Single-target tracking method and device and storage medium

A single-target, single-target technology, applied in image analysis, instrumentation, computing, etc., can solve problems such as inability to handle well, scale changes, color shifts, etc., to achieve the effect of ensuring speed, improving accuracy, and eliminating post-processing steps

Pending Publication Date: 2022-07-05
NANJING UNIV OF POSTS & TELECOMM
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] There is a shortcoming in the existing technology: but in the face of a complex environment (such as blur, scale change, color shift and fast motion, etc.), most existing trackers still cannot handle these scenes well

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Single-target tracking method and device and storage medium
  • Single-target tracking method and device and storage medium
  • Single-target tracking method and device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] A single-target tracking method, comprising:

[0037] get video data;

[0038] Determine the target area of ​​the first frame of the video data, perform feature extraction on the target area through the transformer backbone network, and encode the transformer encoder to obtain the feature encoding of the target area;

[0039] According to the target area of ​​the first frame of the video data, use a Gaussian function to generate M target a priori frames, where M is an integer greater than 3;

[0040] Determine the search area according to the target area of ​​the first frame of the video data;

[0041] Perform feature extraction on the transformer backbone network for the search area, and encode the transformer encoder to obtain the feature code of the search area;

[0042] Input the target area feature encoding, search area feature encoding and M target a priori boxes into the transformer decoder for decoding, and obtain the IoU value of the intersection ratio betwee...

Embodiment 2

[0077] In a second aspect, this embodiment provides a single-target tracking device, including a processor and a storage medium;

[0078] the storage medium is used for storing instructions;

[0079] The processor is configured to operate in accordance with the instructions to perform the steps of the method according to Embodiment 1.

Embodiment 3

[0081] In a third aspect, this embodiment provides a storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method described in Embodiment 1 are implemented.

[0082] As will be appreciated by those skilled in the art, the embodiments of the present application may be provided as a method, a system, or a computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a single-target tracking method and device and a storage medium. The method comprises the following steps: extracting features of a target area and a search area by adopting a transform backbone network; a transform-based coding and decoding architecture is adopted to fuse target area features and search area features to serve a subsequent prediction task, and M (100) target preselection boxes based on a previous frame target position are added while a target area feature code and a search area feature code are jointly sent into a transform decoder. And the IoU prediction module is used for carrying out N times of iterative optimization on a target prediction frame decoded and output by the Transform decoder structure to obtain optimized prediction frames, then calculating IoU between the optimized prediction frames and the annotation frames, and averaging the first three optimized prediction frames of the IoU as a final prediction result. And the speed is ensured while the precision is improved.

Description

technical field [0001] The invention belongs to the technical field of target tracking, relates to a single target tracking method, device and storage medium, and in particular relates to a single target tracking method, device and storage medium for IoU prediction based on a transformer. Background technique [0002] Single object tracking is a very challenging task in computer vision tasks. The purpose of the target tracking task is that given the target information of the first frame, the tracker needs to automatically determine the target state in subsequent frames. Unlike object detection tasks, object features are only available at the inference stage, which means that there is no prior information about the object, such as class and surrounding environment. In recent years, thanks to the rapid development of deep learning, many research results have been achieved in the field of object tracking. [0003] Existing techniques suffer from one shortcoming: However, in t...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/269G06V10/22
CPCG06T7/269G06T2207/10016G06T2207/20084G06T2207/20132
Inventor 范保杰郭小宾蒋国平徐丰羽
Owner NANJING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap