Supercharge Your Innovation With Domain-Expert AI Agents!

Method and device for detecting targets

A target detection and variance technology, applied in character and pattern recognition, image data processing, instruments, etc., can solve the problems of false target detection, easy interference, inaccurate detection results, etc., to meet real-time performance and improve accuracy , to achieve a simple and convenient effect

Active Publication Date: 2011-11-09
HANGZHOU HIKVISION DIGITAL TECH
View PDF4 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method is easily disturbed. For example, when there are swinging leaves, rain and snow, or water waves in the background, it will lead to inaccurate detection results, such as false targets may be detected.

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 and device for detecting targets
  • Method and device for detecting targets
  • Method and device for detecting targets

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] In view of the problems existing in the prior art, an improved target detection scheme is proposed in the present invention, which can improve the accuracy of detection results.

[0022] In order to make the technical solution of the present invention more clear and understandable, the following describes the solution of the present invention in detail with reference to the accompanying drawings and examples.

[0023] figure 1 It is a flowchart of an embodiment of the target detection method of the present invention. like figure 1 shown, including the following steps:

[0024] Step 11: When the first frame of image is input, create a background model for each pixel in the image, and initialize each background model.

[0025] In an actual intelligent video analysis system, the size of each input frame image is the same, for example, they are all 640×480. Then, for these 640×480 pixels, a background model is created for each. Assuming that the grayscale value of a pix...

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 method and device for detecting targets. The method comprises the following steps: when a first frame image is input, constructing a background model for each pixel point in the image and initializing every background model; for each pixel point in each subsequently input frame image, updating a corresponding background model according to the gray value of the pixel point and the gray value of a pixel point in the same coordinate position in a previous frame image and determining whether the pixel point is a foreground point or a background point according to the update result; and obtaining more than one foreground mass by utilizing the determined foreground point and background point and taking the foreground masses as detected targets. The accuracy of the detection results can be improved by applying the method and device disclosed by the invention.

Description

technical field [0001] The invention relates to intelligent video analysis technology, in particular to a target detection method and device. Background technique [0002] Intelligent video analysis refers to the use of technologies such as image processing, computer vision, and pattern recognition to detect and track targets in input video images, such as vehicles or people, and to understand and describe their behavior, such as based on motion trajectories. Behavior analysis of the target, combined with the set behavior rules to output alarm information, etc. Among them, the detection of the target is an important link in the intelligent video analysis, and the accuracy of the detection result will directly affect whether the subsequent processing can be carried out smoothly. [0003] At present, the commonly used target detection method is the target detection method based on background subtraction, that is, the detection is performed by analyzing the difference between ...

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): G06T7/20G06K9/00
Inventor 蔡巍伟浦世亮贾永华任烨全晓臣
Owner HANGZHOU HIKVISION DIGITAL TECH
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com