Video pedestrian detection method fusing multi-target tracking clues

Abstract

The invention discloses a video pedestrian detection method fusing multi-target tracking clues, and belongs to the field of image processing of computer vision.A pedestrian detection module (improvedFaster R-CNN) and a multi-target tracking module are included. According to the method, the feature pyramid is introduced into the feature extraction network, pedestrians are detected on more scales,features of different layers are fused to improve the prediction effect, and the detection rate and accuracy of small targets are improved. According to the invention, the multi-target tracking moduleis used for assisting pedestrian detection, the inter-frame information of the front and rear frames of the video is introduced, the detection stability can be improved, and the historical frame target track and the target number obtained through the tracking module are used for relieving the detection instability caused by deformation, shielding and targets located at the edge of the picture. According to the invention, the anchor point box is modified in the pedestrian detection network part, so that the pedestrian detection network part better conforms to the characteristics of pedestrians, thereby improving the pedestrian detection precision.

Description

technical field [0001] The invention belongs to the field of image processing of computer vision, and more specifically relates to a video pedestrian detection method that integrates multi-target tracking cues. Background technique [0002] Pedestrian detection is a research hotspot in computer vision tasks in recent years. The purpose of pedestrian detection is to determine whether pedestrians exist in an image or video sequence and to give precise positioning to the existing pedestrians. Pedestrian detection has a very wide range of applications in the field of computer applications, and can be applied to many fields including vehicle assisted driving systems, aerial images, intelligent transportation, and video surveillance. [0003] Pedestrian detection is a very difficult research problem, because the appearance of a person under the camera has visual ambiguity and spatio-temporal uncertainty. These difficulties are often due to low-resolution images or poor video qual...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problems of interference to pedestrian detectors caused by factors such as occlusion, out-of-focus, and small pedestrian targets in real video scenes in the prior art, the present invention provides a video pedestrian detection method that integrates multiple target tracking cues, and its purpose is to pass The method of fusing multi-target tracking information and introducing FPN network can detect more small pedestrian targets in video frames and occluded pedestrian targets in dense crowd scenes, etc., and improve the recall rate and robustness of detection

Images