Template matching tracking method and system based on depth feature fusion

Abstract

The invention provides a template matching tracking method and system based on depth feature fusion, and the method comprises the following steps: 1, obtaining video data, and inputting a first frameimage of a video into a depth convolution network; step 2, enabling the deep convolutional network to receive the image frame information, and perform feature extraction and output; 3, obtaining a target position estimated according to the feature information; 4, judging the type of the target, and correcting the target box according to the type information; step 5, extracting the next frame of video data and inputting the data into the deep convolutional network for feature extraction; 6, according to the feature map extracted in the fifth step, performing template matching through the targetfeatures of the last frame; 7, outputting a target position in the current frame; and 8, judging whether video reading is finished or not, finishing target tracking when a finishing condition is met,and skipping to the step 5 when the finishing condition is not met. According to the invention, the target tracking is realized by detecting the target and judging the position of the target in the video.

Description

technical field [0001] The invention relates to a template matching tracking method and system based on deep feature fusion, in particular to the technical field of target tracking. Background technique [0002] With the development of computer technology, detection methods based on deep learning gradually occupy a dominant position in the fields of target detection, classification, and segmentation. Due to factors such as occlusion, illumination, and target non-rigidity in actual scenes, the accuracy and robustness of target tracking still have problems. [0003] In the prior art, when using the depth feature stream to process images, the feature of filtering the still object to establish the feature of the moving object is adopted to propagate the feature of the key frame moving object to the current frame. This technology is prone to drift in the processing process, resulting in insufficient robustness. At the same time, obtaining the depth frame and feature information ...

AI Technical Summary

Problems solved by technology

Due to factors such as occlusion, lighting, and target non-rigidity in actual scenes, there are still problems with the accuracy and robustness of target tracking.

[0003] In the existing technology, when using the depth feature stream to process images, the feature of filtering the static object to establish the feature of the moving object is adopted to propagate the feature of the key frame moving object to the current frame. This technology is prone to drift in the processing process, resulting in insufficient robustness.

At the same time, additional storage costs are required to obtain the depth frame and feature information database, and the feature information sets of all reference contours are calculated and matched one by one, resulting in real-time performance that cannot be satisfied in the actual application process.

Images