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

Deep learning non-yielding zebra crossing detection method based on embedded terminal

An embedded terminal and deep learning technology, applied in the field of deep learning indiscreet zebra crossing detection, can solve the problems of spending a lot of manpower and material resources, too much image data, and vehicles being disrespectful to pedestrians, etc., so as to improve the convenience of installation and improve the detection efficiency. , improve the targeted effect

Pending Publication Date: 2020-09-22
合肥湛达智能科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] With the continuous development of science and technology, the number of vehicles is also increasing, and at the same time, it is accompanied by the situation that vehicles are not polite to pedestrians. For this reason, our country needs to spend a lot of money every year to install capture equipment at traffic light intersections, but the effect is not ideal. Secondly, Due to the large amount of captured image data and the inability to carry out targeted inspections, it takes a lot of manpower and material resources. Therefore, we propose a deep learning method based on embedded terminals to detect impolite zebra crossings.

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 non-yielding zebra crossing detection method based on embedded terminal
  • Deep learning non-yielding zebra crossing detection method based on embedded terminal

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] Such as figure 1 As shown, a deep learning impolite zebra crossing detection method based on an embedded terminal, the embedded terminal includes a podium, a commanding height monitor, a high position monitor, a low point monitor, a communication terminal and a connector, the podium, It is used to receive and display the received monitoring data, and is also used to send out control instructions;

[0046] The commanding height monitor is installed on the top of the highest building or equipment, and is used to take pictures of the surrounding geographical environment from a high place, receive monitoring data transmitted by the high position monitor, and transmit the received monitoring data to the commander platform;

[0047] The high-level monitor is installed on the top of each crossing near the building in the monitoring area of ​​the commanding height monitor, and is used to monitor the overall traffic environment of each crossing, and receives the monitoring data...

Embodiment 2

[0067] Such as figure 1 As shown, a deep learning impolite zebra crossing detection method based on an embedded terminal, the embedded terminal includes a podium, a commanding height monitor, a high position monitor, a low point monitor, a communication terminal and a connector, the podium, It is used to receive and display the received monitoring data, and is also used to send out control instructions;

[0068] The commanding height monitor is installed on the top of the highest building or equipment, and is used to take pictures of the surrounding geographical environment from a high place, receive monitoring data transmitted by the high position monitor, and transmit the received monitoring data to the commander platform;

[0069] The high-level monitor is installed on the top of each crossing near the building in the monitoring area of ​​the commanding height monitor, and is used to monitor the overall traffic environment of each crossing, and receives the monitoring data...

Embodiment 3

[0089] Such as figure 1 As shown, a deep learning impolite zebra crossing detection method based on an embedded terminal, the embedded terminal includes a podium, a commanding height monitor, a high position monitor, a low point monitor, a communication terminal and a connector, the podium, It is used to receive and display the received monitoring data, and is also used to send out control instructions;

[0090] The commanding height monitor is installed on the top of the highest building or equipment, and is used to take pictures of the surrounding geographical environment from a high place, receive monitoring data transmitted by the high position monitor, and transmit the received monitoring data to the commander platform;

[0091] The high-level monitor is installed on the top of each crossing near the building in the monitoring area of ​​the commanding height monitor, and is used to monitor the overall traffic environment of each crossing, and receives the monitoring data...

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 non-yielding zebra crossing detection method based on an embedded terminal. The method comprises the following steps: firstly, detecting the motion trails of people near an intersection through a high-position monitor; comparing the abnormal data with the position of a zebra crossing at an intersection to obtain abnormal data, intercepting a monitoring imageunder the duration of the abnormal data according to the position of the abnormal data, confirming the monitoring image again by a command set, and shooting the user according to a movement track shot by a high-position monitor. The invention relates to a deep learning non-yielding zebra crossing detection method based on an embedded terminal. The method is characterized in that: firstly, intersection conditions are photographed through a high-position monitor, and afterwards, the image which is photographed by a corresponding low-position monitor is extracted for improving detection pertinency; and secondly, the connector is arranged on the existing monitoring equipment, so that the existing equipment can be used under the condition that rewiring or new monitoring equipment does not need to be arranged, the cost can be reduced, and meanwhile, the convenience in installation can be improved.

Description

technical field [0001] The present invention relates to the field of detection methods for impolite zebra crossings, in particular to an embedded terminal-based deep learning detection method for impolite zebra crossings. Background technique [0002] With the continuous development of science and technology, the number of vehicles is also increasing, and at the same time, it is accompanied by the situation that vehicles are not polite to pedestrians. For this reason, our country needs to spend a lot of money every year to install capture equipment at traffic light intersections, but the effect is not ideal. Secondly, Due to the large amount of captured image data and the inability to carry out targeted inspections, it takes a lot of manpower and material resources. Therefore, we propose a deep learning method based on embedded terminals to detect impolite zebra crossings. Contents of the invention [0003] The main purpose of the present invention is to provide an embedde...

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): G06K9/00G06F16/29G06F16/54H04N5/247H04N7/18G08G1/01
CPCG06F16/29G06F16/54H04N7/181G08G1/0125G06V40/16G06V20/54G06V20/625H04N23/90
Inventor 张中桂旺胜
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