Vehicle Detecting Method Based on Gaussian Mixture Models and Blob Analysis
Vehicle detection process provides relevant information about traffic patterns, crash occurrences and traffic peak times in roadways. This paper presents a vehicle detection method in a video sequence using foreground detector based on a Gaussian Mixture Model and Blob Analysis. The proposed method is composed of four major steps: foreground segmentation, blob detection, blob analysis and blob tracking. An implementation of proposed technique has been performed using MATLAB R2017a. The experimental results show that the proposed method can provide useful information for intelligent transportation systems.
The files contained in This dowload were used in the course CS631 Computer Vision Spring 2017 at Pace University.
What you need to run this file
This file were developed and tested on MATLAB R2017a. The products need to run all of the files are:
- Computer Vision System Toolbox
To run this file
Keep all files on the same folder and run the script 'projectSource.m'.
NOTE: This script will read and process the video'dataset.mp4' as a video input.
This project is licensed under the MIT License - see the LICENSE.md file for details