Pedestrian position detection and tracking method and system

Abstract

The invention provides a pedestrian position detection and tracking method and system. The pedestrian position detection and tracking method comprises the following steps: acquiring a video stream ina preset scene, sequentially inputting frame-by-frame images in the video stream into a face detection model, and outputting a face position and a face size target frame of a pedestrian in the video stream; estimating a pedestrian target frame according to the body characteristics of the pedestrian and the face size target frame, fusing the estimated pedestrian target frame with the result of thepedestrian target frame detected by the background subtraction method, and performing correction to obtain a corrected pedestrian target frame; obtaining a position corresponding to the corrected pedestrian target frame according to a mapping relationship between the pedestrian target object and a preset scene geographic position; and calculating the centroid of the corrected pedestrian target frame to serve as the centroid of the pedestrian target of the corresponding frame image, and tracking the centroid of the pedestrian target of each frame image in the preprocessed video stream to realize pedestrian tracking. The method has good detection and tracking effects, and the influence caused by multi-target overlapping is avoided.

Description

technical field [0001] The present disclosure belongs to the field of image processing, and in particular relates to a pedestrian position detection and tracking method and system. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0003] Intelligent surveillance video analysis technology is an emerging application direction and a frontier subject that has attracted much attention in the field of computer vision. With the rapid development of network technology and digital video technology, monitoring technology is developing towards intelligence and networking. The advantage of the intelligent surveillance system is that it uses computer vision algorithms to automatically obtain key information in surveillance videos, minimizing manpower and material resources. As an important foundation of intelligent monitoring technology, moving object detect...

AI Technical Summary

Problems solved by technology

The inventors found that these algorithms have achieved the effect of moving target detection and tracking to a certain extent, but using these traditional detection and tracking algorithms alone not only has a large amount of calculation, but is not robust enough, and cannot learn online, so that the target tracking cannot be achieved. Time-varying tracking effects

With the development of machine learning, the training and classification of samples are gradually introduced into the detection and tracking of moving targets, which increases the complexity of model training, makes detection time-consuming, and cannot meet the real-time requirements of subsequent target tracking.

In addition, the existing technologies do not give full play to the adaptive advantages of human body characteristics in moving target detection and tracking technology, and most of them cannot balance the two requirements of real-time and robustness at the same time.

Images