Vehicle shadow eliminating method based on multi-feature fusion

Abstract

The invention provides a vehicle shadow eliminating method based on multi-feature fusion. The vehicle shadow eliminating method comprises the following steps that (1), image sequences are read to obtain a current frame; (2), background modeling is carried out, a frame difference method is used for extracting vehicle foregrounds for a background frame and the current frame, and binarization processing and morphological processing are carried out on the foregrounds; (3), shadow assessment is carried out on a moving target area; (4), shadow detection is carried out on a vehicle foreground area, and detection is carried out on the basis of color features and edge features to obtain a plurality of candidate shadow areas; (5), the candidate shadow areas are fused to obtain a final shadow area; (6), in the vehicle foreground area, the shadow areas are eliminated, and real target vehicles are left. According to the vehicle shadow detecting algorithm based on multi-feature fusion, a shadow detecting method based on a single feature has limitation, and can not be applied to all traffic scenes, and therefore the vehicle shadow eliminating method with the universality is achieved by fusing a plurality of features.

Description

technical field [0001] The invention relates to the detection and elimination of vehicle shadows. Background technique [0002] With the rapid development of urban traffic, traditional traffic monitoring and detection methods such as coil detection and infrared sensor detection can no longer meet the needs of complex traffic management for multiple information due to their single detection information. In recent years, the field of intelligent transportation has developed vigorously. [0003] In the intelligent traffic monitoring system, based on video analysis technology, computer vision and image processing methods are used to complete the acquisition of traffic information. Without manual intervention, the real-time video analysis is used to realize the modeling of the road background. Vehicle detection and analysis, traffic flow detection, vehicle tracking, etc. At present, the commonly used method of vehicle detection is the frame difference method to extract the targ...

AI Technical Summary

Problems solved by technology

However, the method based on a certain feature alone has its own shortcomings. For example, the method based on color features is not suitable for the detection of grayscale images, and it will cause false detection when the vehicle is similar to the shadow color; the method based on edge features does not consider The shaded area contains complex edges such as lane markings and road boundaries; the shadow-based texture invariance method has a relatively high false detection rate for vehicle areas with inconspicuous texture characteristics

Images