Scene analysis-based vehicle detection method and system

Abstract

The invention provides a scene analysis-based vehicle detection method and system, and the system comprises: a moving target detection module which is used for obtaining a scene video image, carryingout the background modeling in a self-adaptive mode, obtaining a background image and a foreground image, and segmenting a moving target; a moving shadow removing module which is used for judging whether gradient features of the background image need to be reserved or not and removing a moving shadow in the moving target based on a judgment result; and a vehicle detection and segmentation module which is used for judging whether the vehicle is adhered or shielded, performing vehicle segmentation if so and obtaining correct detection and segmentation of the vehicle, and directly obtaining correct detection and segmentation of the vehicle if not. According to the scheme, the vehicle identification and monitoring accuracy in a complex traffic scene is obviously improved, the background modeling stability is high, the resource consumption is low, and the identification speed is high.

Description

technical field [0001] The present invention relates to the field of intelligent transportation and the field of combination of Internet of Things communication and intelligent transportation, in particular to a method and detection system for intelligent detection of vehicles based on scene analysis. Background technique [0002] As an important part of intelligent transportation, vehicle detection has important research value and broad application prospects. Video-based vehicle detection technology belongs to the interdisciplinary field of computer vision, pattern recognition, signal analysis and other disciplines. The real-time detection and tracking technology of vehicles is one of the important technologies of the intelligent transportation system. Carrying out vehicle detection and tracking in complex scenes such as highways or crossroads, statistics can be obtained such as traffic flow, vehicle speed, distribution of traffic flow during peak hours, and lane occupancy....

AI Technical Summary

Problems solved by technology

However, because the position of the camera at the traffic intersection is relatively fixed, the background of the collected video image sequence changes slowly, which requires high real-time processing of the monitoring system, resulting in adhesion and occlusion of moving vehicles at the traffic intersection, and it is impossible to monitor the vehicles at the traffic intersection. Effective detection and analysis

Images