Social Distancing Detector

To check whether if people are following social distancing precautions within a crowd using computer vision technologies

Functioning 💎

• Object detection using the YOLO COCO model to detect only people in the video stream.
• Computes the distances between all detected people in the bounding boxes.
• Based on the computed distances, we determine whether social distancing rule or precaution is being violated or not.

Technologies and Libraries Used

Python

Open CV

Yolo Coco Model

SciPy

dnn Module

Numpy

Argparse

Installation of the Project:package:

1. Clone the repo

   $ git clone https://github.com/Noel6161131110/Social-Distancing-Detector.git
   $ cd Social-Distancing-Detector

2. Install dependencies

   $ pip install -r requirements.txt

3. Run the main social distancing detector file. (set display to 1 if you want to see output video as processing occurs)

   $ python social_distancing_detector.py --input pedestrians.mp4 --output output.avi --display 1

[Caution: The output video stream will not be accurate if you display as processing occurs]

Demo Video 🎥