Multi-target tracking system based on deep learning and implementation method

Abstract

The invention relates to a multi-target tracking system based on deep learning and an implementation method. The method comprises the following steps: getting the target position of a first frame through target detection, and adding multiple to-be-tracked targets to a tracking queue; inputting a next frame of image and traversing the tracking queue to get the position of the target in the next frame; after getting the position of the target in the next frame, judging whether the target is off the screen based on thresholds; if the target is not off the screen, invoking target detection every other fixed frame, and calculating the IOU (intersection over union) of the target detection result and the tracking result; if IOU<0.1, judging that a new target is added to the screen, and adding the target to the tracking queue; if IOU>0.5, replacing the tracking box with the target detection box to correct the position; and continuing target tracking. By carefully designing the network structure and improving the training method, under the condition of high tracking precision, the tracking speed is increased significantly, network redundancy is reduced, and the size of the model is reduced.

Description

technical field [0001] The present invention relates to the field of image processing, in particular to a multi-target tracking system and implementation method based on deep learning, to achieve accurate and fast tracking of multiple targets. Background technique [0002] Moving object tracking is to find interesting moving objects (such as vehicles, pedestrians, animals, etc.) in each frame of monitoring images in a continuous video sequence. Tracking can be roughly divided into the following steps: [0003] 1) Effective description of the target; the tracking process of the target is the same as the target detection, and it needs to be described effectively, that is, the features of the target need to be extracted so as to be able to express the target; generally speaking, we can use the edge and contour of the image , shape, texture, area, histogram, moment feature, transformation coefficient, etc. to describe the characteristics of the target; [0004] 2) Calculation ...

AI Technical Summary

Problems solved by technology

[0011] Today's target tracking algorithm network has many problems such as redundancy, slow speed, large model, difficult to be practical, and impossible to track in real time.

Images