Track generation method and device, electronic equipment and storage medium

Abstract

The invention relates to a track generation method and device, electronic equipment and a storage medium. The method comprises the steps of acquiring multiple frames of images and historical reference frame images corresponding to each frame of image; performing foreground recognition on each frame of image based on the historical reference frame image to generate a foreground binary image; generating a background reference image according to the historical reference frame image; inputting each frame of image, the corresponding foreground binary image and the background reference image into a target detection network for target detection to obtain a target image in each frame of image and position information of the target image; inputting the target image in each frame of image and the position information of the target image into a target re-identification network for target re-identification to obtain target identification information of the target image in each frame of image; and generating track information of the target based on the target identification information and the position information of the target image. According to the embodiment of the invention, the method can improve the target detection precision, achieve the effective target re-recognition, and generate the accurate track information of the target.

Description

technical field [0001] The present disclosure relates to the technical field of computer vision, and in particular to a trajectory generation method, device, electronic equipment and storage medium. Background technique [0002] With the wide application of image processing in civil and commercial fields, object tracking plays an increasingly important role in the fields of intelligent video surveillance, automatic driving and unmanned supermarkets. Therefore, object tracking is also facing higher requirements. [0003] Usually, in the process of target tracking, it is necessary to detect the target first, and then, by re-identifying the detected target, it can generate trajectory information reflecting the movement process of the target within a period of time, and then realize the tracking of the target. However, in some application scenarios, due to the high-speed movement of some targets, such as high-altitude parabolas, etc., it often causes problems such as the extreme...

AI Technical Summary

Problems solved by technology

However, in some application scenarios, due to the high-speed movement of some targets, such as high-altitude parabolas, etc., it often causes problems such as the extremely low pixel ratio of the target in the image, blurring, etc., resulting in the inability of the existing deep learning algorithm-based target detection network. The detected target cannot be effectively re-identified, nor can it generate accurate trajectory information during the target movement process.

Images