Unlock instant, AI-driven research and patent intelligence for your innovation.

Behavior recognition method and device for multi-target tracking

A recognition method, multi-target technology, applied in neural learning methods, character and pattern recognition, instruments, etc., can solve the problems of low accuracy and high cost of behavior recognition technology

Pending Publication Date: 2021-09-14
BEIJING WODONG TIANJUN INFORMATION TECH CO LTD +1
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of this, the embodiment of the present invention provides a multi-target tracking behavior recognition method and device, which can solve the problems of high cost and low accuracy of the existing behavior recognition technology

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
  • Behavior recognition method and device for multi-target tracking
  • Behavior recognition method and device for multi-target tracking
  • Behavior recognition method and device for multi-target tracking

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] DRAWINGS The following description of exemplary embodiments make the present invention, including various details of the embodiments to assist in understanding the present invention, they should be regarded as merely exemplary. Accordingly, those of ordinary skill in the art of the present embodiment will be appreciated that embodiments described herein may make various changes and modifications without departing from the scope and spirit of the invention. Also, for clarity and conciseness, the following description is omitted the description of known functions and Structure.

[0035] figure 1 According to the main process behavior is a schematic diagram of the multi-target recognition method of the first embodiment of the present invention, tracking, such as figure 1 As shown in the multi-target tracking behavior recognition method comprising:

[0036] Step S101, the acquired multiple frames of the video stream, for target detection, target detection frame determined to h...

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 behavior recognition method and device for multi-target tracking, and relates to the technical field of computers. A specific embodiment of the method comprises the following steps: acquiring a multi-frame video stream to perform target detection, and determining a target detection frame of an object with a number, wherein the object number and the target detection frame have a mapping relationship; and tracking the object based on the target detection frame to identify behavior information of continuous frames of the object in the video stream, and further obtaining future behavior information of the object through a preset prediction model. Therefore, the embodiment of the invention can solve the problems of high cost and low accuracy of the existing behavior recognition technology.

Description

Technical field [0001] The present invention relates to computer technology, and in particular relates to a method and apparatus for identifying behavior multi-target tracking. Background technique [0002] Current behavior recognition technology, generally include a conventional sensor based on the behavior recognition: people wear sensors (gravity sensors), the change of acceleration and the direction of the identified behavior. Based on the behavior of a single frame of the traditional optical flow algorithms algorithm identified: multi-frame image to extract features of the optical flow, i.e. the direction of movement of light vector in each frame, and then put into the neural network predicted behavior. Behavior-based depth study to identify a single frame: the acquisition by the camera pictures in each frame, target detection algorithm to each frame, that is, to find pictures of objects and people's real borders and category labels. Based on the depth of behavioral learning...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/241
Inventor 胡淼枫徐达炜
Owner BEIJING WODONG TIANJUN INFORMATION TECH CO LTD