\r \r

Kami Package Detection\r

\r

Get notified the moment a package arrives at your door.\r \r Monitor your camera feed for packages, parcels, backpacks, handbags, and suitcases. When detected, returns the object class and bounding box as JSON — ready for automation.\r \r

Features\r

\r

• 📦 Package & parcel detection\r
• 🧳 Suitcase / backpack / handbag recognition\r
• 🏠 Doorstep & reception monitoring\r
• ⏱ Configurable detection duration\r
• 🔔 JSON output for easy integration\r \r

Scenarios\r

\r

• Doorstep delivery waiting\r
• Office reception package management\r
• Warehouse cargo monitoring\r
• Temporary item watch\r \r

Installation\r

\r

bash setup.sh\r
```\r
\r
Creates `.venv/` and installs `onnxruntime`, `opencv-python-headless`, `numpy`. Idempotent.\r
\r
## Prerequisites\r
\r
- `python3` and `python3-venv` installed\r
- `yolov8s-worldv2.onnx` model file in the skill directory\r
- RTSP camera online and reachable\r
\r
### Model\r
\r
The `yolov8s-worldv2.onnx` model file is included in the skill package. If missing, re-download this skill from ClawHub:\r
\r
```bash\r
clawhub install kami-package-detection\r
```\r
\r
Alternatively, download the YOLOv8s-World v2 `.pt` model from [Ultralytics YOLO-World](https://docs.ultralytics.com/models/yolo-world/) and export it to ONNX yourself. Make sure the class names used during export match the `--class_names` parameter:\r
\r
```bash\r
pip install ultralytics\r
yolo export model=yolov8s-worldv2.pt format=onnx imgsz=320\r
cp yolov8s-worldv2.onnx /path/to/kami-package-detection/\r
```\r
\r
## Parameter Confirmation\r
\r
Before running, confirm these parameters with the user:\r
\r
| Parameter | Default | Description |\r
|-----------|---------|-------------|\r
| `--rtsp_url` | `rtsp://127.0.0.1/live/TNPUSAQ-757597-DRFMY` | RTSP camera URL |\r
| `--conf_threshold` | `0.25` | Confidence threshold (0.0–1.0) |\r
| `--class_names` | `parcel package "delivery box" person "Cardboard box" "Packaging Box" backpack handbag suitcase` | Classes to detect |\r
| `--run_time` | `60` | Max seconds; `0` = unlimited |\r
\r
**Ask the user: do any parameters need to be changed?**\r
\r
## Usage\r
\r
```bash\r
.venv/bin/python yolo_world_onnx.py \\r
  --rtsp_url rtsp://your-camera-address \\r
  --run_time 60\r
```\r
\r
## Output (stdout JSON)\r
\r
```json\r
{\r
  "detections": [\r
    {\r
      "class_name": "parcel",\r
      "bbox": {"x1": 100, "y1": 200, "x2": 300, "y2": 400}\r
    }\r
  ]\r
}\r
```\r
\r
| Field | Type | Description |\r
|-------|------|-------------|\r
| `class_name` | string | Detected object class |\r
| `bbox.x1, y1, x2, y2` | int | Bounding box coordinates |\r
\r
## Exit Codes\r
\r
| Code | Meaning |\r
|------|---------|\r
| `0` | Target detected, JSON output written |\r
| `1` | Error (model missing, RTSP failure, runtime exception) |\r
| `2` | Timeout, no target detected within `--run_time` |\r
\r
## Troubleshooting\r
\r
- `bash: .venv/bin/python: No such file or directory` → Run `bash setup.sh`\r
- `Model file not found` → Place `yolov8s-worldv2.onnx` in the skill directory\r
- `Cannot open video` → Check camera is online and `--rtsp_url` is correct\r