Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Vehicle Detection Method Based on Multiple Components

A vehicle detection and multi-component technology, which is applied in the field of vehicle detection, can solve problems such as inability to handle well, cover vehicle missed detection, etc., and achieve the effect of narrowing the template search range

Active Publication Date: 2018-07-17
HEFEI UNIV OF TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, for the possible side occlusion situation, this method cannot handle it well, and it is easy to cause missed detection of occluded vehicles

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 Method Based on Multiple Components
  • A Vehicle Detection Method Based on Multiple Components
  • A Vehicle Detection Method Based on Multiple Components

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0065] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments. The present invention is a vehicle detection method based on multiple components, the specific process is as follows figure 1 shown. The implementation scheme of the present invention is divided into three main steps: vehicle component selection, component template learning and vehicle detection. These three steps are detailed below:

[0066] Step S1: In vehicle component selection, considering different occlusion situations in complex traffic scenes, such as left / right side occlusion and upper / lower side occlusion, select 6 components from the vehicle object to form a vehicle model according to the importance of the components. Such as figure 2 As shown, the six components are the roof (part 1), the front cover (part 2), the left front (part 3), the right front (part 4), the left rear mirror (part 5), the right Rear mirror (part 6).

[0...

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 vehicle detection method based on multiple parts. The method includes first extracting six parts from a vehicle object according to the remarkable degree and different shielding conditions of vehicle parts for assembling a vehicle part model; then adopting the SVM to train part templates and part detection thresholds of the parts; finally utilizing background modeling based on a frame difference method to obtain a movement area; respectively detecting the six vehicle parts, analyzing the detection mark combination conditions of the different parts and verifying the vehicle shielding type to achieve vehicle detection. The method has the advantages of being easy to achieve, good in robustness, capable of adapting to appropriate deformation and the like, can detect the front shielded vehicles, can also detect the side shielded vehicles in certain angle range, and can be applied to detection of the shielded vehicles on road traffic scene.

Description

technical field [0001] The invention relates to the field of vehicle detection methods, in particular to a vehicle detection method based on multiple components. Background technique [0002] With the acceleration of the country's new-type urbanization, the number of public security cases and traffic accidents involving motor vehicles has increased sharply, and vehicle detection has become an important research content of the urban monitoring system. However, due to the complex imaging conditions in real scenes, vehicle detection faces many difficulties, among which the occlusion problem is particularly prominent. The existence of multiple targets in a complex road environment is the main reason for the mutual occlusion between vehicles. The occlusion leads to the loss of target information, which easily leads to missed detection of targets. [0003] Select the representative local area features of the vehicle, and through the detection of visible parts, it can avoid introd...

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 Patents(China)
IPC IPC(8): G06K9/46
Inventor 杨学志吴克伟薛丽霞陈孝培段伟伟
Owner HEFEI UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com