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

Method used for identifying object motion directions and equipment

A technology of motion direction and objects, applied in the field of image processing, can solve cumbersome and time-consuming problems, and achieve the effect of improving recognition accuracy

Inactive Publication Date: 2016-01-06
RICOH KK
View PDF5 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In such methods, a large number of samples need to be trained in advance, which is a tedious and time-consuming process

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
  • Method used for identifying object motion directions and equipment
  • Method used for identifying object motion directions and equipment
  • Method used for identifying object motion directions and equipment

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0028] figure 2 A flow chart of the method for identifying the moving direction of an object according to the first embodiment of the present invention is shown.

[0029] like figure 2 As shown, in step S201, a sequence of image frames including the object captured by a stereo camera is acquired, and the number of frames of the sequence of image frames is the size of a predetermined sampling window.

[0030]The sampling window is an analysis window for determining the moving direction of the object, that is, when a series of image frames with the size of the sampling window are acquired, the moving direction of the object in the sampling window is determined by analyzing and processing the series of image frames. It can be understood that the size of the sampling window here is the number of acquired image frames for analysis and processing, for example, for figure 1 In the case exemplified in , the size of the sampling window is 6. The size of the sampling window can be ...

no. 2 example

[0063] In the method for recognizing the direction of motion of an object according to the first embodiment of the present invention, a single stereo camera is used to detect the object to identify its direction of motion. However, the detection angle of a single stereo camera is limited, and due to the inherent error of the camera, the detection range and Detection accuracy is also limited. Therefore, in this embodiment, a plurality of stereo cameras are used to detect the object to identify the moving direction of the object, which can solve the problem of object occlusion and further improve the recognition accuracy of the moving direction.

[0064] The method for identifying the moving direction of an object according to this embodiment is substantially the same as the identification method described in the first embodiment. Hereinafter, descriptions of the same contents will be omitted, and only points different from the first embodiment will be described in detail.

[0...

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 provides a method used for identifying object motion directions. The method comprises steps that, a picture frame sequence of an object shot by at least one stereo camera is acquired, a frame number of the picture frame sequence is the size of a pre-determined sampling window; a tracing point in the real world corresponding to an object projection in each picture frame in the picture frame sequence shot by each stereo camera is determined; statistics analysis on overall distribution of multiple corresponding tracking points is carried out to determine the most remarkable change direction, and the most remarkable change direction is taken as the motion direction of the object in the sampling window. According to the method used for identifying the object motion directions, the motion direction can be accurately identified relatively even when the tracking point is influenced by noise, moreover, multiple stereo cameras can be utilized to detect objects, so an object shield problem can be excellently solved, and identification precision can be further improved.

Description

technical field [0001] The present invention relates generally to image processing, and in particular to methods and devices for identifying the direction of motion of an object. Background technique [0002] As people pay more and more attention to public safety, various monitoring systems have spread all over every corner of every city. In these various monitoring systems, the movement direction analysis of moving objects is an indispensable part. For example, in public transportation hubs such as airports, train stations, and subway stations, walking against the flow of people or against the prescribed directions is often considered an abnormal behavior. For another example, for the monitoring system installed in dangerous warehouses such as hazardous chemical storage warehouses and radioactive material storage warehouses, one of its basic functions is to be able to detect the behavior of people approaching dangerous goods, and once such behavior is detected, immediately...

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): G06T7/20G06T7/246G06T7/285
Inventor 王千范圣印王鑫乔刚诸加丹
Owner RICOH KK
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