This project implements a vehicle speed estimation system using computer vision techniques. It leverages the YOLOv4 object detection model and the deepSORT tracking algorithm to detect and track vehicles in video footage, calculating their speeds based on positional changes over time.

VEHICLE SPEED ESTIMATION

Steps to run the system:

• Clone the repository:

git clone https://github.com/Anish713/Vehicle-Speed-Estimation.git

1. Install the required dependencies:

   • Open a terminal or command prompt.
   • Navigate to the project directory.
   • Run the command pip install -r requirements.txt if available to install the necessary packages, else, manually install required packages.

2. Navigate to directory code and Run the command python app.py in the terminal (install missing packages if any and retry).

3. Upload the video using web app.

4. Mark 4 points in video for homography transformation.

5. Provide real world distance between those points.

6. Click Submit and Done.

MORE ON YOLO:

Papers and Links:

• YOLO: Real-Time Object Detection
• YOLOv3: An Incremental Improvement
• YOLOv4: Optimal Speed and Accuracy of Object Detection

Videos:

• https://youtu.be/vz6KgmwzjHA?si=uZIqgfPIyeV7OuY6
• https://youtube.com/playlist?list=PL1u-h-YIOL0sZJsku-vq7cUGbqDEeDK0a&si=F6MVo_HprPWNTxbt

MORE ON DEEPSORT:

Papers and Links:

• Simple Online and Realtime Tracking with a Deep Association Metric

Videos: