Pedestrian traffic behavior recognition system and method based on attitude estimation

A pedestrian traffic and attitude estimation technology, applied in the field of big data recognition, can solve the problems of difficult update of sensors, limited range of action, lack of pedestrian behavior understanding and prediction ability, etc.

Pending Publication Date: 2020-11-24
深圳市自行科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] In the past, for the detection of pedestrians running red lights and occupying lanes, infrared sensors are usually used to detect pedestrian positions, such as whether they have crossed the boundary or left the sidewalk, etc., to judge whether pedestrians have committed traffic violations. In the existing visual solutions, generally It uses target detection and face recognition technology to locate the coordinates of pedestrians and determine whether pedestrians are in illegal areas to detect illegal behavior. In the current technology, sensors have high requirements for infrastructure construction and have a limited range of action. The behaviors that can be detected are also limited by the functions of the sensor and are not easy to update
[0003] Based on the visual target detection scheme, although it has a wider range of action and can detect multiple people at the same time, it lacks the ability to understand and predict pedestrian behavior, such as whether pedestrians are playing with mobile phones, whether they are walking normally, and whether they are about to commit illegal acts prediction

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
  • Pedestrian traffic behavior recognition system and method based on attitude estimation
  • Pedestrian traffic behavior recognition system and method based on attitude estimation
  • Pedestrian traffic behavior recognition system and method based on attitude estimation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] Such as figure 1 and 3 As shown in -5, the embodiment of the present invention provides a pedestrian traffic behavior recognition system based on posture estimation, including: an acquisition module 100, an analysis module 200, an output module 300 and a server 400;

[0035] The acquisition module 100 collects image data of pedestrians, and after processing the image data, transmits the processed image data to the analysis module 200. The acquisition module 100 includes an acquisition unit 101 and a preprocessing unit 102, and the acquisition unit 101 acquires image data of pedestrians , and transmit the image data to the preprocessing unit 102, the preprocessing unit 102 receives the image data transmitted by the acquisition unit 101, and preprocesses the image data, and the preprocessing unit 102 preprocesses the image data by dividing the image data into Continuous picture frames, and image normalization and scaling processing to obtain uniform image data;

[0036]...

Embodiment 2

[0049] The embodiment of the present invention also discloses a pedestrian traffic behavior recognition method based on attitude estimation, such as figure 2 , including the following steps:

[0050] S1, acquire pedestrian image data, the acquisition unit 101 acquires the image data of pedestrians, and transmits the image data to the preprocessing unit 102, the preprocessing unit 102 receives the image data transmitted by the acquisition unit 101, and divides the image data into continuous picture frames, And perform image normalization and scaling processing to obtain image data of uniform specifications, and transmit the image data to the attitude estimation network unit 201;

[0051] Specifically, the preprocessing unit 102 divides the image data collected by the collection unit 101 into continuous picture frames, and performs image normalization and scaling processing to obtain image data of a uniform specification, which is convenient for subsequent processing.

[0052]...

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 pedestrian traffic behavior recognition system and method based on attitude estimation, relating to the field of big data identification. The system comprises an acquisitionmodule, an analysis module, an output module and a server, based on posture estimation technique, the posture key points are combined with the trunk vector, a matching mode is adopted from bottom to top, scattered key points are matched into independent people, the posture information of the uncertain number of people in the visual field range can be identified; a function of acquiring pedestrianattitude coordinates by utilizing an attitude estimation network is realized; attitude coordinates of pedestrians in a period of time are obtained from a large amount of traffic video data; the current behavior is marked; a behavior recognition network with a time sequence analysis capability is trained; therefore, pedestrian behaviors can be identified, and the behaviors of pedestrians can be pre-judged in advance to a certain extent by utilizing the prediction capability of the time sequence analysis network, so that traffic violation behaviors can be found and warned more timely, and the problem that the existing visual target detection scheme lacks the understanding and pre-judgment capability on the behaviors of pedestrians is solved.

Description

technical field [0001] The invention relates to the technical field of big data recognition, in particular to a pedestrian traffic behavior recognition system and method based on attitude estimation. Background technique [0002] In the past, for the detection of pedestrians running red lights and occupying lanes, infrared sensors are usually used to detect pedestrian positions, such as whether they have crossed the boundary or left the sidewalk, etc., to judge whether pedestrians have committed traffic violations. In the existing visual solutions, generally It uses target detection and face recognition technology to locate the coordinates of pedestrians and determine whether pedestrians are in illegal areas to detect illegal behavior. In the current technology, sensors have high requirements for infrastructure construction and have a limited range of action. The behaviors that can be detected are also limited by the functionality of the sensor and are not easy to update. ...

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): G06K9/00
CPCG06V40/25G06V40/10
Inventor 李海云谌璟孙庆新
Owner 深圳市自行科技有限公司
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