Target detection recognition algorithm based on 3D (Three-dimensional) trajectory analysis

A technology of trajectory analysis and target detection, applied in character and pattern recognition, computing, computer parts, etc., can solve problems such as inability to meet real-time monitoring and difficulty in monitoring video attention.

Inactive Publication Date: 2016-11-16
CHANGAN UNIV
View PDF10 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The traditional video monitoring system is mainly based on "manual monitoring", that is, it mainly relies on people to analyze and judge the content in the vi

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
  • Target detection recognition algorithm based on 3D (Three-dimensional) trajectory analysis
  • Target detection recognition algorithm based on 3D (Three-dimensional) trajectory analysis
  • Target detection recognition algorithm based on 3D (Three-dimensional) trajectory analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0065] Comply with the above technical solutions, such as figure 1 Shown, concrete process of the present invention is as follows:

[0066] A target detection and recognition algorithm based on 3D trajectory analysis, the method utilizes a binocular camera installed above the rear door of a bus to collect video images for target detection and recognition, specifically comprising the following steps:

[0067] Step 1, initialize the binocular camera

[0068] (1-1) After installing the binocular camera, use the binocular camera to collect video images at the same time, calibrate the binocular camera through the two frames of video images collected by the binocular camera to obtain the internal and external parameters of the binocular camera, save the calibration The two frames of video images and the internal and external parameters of the binocular camera;

[0069] (1-2) Respectively correct the two frames of video images after calibration to eliminate the deformation of the i...

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 target detection recognition algorithm based on 3D (Three-dimensional) trajectory analysis. In the method, a binocular camera installed above the rear door of a bus is used for collecting a video image to carry out target detection recognition, the motion positions of the same passenger at different moments are taken as movement targets, the motion targets are subjected to preliminary recognition through the depth map of a video screen image, then, a pseudo-motion target is removed, and finally, the accurate detection recognition of the motion target is realized. Through the 3D trajectory analysis, target recognition detection is carried out, trajectory tracking failure caused by illumination in a trajectory tracking process in the prior art is solved, and the accuracy of target recognition detection is improved. The target detection recognition algorithm is free from the restriction of a hardware environment, can carry out real-time detection and is high in detection accuracy. The two-dimensional trajectory of the image of the motion target is converted into a 3D trajectory under a world coordinate system, the most common problem in traditional target recognition that the target can not be detected since the target is covered is solved, and the accuracy of the target recognition detection is improved.

Description

technical field [0001] The invention belongs to the field of video detection, and in particular relates to a target detection and recognition algorithm based on 3D trajectory analysis. Background technique [0002] In today's era, with the development of science and technology, sensing technology has gradually developed, which makes the means for people to obtain information more diversified, and also drives the development of information processing technology. Among the diversified means of information acquisition, the video surveillance system has attracted widespread attention because of its convenient use, rich information content, and intuitive features. The traditional video monitoring system is mainly based on "manual monitoring", that is, it mainly relies on people to analyze and judge the content in the video. Keep a certain amount of attention on the surveillance video, especially in complex scenes, which cannot meet the requirements of real-time surveillance. Th...

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): G06K9/00G06K9/46G06K9/62
CPCG06V20/52G06V10/443G06V2201/07G06F18/22
Inventor 宋焕生孙士杰庞凤兰刘瑞芝李倩丽王璇张文涛
Owner CHANGAN 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
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