Multi-area Target Individual Detection with Free Drawing on Video

TL;DR

This paper introduces a real-time multi-area detection system on video that allows free drawing of detection zones, with a model-independent design, real-time visualization, and flexible configuration for various monitoring applications.

Contribution

It presents a novel, flexible, and real-time multi-area detection method using free drawing on video, independent of the object recognition model used.

Findings

Real-time detection of multiple user-defined areas on video.

Model-independent design allowing easy integration with different recognition models.

Efficient implementation using PIL, OpenCV, and Tkinter.

Abstract

This paper has provided a novel design idea and some implementation methods to make a real time detection of multi-areas with multiple detecting areas that are generated by the real time drawing on the screen display of the video. The drawing on the video will remain the output as polylines, and the colors of the outlines will change when the stage of drawing or detecting is changed. The shape of the drawn area is free to be customized and real-time effective. The configuration of the drawn areas can be renewed and the detecting areas are working individually. The detection result should be shown with a GUI designed by Tkinter. The object recognition model was developed on YOLOv5 but can be changed to others, which means the core design and implementation idea of this paper is model-independent. With PIL and OpenCV and Tkinter, the drawing effect is real time and efficient. The design and code of this research is basic and can be extended to be implemented in numerous monitoring and detecting situations.