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

Video big data traffic scene analysis method based on deep learning

A traffic scene and deep learning technology, which is applied in the field of video big data traffic scene analysis based on deep learning, can solve the problems such as the position of traffic lights and traffic signs that are easy to be ignored

Inactive Publication Date: 2019-08-06
长沙千视通智能科技有限公司
View PDF5 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At the same time, the existing traffic video analysis system is mainly aimed at dynamic vehicles and pedestrians, while relatively static background information, such as the position of the road, the position of traffic lights and traffic signs, etc. are often easily ignored

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
  • Video big data traffic scene analysis method based on deep learning
  • Video big data traffic scene analysis method based on deep learning
  • Video big data traffic scene analysis method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0058] refer to figure 1 , is an embodiment of a method for analyzing traffic scene of video big data based on deep learning of the present invention, and the method for analyzing traffic scene of video big data based on deep learning specifically includes the following steps:

[0059] S1. System video foreground and background analysis: use SOBS (Self-Organizing Neural Network Background Subtraction Algorithm) for background modeling, remove the foreground (cars, pedestrians) in the video freeze, and keep the background video;

[0060] SOBS (self-organizing through artificial neural networks) is a background difference algorithm based on self-organizing neural networks, which mainly draws on the characteristics of neural networks. A network input node corresponds to multiple intermediate nodes, and a pixel in the bac...

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 video big data traffic scene analysis method based on deep learning, which relates to the field of computer vision, and specifically comprises the following steps: S1, analyzing system video foreground and background: carrying out background modeling by adopting an SOBS, removing a foreground in a video frame, and reserving a background video; S2, detecting and classifying system video traffic signs: adopting an R-FCN algorithm to detect the road information of the background image and perform secondary structuring; and S3, counting each piece of data, analyzing information on the road, performing comprehensive summarization, and performing vehicle violation statistics and road planning in combination with a vehicle automatic detection system. The method can be applied to the intelligent brain of urban traffic, is usually combined with a vehicle automatic detection platform for use, can efficiently and accurately judge traffic flow, vehicle road violation andother events, and provides a good software basis for safe cities and intelligent traffic.

Description

technical field [0001] The present invention relates to the field of computer vision, in particular to a traffic scene analysis method based on deep learning of video big data. Background technique [0002] With the rapid development of modern transportation, security and other industries, people pay more and more attention to deep learning technology, which is one of the important research topics of computer vision and pattern recognition technology in the field of intelligent transportation in recent years. At the same time, in recent years, the country has vigorously promoted smart and safe cities and intelligent transportation systems, making the combination of the two possible. [0003] Intelligent transportation system is the effective comprehensive application of advanced information technology, positioning and navigation technology, data communication technology, electronic sensor technology, automatic control technology, image processing technology, computer network...

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): G06K9/00G06K9/62G06K9/34G06N3/04G08G1/01
CPCG08G1/01G06V20/54G06V10/267G06N3/045G06F18/24
Inventor 张斯尧王思远谢喜林张诚黄晋蒋杰
Owner 长沙千视通智能科技有限公司
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