Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Pedestrian positioning and track obtaining method based on camera video stream

An acquisition method and video streaming technology, which is applied in image enhancement, image analysis, image data processing, etc., can solve problems such as complex network and poor model robustness, and achieve the effect of solving large amount of calculation, high accuracy, and cost reduction

Active Publication Date: 2020-11-10
TONGJI UNIV
View PDF9 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

(Wen Feng, Guo Yue, Yuan Kui, He Jia. Pedestrian positioning method and system based on distributed vision [P]. CN105809108A, 2016-07- 27.) The main defect of this invention is that the method mainly focuses on improving pedestrian positioning. The accuracy of detection, but for pedestrian positioning, it is necessary to rely on mobile robots to obtain the mapping relationship between image coordinates and map coordinates, and the network composed of distributed cameras and mobile robots is complex and the robustness of the model is poor

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 positioning and track obtaining method based on camera video stream
  • Pedestrian positioning and track obtaining method based on camera video stream
  • Pedestrian positioning and track obtaining method based on camera video stream

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0027] Compared with the prior art, the technical solution of the embodiment solves the following problems: (1) The features of the indoor target person are extracted based on the video stream of the camera, so as to achieve the purpose of pedestrian detection and classification; The established spatial model and positioning algorithm calculate each frame of the camera video stream to obtain the position information of the detected target person, and obtain a chain structure based on the time stamp of each frame of image, which is the movement of pedestrians (3) Ensure the accuracy of pedestrian detection; (4) Ensure the accuracy of the calculated pedestrian position information and trajectory; (5) Reduce the complexity of the model, reduce the time-consuming calculation, and ensure real-time performance, thereby solving the problem of existing technologies Problems such as complex model, large amount of calculation, and inability to guarantee real-time performance; (6) reduce ...

Embodiment 2

[0057] Based on the method scheme of Embodiment 1 of the present invention, a pedestrian positioning and trajectory acquisition system based on camera video streams is further provided, such as figure 1 As shown, the system includes a fixed camera, a processing terminal and a display terminal.

[0058] The processing end may be a computer terminal, a mobile phone terminal or a cloud server.

[0059] The processing end includes a camera video stream processing module, a pedestrian detection module, and a location acquisition module.

[0060] The video stream processing module: for the video stream acquired by the fixed camera, the video stream processing module is used to transmit the video stream to the pedestrian detection module in units of each frame of image.

[0061] The pedestrian detection module mainly includes two parts, a feature extraction module and a detection module, and adopts HOG+SVM; including the following steps: first, perform operations such as grayscale, ...

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

A pedestrian positioning and track acquisition method based on a camera video stream is characterized by sequentially comprising two steps: 1, a feature extraction and detection algorithm of an indoortarget person; wherein the pedestrian detection module is used for performing pedestrian detection on each frame of image of a camera video stream; 2, a pedestrian position information and a moving track acquisition algorithm thereof; wherein the algorithm is used for acquiring position information and moving tracks of pedestrians detected in each frame of image of a camera video stream. According to the method, the space models of the indoor camera and the pedestrian are established, the related models are established from the vertical section and the horizontal section of the pedestrian respectively, the established models are simple and efficient, the required calculation amount is small, the accuracy of the acquired position information is high, the calculation force can be saved, thetime consumption is reduced, and the real-time performance is ensured.

Description

technical field [0001] The invention belongs to the technical field of machine vision and indoor positioning fusion. Background technique [0002] When satellite positioning cannot be used in an indoor environment, the use of indoor positioning technology can solve the problem that satellite signals are weak when they reach the ground and cannot penetrate buildings. Pedestrian detection, positioning and trajectory acquisition based on camera video stream can become an effective means to assist indoor positioning technology. Moreover, the detection, positioning and trajectory acquisition of pedestrians in the camera scene are also important components of intelligent video surveillance and have application potential, and are also research hotspots in recent years. [0003] In the field of computer vision, pedestrian detection technology is developing rapidly. The cameras used for pedestrian detection mainly include fixed cameras, 3D cameras, RGBD cameras, PTZ cameras, etc. ...

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): G06K9/00G06K9/62G06N3/04G06T7/246G06T7/269
CPCG06T7/246G06T7/269G06T2207/30241G06T2207/20081G06T2207/20084G06V20/40G06V20/46G06V20/52G06N3/045G06F18/214Y02T10/40
Inventor 刘儿兀刘轶铭
Owner TONGJI UNIV
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
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