Deep learning based automatic checking method against red-light-running illegal behavior

A technology of deep learning and running a red light, which is applied in traffic control systems, instruments, character and pattern recognition of road vehicles, etc., can solve problems such as heavy workload, and achieve the effect of improving efficiency and saving manpower

Inactive Publication Date: 2019-06-28
上海眼控科技股份有限公司
View PDF16 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The traditional verification of vehicle illegal electronic police capture pictures is mainly through manual review, and the workload is relatively large. For example, when the ele...

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
  • Deep learning based automatic checking method against red-light-running illegal behavior
  • Deep learning based automatic checking method against red-light-running illegal behavior
  • Deep learning based automatic checking method against red-light-running illegal behavior

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] The present invention will be further described below in conjunction with the accompanying drawings.

[0046] The present invention is mainly based on a basic algorithm module, a logic judgment module and a rule judgment module.

[0047] Such as figure 2 As shown, the basic algorithm module is divided into traffic light detection classification unit, vehicle detection unit, license plate recognition, vehicle re-detection unit and image segmentation unit. First, the pictures are sent to the traffic light detection and classification unit, and the vehicle detection unit then sends the vehicle detection results to the license plate recognition, vehicle re-detection unit and image segmentation unit. Wherein the traffic light detection unit adopts the improved SSD target detection model, because the proportion of the traffic light in the whole picture is very small, the original SSD detection method cannot detect such a small target, the present invention adopts a method o...

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 deep learning based automatic checking method against a red-light-running illegal behavior. The method comprises the following steps that an original illegal behavior image uploaded by a front illegal behavior snapshot device is obtained; the image is cut and re-ordered; vehicle information which needs checking is detected and identified; the state of a traffic light is detected and identified; the original picture is cut to obtain necessary information including solid lines, stop lines, guiding lines, lane lines and zebra crossing lines; the positional relation between the vehicle and the stop lines, guiding lines and lane lines is determined; and whether the original illegal behavior image can pass checking is determined according to a red-light-running e-policeimage screening standard. Thus, the snapshot of the red-light-running illegal behavior is checked automatically, a present artificial checking method can be replaced, the labor force can be saved, and checking is accelerated.

Description

technical field [0001] The invention relates to the technical field of intelligent image recognition such as target detection, attribute classification, and scene segmentation, and in particular to the technical field of artificial intelligence judgment for reviewing snapped pictures by illegal electronic police of motor vehicles. Background technique [0002] With the continuous development of social economy and the continuous improvement of people's living standards, the number of urban motor vehicles has increased rapidly. The number of illegal electronic police capture systems for motor vehicles has also increased rapidly. The traditional verification of vehicle illegal electronic police capture pictures is mainly through manual review, and the workload is relatively large. For example, when the electronic police cannot work normally due to special weather or road renovation, a large number of invalid snapshots will be generated, which causes artificial The audit worklo...

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): G08G1/017G06K9/00G06K9/62G06K9/34
Inventor 周康明
Owner 上海眼控科技股份有限公司
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