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

A method and device for detecting violently moving objects

A moving target and vigorous motion technology, applied in the field of violent motion target detection methods and devices, can solve the problems of slow calculation speed, high computational complexity of optical flow calculation, and inability to meet real-time processing, so as to improve the accuracy and reduce the amount of calculation. Effect

Active Publication Date: 2016-07-06
ZHEJIANG DAHUA TECH CO LTD
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] However, optical flow calculation has the problems of high computational complexity and slow calculation speed, which cannot meet the needs of real-time processing.

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
  • A method and device for detecting violently moving objects
  • A method and device for detecting violently moving objects
  • A method and device for detecting violently moving objects

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] Embodiment 1 of the present invention provides a method for detecting a vigorously moving target. The steps of the method can be as follows figure 2 shown, including:

[0033] Step 101, perform corner detection on a frame of image.

[0034] In this step, the corner point detection may be performed on the position corresponding to the position of a moving object in the first moving object foreground image in the Nth frame of images in the sequence image to obtain the first set of corner points. The first moving target foreground image is obtained by performing foreground detection on the Nth frame of image, where N is a positive integer not less than 2. The method for performing foreground detection is the same as that of the prior art, and will not be repeated here.

[0035] The first foreground image of the moving object may include one moving object, may include multiple moving objects, or may not include the moving object. If the first moving object foreground im...

Embodiment 2

[0058] Embodiment 2 of the present invention provides a method for detecting a vigorously moving target. The steps of the method can be as follows image 3 shown, including:

[0059] Step 201, perform corner detection on the current frame image.

[0060] In this step, a frame of image may be received, and the received frame of image may be used as the current frame image to perform foreground detection on the current frame image to obtain a binarized current frame moving target foreground image, and in the current frame image, Corner detection is performed at the position corresponding to the position of the foreground image of the moving target in the current frame.

[0061] Specifically, in order to increase the speed of corner detection and fully ensure the speed of violently moving target detection, the Harris corner detection method can be used to achieve corner detection (of course, other detection methods can also be used, such as fast-corner corner detection method, ...

Embodiment 3

[0085] Embodiment 3 of the present invention provides a device for detecting violently moving objects. The structure of the device can be as follows Figure 4 shown, including:

[0086] The corner point detection module 11 is used to perform corner point detection on the position corresponding to the position of a moving object in the first moving object foreground image in the Nth frame image in the sequence image, and obtain a first set of corner points, the first corner point set A moving target foreground image is obtained by performing foreground detection on the Nth frame image, wherein the N is a positive integer not less than 2;

[0087] The matching module 12 is used to determine, for each first corner point in the first corner point set, whether there is a second corner point that matches the first corner point in the reference corner point set, and the reference corner point set is for all corner points. In the N-1th frame image in the sequence image, the position ...

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 embodiment of the invention provides a method and device for detection of a violently moving target. The method and device detects angular points (feature points) of a frame image according to the foreground image of the frame image so as to obtain the feature points of a moving target in the frame image. By determining the relative positional relation between matched angular points in the frame image and the previous frame image adjacent to the frame image, the direction and the range of the motion of the moving target in the frame image are determined, so as to be capable of determining whether the moving target in the frame image is the violently moving target in the frame image. Because the scheme determines whether the moving target violently moves acutely by using a small number of points according to the foreground image, the calculated quantity can be effectively reduced. Because the selected feature points can more accurately represent the motion information of the moving target, the accuracy of the determined results can also be improved.

Description

technical field [0001] The present invention relates to the communication field, in particular to a method and device for detecting violently moving objects. Background technique [0002] Intelligent video surveillance is the use of computer vision technology to process, analyze and understand video signals. Without human intervention, through automatic analysis of sequence images, the targets in the surveillance scene are located, identified and tracked, and here Based on the analysis and judgment of the target's behavior, it can send an alarm or provide useful information in time when an abnormal situation occurs. Since intelligent video surveillance does not require manpower to monitor video images, it can actively detect, track and analyze video images of interested targets around the clock, and report events, and the application of intelligent video surveillance is becoming more and more extensive. [0003] The general intelligent video surveillance process can be as f...

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 Patents(China)
IPC IPC(8): G06T7/20
Inventor 吴良健潘华东潘石柱孙莉田建国周洪涛张兴明傅利泉朱江明吴军吴坚
Owner ZHEJIANG DAHUA TECH CO LTD