Related Experiment Video
Updated: Feb 15, 2026

Asthma Detection Research Based on Voice Signal Processing and Machine Learning
Published on: July 22, 2025
Vehicle Detection with Occlusion Handling, Tracking, and OC-SVM Classification: A High Performance Vision-Based
Roxana Velazquez-Pupo1, Alberto Sierra-Romero2, Deni Torres-Roman3
1Center for Advanced Research and Education of the National Polytechnic Institute of Mexico, CINVESTAV Guadalajara, Zapopan C.P. 45019, Mexico. rvelazquez@gdl.cinvestav.mx.
This study introduces an advanced vision system for real-time traffic surveillance. It accurately detects, tracks, and classifies vehicles, even with occlusions, using Gaussian Mixture Models and Kalman filters.
Area of Science:
- Computer Vision
- Artificial Intelligence
- Traffic Engineering
Background:
- Traffic surveillance systems require robust methods for vehicle detection and classification.
- Occlusion presents a significant challenge in accurately analyzing traffic flow.
Purpose of the Study:
- To develop a high-performance, vision-based traffic surveillance system.
- To enable real-time vehicle detection, tracking, counting, and classification with occlusion handling.
Main Methods:
- Utilized adaptive Gaussian Mixture Model (GMM) for background segmentation.
- Implemented an occlusion reduction algorithm and adaptive Kalman filter for tracking.
- Extracted geometric features (area, height, width) for classification using One Class Support Vector Machine (OC-SVM).
Main Results:
- Achieved real-time performance with an occlusion index of 0.312.
- Obtained a global detection rate (recall) and precision up to 98.190%.
- Reached a high F-measure of 99.051% for midsize vehicle classification.
Conclusions:
- The proposed vision system effectively handles occlusions in traffic surveillance.
- The system demonstrates high accuracy in real-time vehicle detection, tracking, and classification.
- Geometric features combined with OC-SVM provide a reliable method for categorizing vehicle sizes.
Related Concept Videos
Vision
Color Vision
Sample Handling
Samples should be transported carefully from collection points to the laboratory. They should be properly sealed and clearly labeled to prevent cross-contamination. To preserve the sample integrity, optimal temperature conditions during transport are essential. This could involve using...
Classification of Titrimetric Analysis Based on Reaction Types
Titrations between an acid and a base lead to neutralization reactions that form...
Cardiovascular Drugs: Classification based on Therapeutic Indications
Depth Perception and Spatial Vision

