Sync crowd-detection from metro-analytics-catalog

README.md

@@ -1,6 +1,6 @@
 # Crowd Detection
 
-> **Validated with:** OpenVINO 2026.0.0, NNCF 3.0.0, DLStreamer 2026.0, Ultralytics 8.3.0, Python 3.11+
+> **Validated with:** OpenVINO 2026.1.0, NNCF 3.0.0, DLStreamer 2026.0, Ultralytics 8.4.46, Python 3.11+
 
 | Property | Value |
 |---|---|
@@ -32,7 +32,7 @@ Smaller variants (`yolo26n`, `yolo26s`) are recommended for high-FPS edge deploy
 ## Prerequisites
 
 - Python 3.11+
-- [Install OpenVINO 2026.0.0](https://docs.openvino.ai/2026/get-started/install-openvino.html)
+- [Install OpenVINO](https://docs.openvino.ai/2026/get-started/install-openvino.html) (latest version)
 - [Install Intel DLStreamer](https://docs.openedgeplatform.intel.com/2026.0/edge-ai-libraries/dlstreamer/get_started/install/install_guide_ubuntu.html)
 
 Create and activate a Python virtual environment before running the scripts:
@@ -52,9 +52,17 @@ Run the provided script to download, export to OpenVINO IR, and optionally quant
 
 ```bash
 chmod +x export_and_quantize.sh
-./export_and_quantize.sh yolo26n        # default: FP16
+./export_and_quantize.sh
+```
+
+This exports the default **yolo26n** model in **FP16** precision.
+
+#### Optional: Select a Different Variant or Precision
+
+```bash
 ./export_and_quantize.sh yolo26n FP32   # full-precision
 ./export_and_quantize.sh yolo26n INT8   # quantized
+./export_and_quantize.sh yolo26s        # larger variant, default FP16
 ```
 
 Replace `yolo26n` with any variant (`yolo26s`, `yolo26m`, `yolo26l`, `yolo26x`).
@@ -80,9 +88,9 @@ Output files:
 | FP16 | Yes | Yes | Yes |
 | INT8 | Yes | Yes | Yes |
 
-> **Note:** For production accuracy, replace the random calibration tensors in
-> `export_and_quantize.sh` with a representative sample of frames from the
-> target deployment site.
+> **Note:** The INT8 calibration uses the bundled sample image.
+> For production accuracy, replace it with a representative set of frames from
+> the target deployment site.
 
 ### OpenVINO Sample
 
@@ -140,13 +148,17 @@ The `export_and_quantize.sh` script downloads `test.jpg` automatically.
 Re-run the OpenVINO sample above.
 The script reads `test.jpg`, prints the crowd count to the console, and writes the annotated frame to `output.jpg`.
 
-Expected console output:
+Expected console output (representative -- actual count depends on the sample image):
 
 ```text
-Detected persons: 4
+Detected persons: <N>
 ```
 
-`output.jpg` is the same image with a green bounding box drawn around each detected person and the text `Crowd count: 4` overlaid in the top-left corner.
+`output.jpg` is the same image with a green bounding box drawn around each detected person and the text `Crowd count: <N>` overlaid in the top-left corner.
+
+> **Tip:** The bundled `test.jpg` (an airport scene) is suitable for a quick
+> demo. For production testing, replace it with an image from your target
+> deployment site showing a representative crowd density.
 
 ### DLStreamer Sample
 

export_and_quantize.sh

@@ -38,7 +38,7 @@ fi
 
 echo "--- Downloading sample test image ---"
 if [[ ! -f test.jpg ]]; then
-    wget -q -O test.jpg https://ultralytics.com/images/bus.jpg
+    wget -q -O test.jpg https://raw.githubusercontent.com/ultralytics/assets/main/im/airport.jpg
     echo "Downloaded: test.jpg"
 else
     echo "Already present: test.jpg"
@@ -67,12 +67,19 @@ if [[ "${PRECISION}" == "INT8" ]]; then
 import nncf
 import openvino as ov
 import numpy as np
+import cv2
 
 core = ov.Core()
 model = core.read_model('${MODEL_NAME}_openvino_model/${MODEL_NAME}.xml')
 
+# Use the downloaded test image for calibration instead of random noise.
+img = cv2.imread('test.jpg')
+img = cv2.resize(img, (640, 640))
+img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB).astype(np.float32) / 255.0
+img = img.transpose(2, 0, 1)[np.newaxis, ...]  # NCHW
+
 def transform_fn(data_item):
-    return np.random.rand(1, 3, 640, 640).astype(np.float32)
+    return img
 
 calibration_dataset = nncf.Dataset(list(range(300)), transform_fn)