Detection method for remnants in complex environment

Abstract

The invention discloses a detection method for remnants in the complex environment. The detection method comprises the following steps: comparing prospect targets obtained on the basis of both a partial updated Gaussian mixture background modeling method and a modified three-frame difference method; in combination with the YCbCr color space based shadow elimination method and the connected domain analysis, dividing to obtain temporary static briquettes within a scene; carrying out the centroid distance judging method on each frame of an image, and counting the rest time of each briquette; marking the static briquettes reaching to the temporal threshold as the remnants after eliminating the possibility of pedestrian residence through the HOG (Histograms of Oriented Gradients) pedestrian detection algorithm, and eliminating the possibility of pedestrian residence through the FAST (Features from Accelerated Segment Test) feature point detection algorithm. The detection method can improve detection accuracy of the remnants, lowers calculation complexity, can be better suitable for the complex environment crowded and frequent in shielding, and enhances the anti-interference capability.

Description

technical field [0001] The invention relates to the field of video image processing, in particular to a detection method for leftovers in complex environments. Background technique [0002] In public places, a major hidden danger that threatens public safety is the placement of unidentified items left behind, such as explosives, toxic substances and other dangerous goods, especially for crowded public areas such as subway stations, airports, and shopping malls, which will cause serious consequences. Remnants refer to objects that are carried into the monitoring scene by moving subjects, separated from the moving subjects, and remain stationary in the scene for more than a certain time threshold (see literature [1]). The main task of relic detection is to intelligently analyze the video surveillance scene, accurately segment the target object from the complex environment with a large number of irrelevant people and objects, and make an alarm in time. [0003] For the realiza...

AI Technical Summary

Problems solved by technology

Literature [2] proposes a method based on dual backgrounds, which compares two mixed Gaussian background models with different update rates to obtain remnant objects, but the computational complexity of modeling two backgrounds at the same time is relatively large, and if the If the time is too long, it will still be integrated into the background, resulting in missed detection

Literature [3] adopts Bayesian inference method to detect leftover luggage, and uses the tracking trajectory information such as the speed, direction, and distance of objects as evidence, and analyzes and identifies events through the framework of Bayesian inference. The processing flow is relatively complicated. Real-time requirements are not easy to meet

Literature [4] uses a real-time updated background model to detect moving target areas, and then determines whether the target area is a remnant or a lost object area by matching the edge of the static foreground area. This method is suitable for complex scenes with dense crowds and frequent occlusions. Anti-interference ability is not strong

Images