This project is developed in Python and makes use of five core technologies. OpenCV is used for video processing, drawing lane dividers, and displaying the live output. YOLOv8 (Ultralytics) is applied for real-time vehicle detection, while DeepSORT ensures accurate object tracking so that each vehicle is counted only once. Pandas is utilized to store and export the traffic data into CSV format for further analysis. Finally, NumPy is employed to handle mathematical operations and array manipulations required during the processing.
In this project, vehicles moving across predefined lanes in a video are detected and tracked in real time. As each vehicle crosses the counting line, the system updates the count per lane and saves the results into a CSV file for further analysis.
INPUT VIDEO: https://www.youtube.com/watch?v=MNn9qKG2UFI
OUTPUT DEMO VIDEO: https://drive.google.com/file/d/1GDBqxstDspVcHURfZssMrEgpiZCxSY7j/view?usp=drivesdk