Motor vehicle right-turn comity pedestrian analysis snapshot system and method based on deep learning

A deep learning and motor vehicle technology, which is applied in the traffic control system of road vehicles, closed-circuit television systems, traffic control systems, etc., can solve problems such as inability to analyze and capture vehicles, give way to pedestrians and violate the law, and achieve high efficiency and high efficiency Effect

Inactive Publication Date: 2019-05-10
ZHEJIANG HAOTENG ELECTRONICS POLYTRON TECH INC
View PDF6 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0012] This application provides a road traffic analysis and capture system based on deep learning for motor vehicles to turn right and give way to pedestrians, which solves the problem that existing electronic police systems and ordinary video surveillance systems cannot analyze and capture vehicles that give way to pedestrians.

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
  • Motor vehicle right-turn comity pedestrian analysis snapshot system and method based on deep learning
  • Motor vehicle right-turn comity pedestrian analysis snapshot system and method based on deep learning
  • Motor vehicle right-turn comity pedestrian analysis snapshot system and method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] The present invention will be further described below in conjunction with the accompanying drawings:

[0049] A deep learning-based vehicle right turn courtesy pedestrian analysis and capture system, including an electronic police system installed at a road intersection and a common video surveillance system, and a video stream access module for accessing the electronic police system and video surveillance The video stream of the system;

[0050] The GPU graphics analysis module performs video decoding on the video stream accessed by the video stream access module, and outputs video data; the deep learning module analyzes the video data of the GPU graphics analysis module, and analyzes the illegal behavior of vehicles that do not avoid pedestrians when turning right. Capture evidence.

[0051] Preferably, the deep learning algorithm module includes:

[0052] The first analysis and judgment unit is configured to judge whether the pedestrian enters the crosswalk area ac...

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 motor vehicle right-turn comity pedestrian analysis snapshot system based on deep learning. The system comprises a video stream access module used for accessing video streamsof a road monitoring system, a GPU graphic analysis module used for performing video decoding on the video streams accessed by the video stream access module to obtain video data, and a deep learningalgorithm module used for analyzing the video data of the GPU graphic analysis module and performing snapshot and evidence obtaining on illegal behavior vehicles which do not avoid pedestrians duringright-turning. According to the system, the problem that a conventional electronic police system and an ordinary video monitoring system fail to analyze and take snapshots of the illegal vehicles which do not avoid pedestrians is solved.

Description

technical field [0001] The invention relates to the field of road traffic, in particular to a deep learning-based system and method for analyzing and capturing pedestrians with a right-turn courtesy of a motor vehicle. Background technique [0002] At present, the green light of the pedestrian crossing is on in my country's road traffic, and a few or even dozens of motor vehicles pass by a right-turning vehicle once the traffic light changes. Among these right-turning motor vehicles, many motor vehicles do not give way to pedestrians, so that pedestrians who are crossing the pedestrian crossing are forced to "Give way". It is a traffic violation that a motor vehicle turns right without giving way to pedestrians. This behavior violates the priority of pedestrians and is also the main reason for some traffic accidents at intersections. It is also an uncivilized and unsafe traffic behavior. [0003] Existing electronic police systems and video surveillance systems often only de...

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
IPC IPC(8): G08G1/017G06K9/00H04N7/18
Inventor 吴宗林夏路
Owner ZHEJIANG HAOTENG ELECTRONICS POLYTRON TECH INC
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