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

Smoky Vehicle Recognition Method Based on Gaussian Mixture and Autoregressive Moving Average Model

A Gaussian mixture model, autoregressive sliding technology, applied in the field of computer vision and pattern recognition, can solve problems such as unfavorable vehicle preservation, time-consuming and labor-intensive, affecting traffic operation, saving manpower and financial resources, improving law enforcement efficiency, and fast computing. Effect

Active Publication Date: 2021-08-13
SOUTHEAST UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, many cities still use road inspections, public reports and manual video surveillance to detect smoky vehicles on the road, which is time-consuming and laborious, and will also affect normal traffic operations, which is not conducive to the preservation of illegal evidence of related 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
  • Smoky Vehicle Recognition Method Based on Gaussian Mixture and Autoregressive Moving Average Model
  • Smoky Vehicle Recognition Method Based on Gaussian Mixture and Autoregressive Moving Average Model
  • Smoky Vehicle Recognition Method Based on Gaussian Mixture and Autoregressive Moving Average Model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0075] Below in conjunction with accompanying drawing and specific embodiment the present invention is described in further detail:

[0076] The invention provides a smoky car recognition method based on Gaussian mixture and autoregressive moving average model, which can synthesize different types of static features, and introduces autoregressive moving average model to describe the dynamic characteristics of key areas, and is effective for camera shake and vehicle shadows High robustness, can reduce noise interference, further improve the recognition rate of smoky cars, and reduce the false alarm rate.

[0077] The present invention provides a smoky car identification method based on Gaussian mixture and autoregressive moving average model, the flow chart of which is as follows figure 1 As shown, follow the steps below:

[0078] Step 1: Use the Gaussian mixture model to detect vehicle moving targets from road surveillance videos;

[0079] Step 2: Extract three features of t...

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 smoky car recognition method based on Gaussian mixture and autoregressive moving average model includes the following steps: (1) using Gaussian mixture model to detect vehicle moving targets from road surveillance video; (2) extracting three features of key areas of the vehicle, including Haar-like feature, co-occurrence matrix gradient direction histogram feature and local binary mode Fourier histogram feature; (3) use the autoregressive moving average model to model the continuous multi-frames of each feature, and get three different models ; (4) For the new vehicle target, the three models are used to classify the three features extracted from the key areas of the vehicle, and the classification results of different features and the comprehensive analysis of continuous multi-frames are used to determine whether the current video segment is black or not. The cigarette truck makes a judgment call. The invention can greatly save manpower and financial resources consumed by traditional methods, is beneficial to the acquisition and preservation of evidence, does not affect normal traffic, and can effectively improve law enforcement efficiency.

Description

technical field [0001] The invention relates to the technical fields of computer vision and pattern recognition, in particular to a black-smoky car recognition method based on a Gaussian mixture and an autoregressive sliding average model. Background technique [0002] On June 16, 2018, the Central Committee of the Communist Party of China and the State Council issued the "Opinions on Comprehensively Strengthening Ecological and Environmental Protection and Resolutely Fighting the Battle of Pollution Prevention and Control", pointing out that "the battle of pollution control from diesel trucks must be fought well,...to build a world of integration of space, earth, vehicles and people." Motor vehicle emission monitoring system, perfect motor vehicle remote sensing monitoring network". Diesel vehicles with serious pollution are also called smoky vehicles. Usually there will be thick black smoke at the exhaust holes. The pollution has always been the focus of motor vehicle poll...

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): G06K9/00G06K9/46G06K9/62
CPCG06V20/584G06V20/52G06V10/507G06V2201/08G06F18/2135G06F18/24
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