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

A smoky vehicle detection method based on multi-sequence dual projection

A detection method and multi-sequence technology, applied in instruments, biological neural network models, computing, etc., can solve problems such as high false alarm rate, affecting traffic, and adverse evidence acquisition and preservation, achieving high real-time performance, simple calculation, and overcoming Effects of Normalization Problems

Active Publication Date: 2021-09-03
SOUTHEAST UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, the monitoring of smoky vehicles in my country mainly relies on the traditional method of blocking vehicles, which is inefficient, labor-intensive, and affects traffic at the same time, which is not conducive to evidence acquisition and preservation
The smoky car video surveillance system we developed still has the disadvantage of high false alarm rate, and there is still a long way to go before wide-scale application

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 smoky vehicle detection method based on multi-sequence dual projection
  • A smoky vehicle detection method based on multi-sequence dual projection
  • A smoky vehicle detection method based on multi-sequence dual projection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0063] Below in conjunction with accompanying drawing and specific embodiment the present invention is described in further detail:

[0064] The present invention provides a detection method for smoky vehicles based on multi-sequence double-projection. The multi-sequence double-projection features invented can fully describe the characteristics of the black smoke in the key areas of black smoke and the characteristics of the left and right symmetry of the rear of the vehicle in the non-smoky area. , the added multi-sequence analysis strategy can describe the dynamic characteristics of the key areas, including the characteristics of the black smoke in the key area of ​​black smoke gradually spreading and the characteristics of the rear of the vehicle in the non-black smoke area moving forward. The calculation of multi-sequence double projection features is simple , high real-time performance. The introduction of local random filtering makes the feature robust to shadows, thereb...

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 method for detecting black smoke vehicles based on multi-sequence double projection. The method includes: (1) detecting moving targets and determining key areas; (2) using integral projection and local random filtering techniques to extract multi-sequence double-projection features to form feature vectors describing key areas; (3) training C-BPNN classification and used for the classification of new feature vectors; (4) Through the analysis of continuous multiple frames, it is judged whether the current vehicle is a smoky vehicle. Utilizing the technical solution of the present invention not only improves the detection efficiency and reduces the cost, but also the proposed multi-sequence double-projection feature has the characteristics of simple calculation and strong description ability, which greatly improves the detection rate of black smoke vehicles and reduces the False alarm rate.

Description

technical field [0001] The present invention relates to the technical field of computer vision and intelligent smoke and fire detection, in particular to a method for detecting smoky vehicles based on multi-sequence double projection. Background technique [0002] "Smoky vehicles" are typical representatives of high-pollution vehicles, and are also the main contributors to inhalable particulate matter. Due to the large number of smoky vehicles and their irregular appearance, how to timely and accurately detect smoky vehicles driving on the road has always been an environmental protection field. The most concerned issue has become the focus of attention since 2018 as the country pays more and more attention to environmental protection. Therefore, if the research of this project is successful, it will have broad application prospects. [0003] At present, the monitoring of smoky vehicles in my country mainly relies on the traditional method of blocking vehicles, which is inef...

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): G06K9/00G06K9/62G06N3/04
CPCG06V20/41G06N3/044G06F18/241
Inventor 路小波陶焕杰
Owner SOUTHEAST UNIV
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