] sigmoid-activated raw mask values in [0, 1]\n */\nexport function computeRawMask(\n  coeffs: Float32Array,\n  protos: Float32Array,\n  numMaskCoeffs: number,\n  maskH: number,\n  maskW: number,\n): Float32Array {\n  const maskSize = maskH * maskW\n  const rawMask = new Float32Array(maskSize)\n\n  // mask_raw[y * maskW + x] = sum_k( coeffs[k] * protos[k * maskSize + y * maskW + x] )\n  // Then apply sigmoid element-wise.\n  for (let px = 0; px < maskSize; px++) {\n    let val = 0\n    for (let k = 0; k < numMaskCoeffs; k++) {\n      val += (coeffs[k] ?? 0) * (protos[k * maskSize + px] ?? 0)\n    }\n    rawMask[px] = sigmoid(val)\n  }\n\n  return rawMask\n}\n\n/**\n * Crop a flat [maskH × maskW] mask to a bounding box region (in mask coordinate space),\n * threshold to binary, and return the cropped Uint8Array along with its dimensions.\n *\n * @param rawMask       [maskH × maskW] sigmoid-activated values in [0, 1]\n * @param maskH         full mask grid height\n * @param maskW         full mask grid width\n * @param bbox          detection bounding box in the inference input space (e.g. 640×640 letterboxed)\n * @param maskThreshold threshold above which a pixel is considered foreground (default 0.5)\n * @param maskScale     ratio of mask resolution to inference resolution (e.g. 160/640 = 0.25)\n * @returns             { data: Uint8Array, width, height } of the cropped binary mask\n */\nexport function cropAndThresholdMask(\n  rawMask: Float32Array,\n  maskH: number,\n  maskW: number,\n  bbox: BoundingBox,\n  maskThreshold: number,\n  maskScale: number,\n): { readonly data: Uint8Array; readonly width: number; readonly height: number } {\n  const cropX1 = Math.max(0, Math.floor(bbox.x * maskScale))\n  const cropY1 = Math.max(0, Math.floor(bbox.y * maskScale))\n  const cropX2 = Math.min(maskW, Math.ceil((bbox.x + bbox.w) * maskScale))\n  const cropY2 = Math.min(maskH, Math.ceil((bbox.y + bbox.h) * maskScale))\n\n  const cropW = Math.max(1, cropX2 - cropX1)\n  const cropH = Math.max(1, cropY2 - cropY1)\n\n  const data = new Uint8Array(cropW * cropH)\n\n  for (let row = 0; row < cropH; row++) {\n    const srcRow = cropY1 + row\n    for (let col = 0; col < cropW; col++) {\n      const srcCol = cropX1 + col\n      const srcIdx = srcRow * maskW + srcCol\n      data[row * cropW + col] = (rawMask[srcIdx] ?? 0) > maskThreshold ? 255 : 0\n    }\n  }\n\n  return { data, width: cropW, height: cropH }\n}\n\n/**\n * YOLO-seg postprocessing: run detection filtering + NMS, then decode instance masks.\n *\n * The seg detection tensor has layout [1, 4 + numClasses + numMaskCoeffs, numBoxes]:\n *   rows 0–3            : cx, cy, w, h\n *   rows 4 to 4+C-1     : class scores\n *   rows 4+C to end     : mask coefficients (32)\n *\n * Steps:\n *   1. Filter boxes by confidence threshold, collecting mask coefficients per candidate.\n *   2. Run NMS across all candidates.\n *   3. For each surviving detection, compute the instance mask and attach it.\n */\nexport function yoloSegPostprocess(\n  segOutput: YoloSegOutput,\n  options: YoloSegPostprocessOptions,\n): SpatialDetection[] {\n  const {\n    detectionOutput,\n    protoOutput,\n    numClasses,\n    numBoxes,\n    numMaskCoeffs,\n    maskHeight,\n    maskWidth,\n  } = segOutput\n\n  const {\n    confidence,\n    iouThreshold,\n    labels,\n    scale,\n    padX,\n    padY,\n    originalWidth,\n    originalHeight,\n    maskThreshold = 0.5,\n  } = options\n\n  // The mask resolution to inference resolution scale factor (e.g. 160/640 = 0.25)\n  // We derive the inference size from scale/pad context: the letterboxed input is typically 640×640\n  // but we receive coordinates in that space already, so we use maskHeight / inferH.\n  // Since all YOLO-seg models use 640×640 input and 160×160 proto, the ratio is always 160/640.\n  // We compute it generically from the known prototype dims + fixed YOLO input of 640.\n  const yoloInputSize = 640\n  const maskScale = maskHeight / yoloInputSize\n\n  interface Candidate {\n    readonly bbox: BoundingBox\n    readonly score: number\n    readonly classIdx: number\n    readonly coeffs: Float32Array\n  }\n\n  const candidates: Candidate[] = []\n\n  for (let i = 0; i < numBoxes; i++) {\n    const cx = detectionOutput[0 * numBoxes + i] ?? 0\n    const cy = detectionOutput[1 * numBoxes + i] ?? 0\n    const w = detectionOutput[2 * numBoxes + i] ?? 0\n    const h = detectionOutput[3 * numBoxes + i] ?? 0\n\n    let bestScore = -Infinity\n    let bestClass = 0\n\n    for (let j = 0; j < numClasses; j++) {\n      const score = detectionOutput[(4 + j) * numBoxes + i] ?? 0\n      if (score > bestScore) {\n        bestScore = score\n        bestClass = j\n      }\n    }\n\n    if (bestScore < confidence) continue\n\n    const bbox: BoundingBox = {\n      x: cx - w / 2,\n      y: cy - h / 2,\n      w,\n      h,\n    }\n\n    // Extract mask coefficients for this box\n    const coeffs = new Float32Array(numMaskCoeffs)\n    for (let k = 0; k < numMaskCoeffs; k++) {\n      coeffs[k] = detectionOutput[(4 + numClasses + k) * numBoxes + i] ?? 0\n    }\n\n    candidates.push({ bbox, score: bestScore, classIdx: bestClass, coeffs })\n  }\n\n  if (candidates.length === 0) return []\n\n  const keptIndices = nms(candidates, iouThreshold)\n\n  return keptIndices.map((idx) => {\n    const { bbox, score, classIdx, coeffs } = candidates[idx]!\n    const label = labels[classIdx] ?? String(classIdx)\n\n    // Scale bbox back from letterbox space to original image coords\n    const x = Math.max(0, Math.min(originalWidth, (bbox.x - padX) / scale))\n    const y = Math.max(0, Math.min(originalHeight, (bbox.y - padY) / scale))\n    const x2 = Math.max(0, Math.min(originalWidth, (bbox.x + bbox.w - padX) / scale))\n    const y2 = Math.max(0, Math.min(originalHeight, (bbox.y + bbox.h - padY) / scale))\n    const finalBbox: BoundingBox = { x, y, w: x2 - x, h: y2 - y }\n\n    // Decode instance mask using the letterbox-space bbox (before coord scaling)\n    const rawMask = computeRawMask(coeffs, protoOutput, numMaskCoeffs, maskHeight, maskWidth)\n    const { data: maskData, width: mW, height: mH } = cropAndThresholdMask(\n      rawMask,\n      maskHeight,\n      maskWidth,\n      bbox,\n      maskThreshold,\n      maskScale,\n    )\n\n    return {\n      class: label,\n      originalClass: label,\n      score,\n      bbox: finalBbox,\n      mask: maskData,\n      maskWidth: mW,\n      maskHeight: mH,\n    } satisfies SpatialDetection\n  })\n}\n"],"mappings":";;;;;;;;;;;;AAgBA;AAAA,EACE;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,OACK;;;ACIA,SAAS,QAAQ,GAAmB;AACzC,SAAO,KAAK,IAAI,KAAK,IAAI,CAAC,CAAC;AAC7B;AAYO,SAAS,eACd,QACA,QACA,eACA,OACA,OACc;AACd,QAAM,WAAW,QAAQ;AACzB,QAAM,UAAU,IAAI,aAAa,QAAQ;AAIzC,WAAS,KAAK,GAAG,KAAK,UAAU,MAAM;AACpC,QAAI,MAAM;AACV,aAAS,IAAI,GAAG,IAAI,eAAe,KAAK;AACtC,cAAQ,OAAO,CAAC,KAAK,MAAM,OAAO,IAAI,WAAW,EAAE,KAAK;AAAA,IAC1D;AACA,YAAQ,EAAE,IAAI,QAAQ,GAAG;AAAA,EAC3B;AAEA,SAAO;AACT;AAcO,SAAS,qBACd,SACA,OACA,OACA,MACA,eACA,WACgF;AAChF,QAAM,SAAS,KAAK,IAAI,GAAG,KAAK,MAAM,KAAK,IAAI,SAAS,CAAC;AACzD,QAAM,SAAS,KAAK,IAAI,GAAG,KAAK,MAAM,KAAK,IAAI,SAAS,CAAC;AACzD,QAAM,SAAS,KAAK,IAAI,OAAO,KAAK,MAAM,KAAK,IAAI,KAAK,KAAK,SAAS,CAAC;AACvE,QAAM,SAAS,KAAK,IAAI,OAAO,KAAK,MAAM,KAAK,IAAI,KAAK,KAAK,SAAS,CAAC;AAEvE,QAAM,QAAQ,KAAK,IAAI,GAAG,SAAS,MAAM;AACzC,QAAM,QAAQ,KAAK,IAAI,GAAG,SAAS,MAAM;AAEzC,QAAM,OAAO,IAAI,WAAW,QAAQ,KAAK;AAEzC,WAAS,MAAM,GAAG,MAAM,OAAO,OAAO;AACpC,UAAM,SAAS,SAAS;AACxB,aAAS,MAAM,GAAG,MAAM,OAAO,OAAO;AACpC,YAAM,SAAS,SAAS;AACxB,YAAM,SAAS,SAAS,QAAQ;AAChC,WAAK,MAAM,QAAQ,GAAG,KAAK,QAAQ,MAAM,KAAK,KAAK,gBAAgB,MAAM;AAAA,IAC3E;AAAA,EACF;AAEA,SAAO,EAAE,MAAM,OAAO,OAAO,QAAQ,MAAM;AAC7C;AAeO,SAAS,mBACd,WACA,SACoB;AACpB,QAAM;AAAA,IACJ;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,EACF,IAAI;AAEJ,QAAM;AAAA,IACJ;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,IACA,gBAAgB;AAAA,EAClB,IAAI;AAOJ,QAAM,gBAAgB;AACtB,QAAM,YAAY,aAAa;AAS/B,QAAM,aAA0B,CAAC;AAEjC,WAAS,IAAI,GAAG,IAAI,UAAU,KAAK;AACjC,UAAM,KAAK,gBAAgB,IAAI,WAAW,CAAC,KAAK;AAChD,UAAM,KAAK,gBAAgB,IAAI,WAAW,CAAC,KAAK;AAChD,UAAM,IAAI,gBAAgB,IAAI,WAAW,CAAC,KAAK;AAC/C,UAAM,IAAI,gBAAgB,IAAI,WAAW,CAAC,KAAK;AAE/C,QAAI,YAAY;AAChB,QAAI,YAAY;AAEhB,aAAS,IAAI,GAAG,IAAI,YAAY,KAAK;AACnC,YAAM,QAAQ,iBAAiB,IAAI,KAAK,WAAW,CAAC,KAAK;AACzD,UAAI,QAAQ,WAAW;AACrB,oBAAY;AACZ,oBAAY;AAAA,MACd;AAAA,IACF;AAEA,QAAI,YAAY,WAAY;AAE5B,UAAM,OAAoB;AAAA,MACxB,GAAG,KAAK,IAAI;AAAA,MACZ,GAAG,KAAK,IAAI;AAAA,MACZ;AAAA,MACA;AAAA,IACF;AAGA,UAAM,SAAS,IAAI,aAAa,aAAa;AAC7C,aAAS,IAAI,GAAG,IAAI,eAAe,KAAK;AACtC,aAAO,CAAC,IAAI,iBAAiB,IAAI,aAAa,KAAK,WAAW,CAAC,KAAK;AAAA,IACtE;AAEA,eAAW,KAAK,EAAE,MAAM,OAAO,WAAW,UAAU,WAAW,OAAO,CAAC;AAAA,EACzE;AAEA,MAAI,WAAW,WAAW,EAAG,QAAO,CAAC;AAErC,QAAM,cAAc,IAAI,YAAY,YAAY;AAEhD,SAAO,YAAY,IAAI,CAAC,QAAQ;AAC9B,UAAM,EAAE,MAAM,OAAO,UAAU,OAAO,IAAI,WAAW,GAAG;AACxD,UAAM,QAAQ,OAAO,QAAQ,KAAK,OAAO,QAAQ;AAGjD,UAAM,IAAI,KAAK,IAAI,GAAG,KAAK,IAAI,gBAAgB,KAAK,IAAI,QAAQ,KAAK,CAAC;AACtE,UAAM,IAAI,KAAK,IAAI,GAAG,KAAK,IAAI,iBAAiB,KAAK,IAAI,QAAQ,KAAK,CAAC;AACvE,UAAM,KAAK,KAAK,IAAI,GAAG,KAAK,IAAI,gBAAgB,KAAK,IAAI,KAAK,IAAI,QAAQ,KAAK,CAAC;AAChF,UAAM,KAAK,KAAK,IAAI,GAAG,KAAK,IAAI,iBAAiB,KAAK,IAAI,KAAK,IAAI,QAAQ,KAAK,CAAC;AACjF,UAAM,YAAyB,EAAE,GAAG,GAAG,GAAG,KAAK,GAAG,GAAG,KAAK,EAAE;AAG5D,UAAM,UAAU,eAAe,QAAQ,aAAa,eAAe,YAAY,SAAS;AACxF,UAAM,EAAE,MAAM,UAAU,OAAO,IAAI,QAAQ,GAAG,IAAI;AAAA,MAChD;AAAA,MACA;AAAA,MACA;AAAA,MACA;AAAA,MACA;AAAA,MACA;AAAA,IACF;AAEA,WAAO;AAAA,MACL,OAAO;AAAA,MACP,eAAe;AAAA,MACf;AAAA,MACA,MAAM;AAAA,MACN,MAAM;AAAA,MACN,WAAW;AAAA,MACX,YAAY;AAAA,IACd;AAAA,EACF,CAAC;AACH;;;AD3MA,SAAS,WAAW,SAA0B;AAC5C,SAAO,QAAQ,SAAS,MAAM;AAChC;AAGA,IAAM,uBAAqD;AAAA,EACzD,GAAG;AAAA,EACH,GAAG;AACL;AAGA,SAAS,cACP,YACA,UACoB;AACpB,SAAO,WACJ,OAAO,CAAC,MAAM,SAAS,QAAQ,EAAE,KAAK,MAAM,MAAS,EACrD,IAAI,CAAC,OAAO;AAAA,IACX,GAAG;AAAA,IACH,eAAe,EAAE;AAAA,IACjB,OAAO,SAAS,QAAQ,EAAE,KAAK;AAAA,EACjC,EAAE;AACN;AAEA,IAAqB,uBAArB,MAAwF;AAAA,EAC7E,KAAK;AAAA,EACL,OAAO;AAAA,EACP,eAAyC;AAAA,EACzC,gBAAgB,CAAC,UAAU,WAAW,QAAQ;AAAA,EAC9C,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,UAAU,WAAW,QAAQ;AAAA,IAC7C,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,qBAAqB,KAAK,CAAC,MAAM,EAAE,OAAO,OAAO;AAC/D,QAAI,CAAC,OAAO;AACV,YAAM,IAAI,MAAM,0CAA0C,OAAO,GAAG;AAAA,IACtE;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,OAAO,OAA4C;AACvD,UAAM,QAAQ,KAAK,IAAI;AACvB,UAAM,EAAE,OAAO,QAAQ,QAAQ,OAAO,IAAI,KAAK,WAAW;AAC1D,UAAM,aAAa,KAAK,IAAI,QAAQ,MAAM;AAE1C,UAAM,KAAK,MAAM,UAAU,MAAM,MAAM,UAAU;AAEjD,UAAM,aAAa,KAAK,WAAW,OAAO;AAC1C,UAAM,SAAS,KAAK,WAAW,OAAO,IAAI,CAAC,MAAM,EAAE,EAAE;AACrD,UAAM,kBAAkB;AAAA,MACtB,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;AAEA,QAAI;AAEJ,QAAI,WAAW,KAAK,WAAW,EAAE,GAAG;AAIlC,YAAM,UAAU,MAAM,KAAK,OAAO,eAAe,GAAG,MAAM,CAAC,GAAG,GAAG,YAAY,UAAU,CAAC;AACxF,YAAM,cAAc,OAAO,KAAK,OAAO;AAEvC,UAAI,YAAY,SAAS,GAAG;AAC1B,cAAM,IAAI;AAAA,UACR,oCAAoC,KAAK,WAAW,EAAE,cAAc,YAAY,MAAM;AAAA,QACxF;AAAA,MACF;AAGA,YAAM,kBAAkB,QAAQ,YAAY,CAAC,CAAE;AAC/C,YAAM,cAAc,QAAQ,YAAY,CAAC,CAAE;AAG3C,YAAM,gBAAgB;AACtB,YAAM,WAAW,gBAAgB,UAAU,IAAI,aAAa;AAC5D,YAAM,aAAa;AACnB,YAAM,YAAY;AAElB,sBAAgB;AAAA,QACd;AAAA,UACE;AAAA,UACA;AAAA,UACA;AAAA,UACA;AAAA,UACA;AAAA,UACA;AAAA,UACA;AAAA,QACF;AAAA,QACA;AAAA,MACF;AAAA,IACF,OAAO;AAEL,YAAM,SAAS,MAAM,KAAK,OAAO,IAAI,GAAG,MAAM,CAAC,GAAG,GAAG,YAAY,UAAU,CAAC;AAC5E,YAAM,WAAW,OAAO,UAAU,IAAI;AACtC,sBAAgB,gBAAgB,QAAQ,YAAY,UAAU,eAAe;AAAA,IAC/E;AAEA,UAAM,aAAa,cAAc,eAAe,aAAa;AAE7D,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,oBAAoB;AAAA,cACjC,aAAa;AAAA,cACb,iBAAiB;AAAA,cACjB,eAAe,CAAC,QAAQ,UAAU,YAAY,QAAQ;AAAA,cACtD,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,SAAS;AAAA,gBACP,EAAE,OAAO,QAAQ,OAAO,qBAAqB;AAAA,gBAC7C,EAAE,OAAO,QAAQ,OAAO,eAAe;AAAA,gBACvC,EAAE,OAAO,UAAU,OAAO,iBAAiB;AAAA,gBAC3C,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,UAAU,OAAO,SAAS;AAAA,gBACnC,EAAE,OAAO,QAAQ,OAAO,gBAAgB;AAAA,gBACxC,EAAE,OAAO,YAAY,OAAO,oBAAoB;AAAA,cAClD;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,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,oBAAoB;AAAA,EACjC;AAAA,EAEA,qBAAuC;AAErC,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-IYHMGYGP.mjs

@@ -0,0 +1,79 @@
+// src/addons/camera-native-detection/index.ts
+var NATIVE_LABELS = [
+  { id: "person", name: "Person" },
+  { id: "vehicle", name: "Vehicle" },
+  { id: "motion", name: "Motion" },
+  { id: "face", name: "Face" }
+];
+var NATIVE_CLASS_MAP = { mapping: {}, preserveOriginal: true };
+var CameraNativeDetectionAddon = class {
+  id = "camera-native-detection";
+  slot = "detector";
+  inputClasses = null;
+  outputClasses = ["person", "vehicle", "motion", "face"];
+  slotPriority = 5;
+  manifest = {
+    id: "camera-native-detection",
+    name: "Camera Native Detection",
+    version: "0.1.0",
+    description: "Passthrough adapter for camera-native events (Frigate, Scrypted, ONVIF) \u2014 no inference engine",
+    packageName: "@camstack/vision",
+    slot: "detector",
+    inputClasses: void 0,
+    outputClasses: ["person", "vehicle", "motion", "face"],
+    supportsCustomModels: false,
+    mayRequirePython: false,
+    defaultConfig: {}
+  };
+  // eslint-disable-next-line @typescript-eslint/no-unused-vars
+  async initialize(_ctx) {
+  }
+  // eslint-disable-next-line @typescript-eslint/no-unused-vars
+  async detect(_frame) {
+    return {
+      detections: [],
+      inferenceMs: 0,
+      modelId: "camera-native"
+    };
+  }
+  async shutdown() {
+  }
+  getConfigSchema() {
+    return {
+      sections: [
+        {
+          id: "info",
+          title: "Camera Native Detection",
+          description: "This addon forwards detections from native camera events (Frigate webhooks, Scrypted push notifications, ONVIF events). No configuration required.",
+          fields: []
+        }
+      ]
+    };
+  }
+  getClassMap() {
+    return NATIVE_CLASS_MAP;
+  }
+  getModelCatalog() {
+    return [];
+  }
+  getAvailableModels() {
+    return [];
+  }
+  getActiveLabels() {
+    return NATIVE_LABELS;
+  }
+  async probe() {
+    return {
+      available: true,
+      runtime: "onnx",
+      // no runtime used; satisfies the type
+      device: "cpu",
+      capabilities: ["fp32"]
+    };
+  }
+};
+
+export {
+  CameraNativeDetectionAddon
+};
+//# sourceMappingURL=chunk-IYHMGYGP.mjs.map

package/dist/chunk-IYHMGYGP.mjs.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../src/addons/camera-native-detection/index.ts"],"sourcesContent":["import type {\n  IDetectorProvider,\n  IDetectionAddon,\n  AddonManifest,\n  AddonContext,\n  FrameInput,\n  DetectorOutput,\n  ConfigUISchema,\n  ClassMapDefinition,\n  ProbeResult,\n  ModelCatalogEntry,\n  DetectionModel,\n  LabelDefinition,\n} from '@camstack/types'\n\n// Labels reported by cameras natively (a superset across manufacturers)\nconst NATIVE_LABELS: readonly LabelDefinition[] = [\n  { id: 'person', name: 'Person' },\n  { id: 'vehicle', name: 'Vehicle' },\n  { id: 'motion', name: 'Motion' },\n  { id: 'face', name: 'Face' },\n] as const\n\nconst NATIVE_CLASS_MAP: ClassMapDefinition = { mapping: {}, preserveOriginal: true }\n\n/**\n * CameraNativeDetectionAddon\n *\n * A stub detector that wraps native camera event subscriptions (e.g. Frigate / Scrypted\n * webhooks). The detect() method always returns empty — real detections are delivered\n * asynchronously via external event subscriptions which should populate the pipeline\n * from outside this addon's detect() call.\n *\n * This addon exists so the pipeline can declare a 'detector' slot backed by camera events\n * without requiring any inference model.\n */\nexport default class CameraNativeDetectionAddon implements IDetectorProvider, IDetectionAddon {\n  readonly id = 'camera-native-detection'\n  readonly slot = 'detector' as const\n  readonly inputClasses: readonly string[] | null = null\n  readonly outputClasses = ['person', 'vehicle', 'motion', 'face'] as const\n  readonly slotPriority = 5\n  readonly manifest: AddonManifest = {\n    id: 'camera-native-detection',\n    name: 'Camera Native Detection',\n    version: '0.1.0',\n    description:\n      'Passthrough adapter for camera-native events (Frigate, Scrypted, ONVIF) — no inference engine',\n    packageName: '@camstack/vision',\n    slot: 'detector',\n    inputClasses: undefined,\n    outputClasses: ['person', 'vehicle', 'motion', 'face'],\n    supportsCustomModels: false,\n    mayRequirePython: false,\n    defaultConfig: {},\n  }\n\n  // eslint-disable-next-line @typescript-eslint/no-unused-vars\n  async initialize(_ctx: AddonContext): Promise<void> {\n    // No engine to initialize — events come from external subscriptions\n  }\n\n  // eslint-disable-next-line @typescript-eslint/no-unused-vars\n  async detect(_frame: FrameInput): Promise<DetectorOutput> {\n    // Real detections are delivered via event subscriptions, not through detect().\n    // This method intentionally returns empty.\n    return {\n      detections: [],\n      inferenceMs: 0,\n      modelId: 'camera-native',\n    }\n  }\n\n  async shutdown(): Promise<void> {\n    // Nothing to tear down\n  }\n\n  getConfigSchema(): ConfigUISchema {\n    return {\n      sections: [\n        {\n          id: 'info',\n          title: 'Camera Native Detection',\n          description:\n            'This addon forwards detections from native camera events (Frigate webhooks, ' +\n            'Scrypted push notifications, ONVIF events). No configuration required.',\n          fields: [],\n        },\n      ],\n    }\n  }\n\n  getClassMap(): ClassMapDefinition {\n    return NATIVE_CLASS_MAP\n  }\n\n  getModelCatalog(): ModelCatalogEntry[] {\n    return []\n  }\n\n  getAvailableModels(): DetectionModel[] {\n    return []\n  }\n\n  getActiveLabels(): readonly LabelDefinition[] {\n    return NATIVE_LABELS\n  }\n\n  async probe(): Promise<ProbeResult> {\n    return {\n      available: true,\n      runtime: 'onnx', // no runtime used; satisfies the type\n      device: 'cpu',\n      capabilities: ['fp32'],\n    }\n  }\n}\n"],"mappings":";AAgBA,IAAM,gBAA4C;AAAA,EAChD,EAAE,IAAI,UAAU,MAAM,SAAS;AAAA,EAC/B,EAAE,IAAI,WAAW,MAAM,UAAU;AAAA,EACjC,EAAE,IAAI,UAAU,MAAM,SAAS;AAAA,EAC/B,EAAE,IAAI,QAAQ,MAAM,OAAO;AAC7B;AAEA,IAAM,mBAAuC,EAAE,SAAS,CAAC,GAAG,kBAAkB,KAAK;AAanF,IAAqB,6BAArB,MAA8F;AAAA,EACnF,KAAK;AAAA,EACL,OAAO;AAAA,EACP,eAAyC;AAAA,EACzC,gBAAgB,CAAC,UAAU,WAAW,UAAU,MAAM;AAAA,EACtD,eAAe;AAAA,EACf,WAA0B;AAAA,IACjC,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,SAAS;AAAA,IACT,aACE;AAAA,IACF,aAAa;AAAA,IACb,MAAM;AAAA,IACN,cAAc;AAAA,IACd,eAAe,CAAC,UAAU,WAAW,UAAU,MAAM;AAAA,IACrD,sBAAsB;AAAA,IACtB,kBAAkB;AAAA,IAClB,eAAe,CAAC;AAAA,EAClB;AAAA;AAAA,EAGA,MAAM,WAAW,MAAmC;AAAA,EAEpD;AAAA;AAAA,EAGA,MAAM,OAAO,QAA6C;AAGxD,WAAO;AAAA,MACL,YAAY,CAAC;AAAA,MACb,aAAa;AAAA,MACb,SAAS;AAAA,IACX;AAAA,EACF;AAAA,EAEA,MAAM,WAA0B;AAAA,EAEhC;AAAA,EAEA,kBAAkC;AAChC,WAAO;AAAA,MACL,UAAU;AAAA,QACR;AAAA,UACE,IAAI;AAAA,UACJ,OAAO;AAAA,UACP,aACE;AAAA,UAEF,QAAQ,CAAC;AAAA,QACX;AAAA,MACF;AAAA,IACF;AAAA,EACF;AAAA,EAEA,cAAkC;AAChC,WAAO;AAAA,EACT;AAAA,EAEA,kBAAuC;AACrC,WAAO,CAAC;AAAA,EACV;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;AAAA;AAAA,MACT,QAAQ;AAAA,MACR,cAAc,CAAC,MAAM;AAAA,IACvB;AAAA,EACF;AACF;","names":[]}