pankajrawat9075 / vehicle-counting-and-tracking-using-yolov8-and-bytetrack

Object-tracking-using-YOLO-DEEPSORT-computer-vision

Overview

You Only Look Once (YOLO) is a CNN architecture for performing real-time object detection. The algorithm applies a single neural network to the full image, and then divides the image into regions and predicts bounding boxes and probabilities for each region. For more detailed working of YOLO algorithm, please refer to the YOLO paper.

ByteTrack is a simple, fast and strong multi-object tracker(https://arxiv.org/abs/2110.06864).

This project aims to count every vehicle (motorcycle, bus, car, cycle, truck, train), going in and out of town, detected in the input video using YOLOv8 object-detection algorithm and ByteTrack MOT.

Dependencies

• OS: Windows/ Linux
• Python >= 3.10.5

pip install -r requirement.txt

Download any street video file to run the vehicle counting and upload in same folder as main.ipynb file

Running the model

Clone the repository and run the main.ipynb file. All instructions to run the code is in the main.ipynb file itself.

Check some results here

https://drive.google.com/drive/folders/1Je9B27jBGTi25Y8PqEKIUWcsLwMsWMGA?usp=sharing