A vehicle detection and tracking method

A vehicle detection and vehicle tracking technology, applied in instruments, biological neural network models, character and pattern recognition, etc., can solve problems such as high price and inability to achieve practical applications

Inactive Publication Date: 2019-06-14
HANGZHOU DIANZI UNIV
View PDF7 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The existing unmanned vehicle system developed by Google is already world-leading, but the price is too expensive, but it is still in the research and development stage in China and cannot be used in practice.

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
  • A vehicle detection and tracking method
  • A vehicle detection and tracking method
  • A vehicle detection and tracking method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] The present invention will be further described below in conjunction with the accompanying drawings.

[0054] A vehicle detection and tracking method, which uses the improved SSD-MobileNets target detection algorithm combined with particle filter and CamShift algorithm to detect and track vehicles, providing safety guarantee for unmanned driving. Such as figure 1 As shown, first, the video is collected through the camera in front of the vehicle, and the vehicle is detected in real time through the SSD-MobileNets target detection module. If a vehicle is detected in a certain frame of video, the next frame of the video is used to track the current vehicle through the CamShift target tracking algorithm. Tracking, the frame of video after tracking is verified by particle filtering to prevent vehicles from no longer tracking or multiple vehicles being mistaken for one vehicle because the color is similar to the environment and other vehicles. Finally, by judging whether the ...

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 relates to a vehicle detection and tracking method. An existing system is too expensive and cannot achieve the practical application. According to the method, a detection module built byan SSD algorithm and MobileNts and a tracking module built by a particle filtering algorithm and a CamShift algorithm are adopted to carry out vehicle detection tracking, and an embedded mobile terminal is adopted in a development environment. According to the method, an SSD and MobileNts in a neural network are adopted, and the method is established with a traditional target tracking CamShift algorithm and particle filtering, and comprises a vehicle detection method and a vehicle tracking method. The method plays a key role in the aspect of unmanned driving, not only solves the difficultiesof most important vehicle detection and tracking directions in unmanned vehicle driving, but also can solve the problem of high hardware price, and has great practical significance and a wide application scene in the aspect of improving social and economic benefits.

Description

technical field [0001] The invention belongs to the field of artificial intelligence, specifically the technical field of unmanned driving, and relates to a vehicle detection and tracking method, in particular to a SSD (Single Detector) neural network improved through the framework of MobileNets (Mobile Vision Network) Combined with the embedded development method combining CamShift (continuous adaptive expected movement) algorithm and particle filter two target trackers, this technology realizes the real-time identification and tracking of vehicles through the embedded mobile terminal. Background technique [0002] In recent years, the rapid development of Internet technology has brought opportunities for revolutionary changes in the automotive industry. At the same time, automotive intelligent technology is gradually being widely used. This technology makes the operation of the car easier and the driving safety better. The most typical and popular future application is dri...

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): G06K9/00G06K9/46G06N3/04
Inventor 姜显扬王智徐磊许晓荣姚英彪
Owner HANGZHOU DIANZI UNIV
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