Update bytetracker example

runtime/hailo-8/python/detection_with_tracker/README.md

@@ -10,54 +10,63 @@ Requirements
 ------------
 
 - hailo_platform==4.18.0
-- ByteTracker
+- Roboflow supervision
 - OpenCV (cv2)
 - tqdm
-- supervision
+
+Note: Roboflow supervision ships ByteTracker already. Thus, you needn't install bytetracker
 
 Supported Models
 ----------------
 
-This example expects the hef to contain HailoRT-Postprocess. Because of that, this example only supports detections models that allow hailort-postprocess:
+This example expects the HEF model to contain HailoRT-Postprocess. Because of that, this example only supports detections models that allow hailort-postprocess:
 - yolov5/6/7/8
 - yolox
 - ssd
 - centernet
 
-
 Usage
 -----
 
-0. Install PyHailoRT
+0. Create a virtualenv
+    ```shell script
+    python -m venv .venv
+    source .venv/bin/activate
+    ```
+
+1. Install PyHailoRT
     - Download the HailoRT whl from the Hailo website - make sure to select the correct Python version. 
     - Install whl:
         ```shell script
         pip install hailort-X.X.X-cpXX-cpXX-linux_x86_64.whl
         ```
 
-1. Clone the repository:
+2. Clone the repository:
     ```shell script
-    git clone <https://github.com/hailo-ai/Hailo-Application-Code-Examples.git>
+    git clone https://github.com/hailo-ai/Hailo-Application-Code-Examples.git
 
-    cd Hailo-Application-Code-Examples/runtime/python/detection_with_tracker
+    cd Hailo-Application-Code-Examples/runtime/hailo-8/python/detection_with_tracker/
     ```
 
-2. Install dependencies:
+3. Install dependencies:
     ```shell script
     pip install -r requirements.txt
     ```
 
-
-3. Download example files:
+4. Download example files:
     ```shell script
     ./download_resources.sh
     ```
 
-4. Run the script:
+5. Run the script:
     ```shell script
     ./object_detection_tracking.py -n <net> -i <input_video> -o <output_video> -l <labels> -s <score_thresh>
     ```
 
+As a result, the program will perform the detection/tracking of objects in the video file, generating the output video in the same directory:
+
+![image](https://github.com/user-attachments/assets/1b7fe0ab-eb73-4f47-b493-ec17832931a9)
+
 Arguments
 ---------
 
@@ -75,14 +84,14 @@ Example
 -------
 **Command**
 ```shell script
-./detection_with_tracker.py -i input_video.mp4 -o output_video.mp4 -l coco.txt -s 0.5
+./detection_with_tracker.py -n yolov5m_wo_spp_60p.hef -i input_video.mp4 -o output_video.mp4 -l coco.txt -s 0.5
 ```
 
 Additional Notes
 ----------------
 
-- The example was only tested with ``HailoRT v4.18.0``
-- The example expects a HEF which contains the HailoRT Postprocess
+- The example was only tested with `HailoRT v4.18.0` and `HailoRT v4.21.0`
+- The example expects a HEF model file which contains the HailoRT Postprocess
 - The script assumes that the input video is in a standard format supported by OpenCV (e.g., .mp4, .avi).
 
 Disclaimer

runtime/hailo-8/python/detection_with_tracker/requirements.txt

@@ -1,6 +1,6 @@
-bytetracker
+cython
 supervision==0.25.1
 loguru
 tqdm
 requests
-opencv-python
+opencv-python