Skip to content

Latest commit

 

History

History
61 lines (48 loc) · 1.79 KB

File metadata and controls

61 lines (48 loc) · 1.79 KB

Object Detection and Count in polygon zone

This repository contains multiple Python files for object detection and object counting in different regions of a frame, utilizing various versions of YOLO (You Only Look Once) algorithms.

Installation

git clone https://github.com/sankalpvarshney/Detect-and-count-objects-in-polygon-zone.git
cd Detect-and-count-objects-in-polygon-zone
conda create --prefix ./env python=3.8 -y
conda activate ./env
pip install -r requirements.txt

Usage

Linux

For single polygon region uisng YOLO v8

python yolov8SinglePolygon.py -i <input video path> -o <output video path>

For multiple polygon regions uisng YOLO v5

python yolov5MultiplePolygon.py -i <input video path> -o <output video path>

For multiple polygon regions uisng YOLO v8 (Recommended for multiple region)

python yolov8MultiplePolygon.py -i <input video path> -o <output video path>

Python

For single polygon region uisng YOLO v8

from yolov8SinglePolygon import CountObject
obj = CountObject(<input_file_path>,<output_file_path>)
obj.process_video()

For multiple polygon regions uisng YOLO v5

from yolov5MultiplePolygon import CountObject
obj = CountObject(<input_file_path>,<output_file_path>)
obj.process_video()

For multiple polygon regions uisng YOLO v8 (Recommended for multiple region)

from yolov8MultiplePolygon import CountObject
obj = CountObject(<input_file_path>,<output_file_path>)
obj.process_video()
compressed-mall2-modified.mp4

Contributing

Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.

Please make sure to update tests as appropriate.