Vehicle video analysis method and system thereof

A video analysis and vehicle technology, which is applied in the field of vehicle video analysis methods and systems, can solve the problems of difficulty in target extraction and failure to extract vehicles in the target area, and achieve the effect of avoiding misjudgment

Inactive Publication Date: 2012-04-11
ANHUI CHAOYUAN INFORMATION TECH
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, in the existing intelligent transportation field, target extraction in complex scenes has always been a difficult problem. At present, it is not possible to extract the complete target area and the vehicle after removing the shadow.

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
  • Vehicle video analysis method and system thereof
  • Vehicle video analysis method and system thereof
  • Vehicle video analysis method and system thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0033] see figure 1 As shown, the target region is extracted, including:

[0034] Step 101: In the HSV space V channel, normalize the ratio of the current frame to the background image and map it to 0-255; wherein, normalization is to map a set of data to the (0,1) interval;

[0035] Step 102: Perform histogram statistics and Gaussian fitting to obtain the mean value u and variance δ of the ratio map; wherein, Gaussian fitting is to first use a local Gaussian function to respectively fit the data points around the extreme value, and then fit the obtained Adjacent local functions are spliced ​​together to form a global fitting function.

[0036] Step 103: remove the points in the ratio whose ratio is within u±Kδ and use the part of the ratio outside u±Kδ as the target area; where K is a coefficient related to image noise.

[0037] see figure 2 As shown, shadow removal includes:

[0038] Step 201: Divide the shadow into four directions: front, back, left, and right, and det...

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 provides a vehicle video analysis method and a system thereof. The method comprises the following steps: (1) extraction of a target area: in a V channel of HSV space, carrying out normalization on a ratio graph of a present frame and a background graph and mapping the ratio graph to a 0-255 range, obtaining an average value u and a variance delta of the ratio graph through histogramstatistics and Gaussian fitting, and taking a part except for u+ / - Kdelta in the ratio graph as the target area, wherein, K is a coefficient related to image noise; (2) removal of a shadow: dividing directions of the shadow into four directions; with regards to removal of the shadow at left and right directions, carrying out breaking and segmentation according to width of the shadow and a vehiclebody in a same connected domain, and with regards to removal of the shadow at front and back directions, comparing gradient sum of each row and a gradient row average value of the whole connected domain in a same connected domain and carrying out segmentation. According to the video analysis method, a complete body area can be extracted, obstruction of realizing subsequent video analysis functions of analyzing behaviors of pressing a line, changing a lane, running a red light and the like of a vehicle is eliminated, and misjudgement of the functions is avoided.

Description

technical field [0001] The invention relates to the field of intelligent transportation, in particular to a vehicle video analysis method and system. Background technique [0002] With the increase of the mileage of vehicles and roads, the speed of vehicles increases, and the number of traffic accidents continues to increase, which affects the development of the national economy and the normal life of the people. One of the main factors leading to the increase in the number of traffic accidents is various violations of rules and regulations caused by humans and non-humans during the driving process of vehicles. [0003] In the construction of existing road traffic safety facilities, several well-known technical tools are adopted, which can monitor and record the violation process of the above-mentioned events, and can punish the vehicles and personnel involved according to regulations. For example, the electronic police can record the process of vehicles running red lights;...

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): G06K9/54G08G1/01
Inventor 张俊王伟邓宏平刘星
Owner ANHUI CHAOYUAN INFORMATION TECH
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