Method and system for nighttime vehicle detection on basis of vehicle light identification

Abstract

The invention discloses a method and system for nighttime vehicle detection on the basis of vehicle light identification. The method includes: inhibiting a camera through strong light, obtaining traffic video data, and determining analyzed area-of-interest; performing filtering processing on images on the basis of mathematical morphology, and obtaining communication area information on the basis; then building vehicle light screening and matching rules, and screening and matching vehicle lights; performing position prediction on a target, setting vehicle confidence degree, updating stored vehicle position information, and achieving tracking of vehicles; and finally performing calculation and statistics on parameters of traffic flow, vehicle speed and the like of the vehicles left the area-of-interest. The method and system for the nighttime vehicle detection on the basis of the vehicle light identification adopts a large number of vehicle light image data statistic priori knowledge to identify vehicle light pairs and selects the vehicle light pair with highest matching degree from a connection area. The vehicle identification method enables the vehicle lights to be separated from nighttime scenes effectively and has good scene adaptability.

Description

technical field [0001] The invention relates to a method and device for detecting vehicles at night and tracking and counting traffic, in particular to a method and system for detecting vehicles at night based on vehicle light recognition, which belongs to intelligent transportation technology. Background technique [0002] With the rapid development of the national economy, the number of mobile vehicles in the country is increasing day by day, and the transportation system is also facing great pressure. In this context, intelligent transportation systems have developed rapidly in recent years, especially in expressway systems. Intelligent Transportation System (Intelligent Transport System, referred to as ITS) is an effective integration of information technology, data communication transmission technology, electronic sensing technology, electronic control technology and computer processing technology to the entire transportation management system, and established a It is ...

AI Technical Summary

Problems solved by technology

But the disadvantage is that the power consumption of infrared is also relatively large, and the halo captured by the infrared camera is very large

[0005] The method based on background extraction can eliminate the influence of the reflected light of the car lights on the road surface on the detection, but this method needs to be based on a more complex background model, such as a Gaussian mixture model, and the dynamic changes of the external environment will have a large impact on the background model. Influences, such as changes in lighting and weather, can make the detection rate drop significantly

In addition, if the traffic flow is large, the detection rate of the algorithm will also drop significantly

The method based on temporal differencing avoids the shortcomings of background modeling, and the algorithm complexity is low, but this method is sensitive to noise, the detection rate is low when there is noise, and it is difficult to calibrate the camera

[0006] In addition to the difference in detection equipment, night detection algorithms are also very different

Although the method based on feature recognition is less affected by noise, the detection rate is very low when the external lighting conditions are dark or dark

Detect traffic flow based on the color information in the taillights, but affected by the ambient light, the color of the taillights sometimes appears as a single white, so the detection rate will drop significantly

Images