Multi-target tracking system combining deep learning SSD algorithm with KCF algorithm

Abstract

The invention discloses a multi-target tracking system combining a deep learning SSD algorithm with a KCF algorithm, and the system comprises the following steps: setp 1, obtaining an image, and transmitting the image into an SSD deep learning model for target recognition; step 2, the SSD algorithm carries out target identification through GPU acceleration, judges an identification result, filtersimproper targets, and then records position information of each target; step 3, judging whether the acquired image is a first frame of image in the to-be-tracked image sequence or not; if yes, executing the step 4, and if not, executing the step 5; step 4, establishing an object for each target according to the new target position information obtained by the SSD algorithm; an object and a position of target tracking are determined through SSD detection, a KCF algorithm is used for tracking, a target moving track is recorded, and in the tracking process, the SSD algorithm performs optimizationcorrection at the same time to prevent tracking offset, tracking failure, tracking target errors and increase the tracking speed until a target disappears, and the obtained target track is used for service layer analysis.

Description

technical field [0001] The invention belongs to the field of video target tracking, relates to computer technology, and specifically relates to a multi-target tracking system with deep learning SSD algorithm combined with KCF algorithm. Background technique [0002] High-performance object tracking methods are the core technology in the field of computer vision. In the classic target tracking methods, the current tracking algorithms can also be divided into two categories: generative model and discriminative model. The production method uses the generative model to describe the performance characteristics of the target, and then minimizes the reconstruction error by searching for candidate targets (that is, to find the best matching window); the production method focuses on the description of the target itself, ignores the background information, It is easy to drift when the change is drastic or when it is blocked. Discriminative methods train classifiers to distinguish ob...

AI Technical Summary

Problems solved by technology

[0004] After years of development, the tracking algorithm has a good tracking effect, but there is a certain probability that the tracking will deviate or cause mistracking problems due to changes in factors such as illumination, occlusion, and scale, and the problem of target tracking cannot be repaired.

Images