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

Deep learning retrograde motion detection method based on embedded terminal

An embedded terminal and deep learning technology, applied in the field of deep learning retrograde detection, can solve problems such as traffic accidents, achieve the effect of strengthening comprehensive judgment, accurately and automatically identifying the retrograde behavior of traffic vehicles, and improving the accuracy of judgment

Pending Publication Date: 2021-02-12
合肥湛达智能科技有限公司
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the deficiencies of the prior art, the present invention discloses a deep learning retrograde detection method based on an embedded terminal, which is used to solve the problem that the retrograde behavior of traffic vehicles easily causes traffic accidents, and establishes a set of efficient retrograde intelligent detection methods It is to prevent traffic vehicles from going against the road

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 retrograde motion detection method based on embedded terminal

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0026] This embodiment discloses as figure 1 A deep learning retrograde detection method based on an embedded terminal is shown, including the following steps:

[0027] S1 Set the detector area on the road section where the vehicle is traveling in reverse, and divide the detector area into two continuous sub-areas;

[0028] S2 collects two vehicle video images within the preset time slice Δt time range;

[0029] S3 identifies whether there is a vehicle passing through by analyzing and comparing the time sequence of the two images appearing in the detector;

[0030] S4 uses frame counting and boundary detection to identify the movement process of the vehicle, and calibrates the detector area from the beginning to the end;

[0031] S5 recognizes whether the vehicle has retrograde behavior through the relative movement direction of the moving vehicle, and inputs the deep learning neural network as a sample for learning and training;

[0032] S6 judges the occurrence of the veh...

Embodiment 2

[0040] This embodiment discloses a system that does not use the "warning line" method in setting. As long as the historical movement trajectory of the target is determined to be in the prohibited direction, the alarm will be issued. The detector setting uses a sector to mark the movement direction. The position and size of the sector can be passed The software of the system can be set arbitrarily, which is more extensive and practical for expanding applications to other industries.

[0041] Suppose the gray value of the moving target is X, and the gray value of the background pixel is Y, then the movement of the moving target in the detection area is equivalent to a block area moving in the background area of ​​Y, and the area of ​​the moving target A motion boundary is formed in the background area.

[0042] If the target is a vehicle, during the movement, the head and tail of the vehicle form a horizontal boundary, and the two sides of the vehicle form a vertical boundary. 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 invention relates to the technical field of intelligent transportation, in particular to a deep learning retrograde motion detection method based on an embedded terminal, which comprises the following steps: setting a detector area in a vehicle retrograde motion multi-occurrence road section, and dividing the detector area into two continuous sub-areas; identifying whether a vehicle passes ornot is by analyzing and comparing the appearing time sequence of the two images in the detector; recognizing whether the vehicle has a retrograde motion behavior or not according to the relative motion direction of the moving vehicle, and inputting the vehicle as a sample into a deep learning neural network for learning training; and judging the occurrence of a vehicle retrograde motion behavior according to the vehicle driving direction, capturing a violation scene image, intercepting a violation video, and completing detection. According to the invention, by means of deep learning, boundarydetection is carried out by using a sobel operator, and a motion boundary formed in a background when a vehicle passes through a detector is identified, so that comprehensive judgment is enhanced, thejudgment accuracy is improved, real-time judgment of vehicle retrograde motion is realized, and a retrograde motion behavior of a traffic vehicle is relatively accurately and automatically identified.

Description

technical field [0001] The invention relates to the technical field of intelligent transportation, in particular to a deep learning retrograde detection method based on an embedded terminal. Background technique [0002] With the advancement of computer chip technology and network technology, a new type of network video surveillance system has emerged, that is, a video surveillance system based on an embedded video server. Its structure is generally: at the remote monitoring site, there are several cameras, various detection, alarm probes and data equipment, which are aggregated to the video server through their own transmission lines, and the video server transmits these information to a network through the communication network. or multiple monitoring centers for users to view or browse, and authorized users can also control external devices based on this information. [0003] The video monitoring system based on the embedded video server inherits the advantages of the PC...

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): G06K9/00G06K9/34G06K9/46G06N3/04G06N3/08G08G1/017G08G1/056
CPCG06N3/08G08G1/0175G08G1/056G06V20/52G06V20/584G06V10/267G06V10/44G06V2201/08G06N3/045
Inventor 张中桂旺胜黄俊杰
Owner 合肥湛达智能科技有限公司
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com