feat: add engine auto-recompilation, mortality detection, multi-execution batching, and dashboard updates

- Add engine_utils for TensorRT compatibility verification, auto-recompilation from .pt models, and YAML auto-updates - Add mortality detection pipeline (mortality.py, test_run_mortality.sh, mortality_config.yaml) - Add multi-execution batch modes (parallel_processes, tensor_batching, hybrid) in batch_runner.py - Add daily test run automation scripts and video processing runners - Add dashboard REST API, live stream endpoints, and web UI templates - Clean up git tracking by ignoring __pycache__, .pyc, and build artifacts
2026-08-19 10:17:17 +07:00
1 parent c05f3d98d0
commit 010f6e1493
@@ -47,12 +47,16 @@ src/chicken_counter/
 ## Install

 ```bash
-python -m pip install -e .
+python3 -m venv venv
+venv/bin/pip install --upgrade pip
+venv/bin/pip install -r requirements.txt
 ```

 For Jetson deployment you will usually want a Jetson-compatible OpenCV and PyTorch
 stack already installed, then install the rest of the package around that environment.

+> **Tip:** See `RUN.md` for a full step-by-step quickstart guide for new developers.
+
 ## Run

 Update `configs/cameras/example_camera.yaml` with:
@@ -199,7 +203,9 @@ detection:
  imgsz: 640            # keep 640 while using existing TensorRT .engine
 ```

-`configs/cycle7_batch.yaml` already uses these production defaults.
+`configs/cycle7_batch.yaml` and `configs/cycle7_batch_optimized.yaml` already use these production defaults.
+
+`configs/cycle7_batch_optimized.yaml` adds per-camera parallelism, trimmed inference settings, and optimized YAML structure for the Sukawarna enclosure.

 **Validation:** run a short clip with stride enabled, then compare `total_entered` against
 `inference_stride: 1` and `motion.stride_frames: 1`. Watch checkpoint `fps=` logs for
@@ -217,6 +223,39 @@ for tuning.
 - The optical-flow trigger is vision-first, though the config structure leaves room for
  a future controller/encoder integration path

+## Multi-Stage Growth Cycles & Day 0 Configuration
+
+The pipeline dynamically adjusts detection and ROI entry thresholds based on flock age (Days Old Chick / DOC vs Mid-Cycle):
+
+- **Day 0 (`cycle_start_date`)**: Configured in `configs/cycle7_batch_optimized.yaml` (default: `"2026-05-22"`). Can be overridden via CLI (`--cycle-start-date YYYY-MM-DD`) or REST API (`/api/config/cycle_start_date`).
+- **`early_cycle` (Days 0–15)**: Automatically applies high-sensitivity detection thresholds (`conf: 0.12`, `min_box_area_px: 200`, `min_overlap_ratio: 0.25`) for small fast-moving DOC chicks.
+- **`mid_cycle` (Days 16+)**: Preserves standard tuned per-camera defaults (`conf: 0.35–0.50`, `min_box_area_px: 2500–3000`).
+
+## Mortality Detection
+
+A separate pipeline detects carcasses (dead birds) from still photos. Supports multi-image daily runs and date subfolders (`mortality/YYYY-MM-DD/`).
+
+```bash
+# Run on default mortality directory
+./test_run_mortality.sh
+
+# Run on a specific date (auto-creates/routes to mortality/2026-05-23/)
+chicken-counter mortality --date 2026-05-23
+```
+
+Key features:
+- **Multi-Image & Multi-Day Support**: Processes multiple images per day (e.g. morning/afternoon scans), aggregates the grand total carcass count (`total_mortality_count`), and saves outputs into date-isolated directories.
+- **2-Pass Detect & Refine**: runs the YOLO segmentation model once to find candidate regions, then uses `cv2.matchTemplate` to do a similarity search over each candidate before confirming it as a detection. This reduces false positives significantly.
+- **Containment filtering**: boxes where `IoA > 0.50` against a larger box are suppressed.
+- **Centroid deduplication**: detections whose centroids are within `dedupe_radius_px` of each other are merged to prevent counting the same carcass twice.
+- Uses the **segmentation model** (`models/chicken-detection-model-v26n-seg-300e-best-2026-04-18.pt`) which provides higher boundary precision than the standard detection model.
+
+Outputs for each daily run:
+- `output_<name>.jpg` — annotated images with bounding boxes and carcass IDs
+- `mortality_report.json` — full summary report with `total_mortality_count`, per-image breakdown, and detection coordinates
+
+Config: `configs/mortality_config.yaml`
+
 ## Headless Jetson MP4 Example

 For a headless run that saves both output video and periodic checkpoint images, use a
@@ -255,7 +294,7 @@ motion:
  flow_scale: 0.5
 display:
  show_window: false
-  output_path: /media/jetson/DATA/try-sukawarna-vis.mp4
+  output_path: /home/asus/.Codes/try-sukawarna-vis.mp4
  encoder: auto
  output_bitrate_kbps: 4000
 performance:
@@ -294,14 +333,15 @@ For everyday processing of 4 cameras, use `configs/cycle7_batch.yaml`.

 ### Input folder layout

-Place today's videos under:
+Place today's videos in a `VIDEOS` folder **adjacent to the project directory** (i.e. `../VIDEOS` relative to the project root):

 ```text
-/media/jetson/DATA/chicken-sukawarna/cycle7/2026-07-09/
-  kandang_1_camera_1_2026-07-09_120056.mp4
-  kandang_1_camera_2_2026-07-09_120456.mp4
-  kandang_1_camera_3_2026-07-09_121012.mp4
-  kandang_1_camera_4_2026-07-09_121530.mp4
+../VIDEOS/cycle7/kandang-atas/
+  2026-06-18/
+    kandang_1_camera_1_2026-06-18_120056.mp4
+    kandang_1_camera_2_2026-06-18_120456.mp4
+    kandang_1_camera_3_2026-06-18_121012.mp4
+    kandang_1_camera_4_2026-06-18_121530.mp4
 ```

 Date folders use `YYYY-MM-DD`. Camera files are matched by `camera_num` using the
@@ -310,13 +350,32 @@ pattern `kandang_*_camera_{num}_*.mp4`.
 ### Run commands

 ```bash
-# Process today's folder
-chicken-counter batch --config configs/cycle7_batch.yaml
+# Process today's folder using default parallel process mode
+chicken-counter batch --config configs/cycle7_batch_optimized.yaml

-# Process a specific date
-chicken-counter batch --config configs/cycle7_batch.yaml --date 2026-07-09
+# Process a specific date using Model-Level Tensor Batching mode
+chicken-counter batch --config configs/cycle7_batch_optimized.yaml --date 2026-06-18 --mode tensor_batching
+
+# Process a specific date using Hybrid mode (Threaded CPU + Batched GPU)
+chicken-counter batch --config configs/cycle7_batch_optimized.yaml --date 2026-06-18 --mode hybrid
+
+# Run automated batch script for Tensor Batching
+./test_run_tensor_batch.sh           # Runs all dates (2026-06-10 to 2026-06-19)
+./test_run_tensor_batch.sh 2026-06-18 # Runs a specific date
+
+# Run automated batch script for Hybrid execution mode
+./test_run_hybrid.sh                 # Runs all dates (2026-06-10 to 2026-06-19)
+./test_run_hybrid.sh 2026-06-18      # Runs a specific date
 ```

+### Execution Modes (`execution_mode`)
+
+Set `batch.execution_mode` in `configs/cycle7_batch_optimized.yaml` or override via `--mode`:
+
+- `parallel_processes` (Default): Runs cameras in separate OS processes (e.g. via `test_run.sh`).
+- `tensor_batching`: Synchronizes camera frame streams and executes a single batched GPU model inference pass across all cameras (`batch_size=N`).
+- `hybrid`: Combines multi-threaded CPU frame capture, optical flow, and rendering across CPU cores with a single synchronized batched GPU forward pass (`batch_size=N`).
+
 Single-camera mode still works:

 ```bash
@@ -327,7 +386,7 @@ chicken-counter run --config configs/cameras/example_camera.yaml
 ### Output layout

 ```text
-/media/jetson/DATA/chicken-sukawarna/cycle7/2026-07-09/output/
+../VIDEOS/cycle7/kandang-atas/2026-06-18/output/
  CC1_vis.mp4
  CC1_compressed.mp4
  CC2_vis.mp4
@@ -335,7 +394,7 @@ chicken-counter run --config configs/cameras/example_camera.yaml
  ...
  checkpoints/CC1/frame_003000.jpg
  checkpoints/CC2/frame_006000.jpg
-  counts_2026-07-09.json
+  counts_2026-06-18.json
 ```

 After all 4 cameras finish counting, the batch runner compresses each annotated video
@@ -384,11 +443,37 @@ For a ~72k frame run that is about 24 images per camera.
 ### Cron example

 ```cron
-0 7 * * * cd /media/jetson/DATA/chicken-sukawarna && /usr/bin/chicken-counter batch --config configs/cycle7_batch.yaml >> logs/cycle7-batch.log 2>&1
+0 7 * * * cd /path/to/chicken-counting-sukawarna-det && ./test_run.sh >> logs/cycle7-batch.log 2>&1
 ```

 Requires `ffmpeg` on the Jetson PATH for post-run compression.

+## Dashboard & API
+
+Start the live dashboard and API server:
+
+```bash
+# Portable launcher (recommended) — auto-discovers mortality dir
+./start_dashboard.sh
+
+# Or start manually
+PYTHONPATH=src venv/bin/python dashboard.py \
+  --port 8080 \
+  --db db/chicken_counts.db \
+  --mortality-dir ../VIDEOS/cycle7/kandang-atas/mortality
+```
+
+Key API endpoints (see `API.md` for full schema):
+
+| Endpoint | Description |
+| :--- | :--- |
+| `GET /api/db/summary` | Lifetime totals across all dates |
+| `GET /api/db/history` | Per-date summary, newest first |
+| `GET /api/db/date/<YYYY-MM-DD>` | Per-camera breakdown for a date |
+| `GET /api/mortality/latest` | Latest carcass detection report |
+| `GET /api/mortality/history` | All mortality reports, newest first |
+| `GET /api/mortality/image/<name>` | Serve annotated output JPEG |
+
 ## Next Jetson-Focused Improvements

 1. Add a hardware-aware video ingest path for CSI/GStreamer.
@@ -397,4 +482,5 @@ Requires `ffmpeg` on the Jetson PATH for post-run compression.

 Recent work includes daily 4-camera batch processing, JSON count reports, post-run
 compression under 200 MB, GStreamer hardware encoding, overlay buffer reuse,
-duplicate optical-flow removal (`gmc_method: none`), and long-run ETA logging.
+duplicate optical-flow removal (`gmc_method: none`), long-run ETA logging, mortality
+2-pass detection with feature similarity search, and a REST API via `dashboard.py`.