Multi-target tracking method, device and apparatus and storage medium

一种多目标跟踪、目标的技术，应用在多目标跟踪方法,设备及存储介质,装置领域，能够解决计算速度慢、提取SIFT特征耗时、无法满足多目标跟踪实时处理的要求等问题，达到提升处理速度、满足实时处理的效果

Active Publication Date: 2019-01-15
APOLLO INTELLIGENT DRIVING (BEIJING) TECHNOLOGY CO LTD
View PDF7 Cites 29 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] Using the above method, although a good tracking effect will be obtained, the better the description of the features, the slower the calculation speed. For example, the SIFT feature has a strong description ability, but the process of extracting the SIFT feature will be very time-consuming, so it cannot meet multiple objectives. Requirements for real-time processing in tracking

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
  • Multi-target tracking method, device and apparatus and storage medium
  • Multi-target tracking method, device and apparatus and storage medium
  • Multi-target tracking method, device and apparatus and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] In order to make the technical solution of the present invention more clear and understandable, the solution of the present invention will be further described below with reference to the accompanying drawings and examples.

[0056] Apparently, the described embodiments are some, but not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts fall within the protection scope of the present invention.

[0057] figure 1 It is a flowchart of an embodiment of the multi-target tracking method of the present invention, such as figure 1 As shown, including the following specific implementation methods:

[0058]In 101, the current image to be processed is obtained, and the current image is input to the pre-trained convolutional neural network model to obtain the target detection result;

[0059] In 102, the feature vectors of the detected targets are resp...

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 multi-target tracking method, device and apparatus and a storage medium, wherein, the method comprises the following steps: obtaining a current image to be processed, inputting the current image to a convolution neural network model trained in advance, and obtaining a target detection result; extracting feature vectors of each detected object from a preselected convolution layer; calculating the similarity between the feature vectors of each object in the current image and the feature vectors of each object in the previous image respectively. The association of the same object in different image frames is completed according to the calculation results and the tracking number is assigned. The scheme of the invention can meet the requirements of real-time processingand the like.

Description

【Technical field】 [0001] The invention relates to computer application technology, in particular to a multi-target tracking method, device, equipment and storage medium. 【Background technique】 [0002] Visual multi-target tracking is one of the key technologies of visual obstacle detection. Its main function is to assign the same number to the same target in consecutive image frames to estimate the trajectory of each target. [0003] The tracking algorithm usually adopts the Tracking by Detection method, that is, the tracking process is strongly dependent on the detection results. The implementation process mainly includes: performing target detection, data association of inter-frame detection results, and assigning numbers to targets. [0004] Among them, data association is an important link in the tracking process, its performance will directly affect the quality of tracking, and the speed of data association will directly affect whether the tracking algorithm can become ...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/58G06N3/045G06F18/241G06T2207/10016G06T2207/20081G06T2207/20084G06T7/246G06V40/173G06V10/758G06T7/251G06N5/046G06T7/97G06F17/16G06T7/11G06F18/22
Inventor 高涵万吉夏添
Owner APOLLO INTELLIGENT DRIVING (BEIJING) TECHNOLOGY CO LTD
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