Template matching tracking method and system based on depth feature fusion

A technology of template matching and depth features, applied in the field of target tracking, can solve problems such as insufficient robustness, lack of real-time performance, and easy drift, etc., and achieve the effect of improving robustness and suppressing jitter and drift

CN112287906AActive Publication Date: 2021-01-29CHINA AUTOMOTIVE INNOVATION CORP
5 Cites 1 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2021-01-29

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

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.
Need to check novelty before this filing date? Find Prior Art

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 ...

Examples

Embodiment Construction

[0042] The present invention realizes the purpose of target tracking through a template matching tracking method based on deep feature fusion and a system for realizing the method. Below through embodiment, in conjunction with accompanying drawing, this scheme is described further in detail.

[0043] In this application, we propose a template matching tracking method based on deep feature fusion and a system for implementing the method, which includes a template matching tracking method based on deep feature fusion, as shown in the attached figure 1 Shown, be that the inventive method realizes flowchart, specifically divide into the following steps:

[0044] Step 1: Obtain video data, and input the first frame image of the video into the deep convolutional network; this step further preprocesses the acquired video data, specifically processing the size of the image to be input into the deep convolutional network into a deep convolutional network The acceptable size of the pro...