Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Adhesion object segmentation method based on VIBE in object detection

A target segmentation and target detection technology, applied in image analysis, image data processing, instruments, etc., can solve the problems of inaccurate target segmentation, inability to solve segmentation, and high cost of clustering and segmentation time.

Inactive Publication Date: 2014-06-04
HUZHOU TEACHERS COLLEGE
View PDF0 Cites 28 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The threshold method is susceptible to background interference, and it is inaccurate for the segmentation of objects with insignificant grayscale changes; clustering segmentation takes a lot of time and is not real-time; segmentation based on morphology makes full use of the spatial information of the image, and the most widely used is the watershed algorithm , but the over-segmentation phenomenon cannot be solved due to the existence of noise

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
  • Adhesion object segmentation method based on VIBE in object detection
  • Adhesion object segmentation method based on VIBE in object detection
  • Adhesion object segmentation method based on VIBE in object detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] refer to figure 1 , figure 2 , image 3 and Figure 4 , a VIBE-based adhesion target segmentation method in a target detection of the present invention, comprising the following steps successively:

[0028] a) VIBE-based background subtraction: In a static scene, the VIBE algorithm is used to detect and obtain the moving target area in the foreground area. The VIBE algorithm uses a random strategy to update the background model in time and space. This strategy is exactly the same as the background The update is consistent with the situation that the foreground target suddenly changes to the background motion scene, and it is assumed that there is at least one moving target area in the foreground area detected by the VIBE algorithm;

[0029] b) HOG feature vector extraction: Since the appearance and shape of the local target in the image can always be described by its gradient direction or the direction density distribution of the edge, the HOG feature vector can eff...

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 an adhesion object segmentation method based on VIBE in object detection. The method includes the steps of background subtraction based on the VIBE, HOG feature vector extraction, SVM training and detection and segmentation algorithm optimization of multiple moving objects. For solving the problem of object adhesion occurring when the moving objects are shielded, the algorithm that spatial-temporal features are used for conducting rough segmentation on the moving objects in a video and then HOG features of the objects are extracted, trained and classified to perform precise segmentation is provided, the algorithm includes the steps that firstly, object detection is conducted through a VIBE algorithm, and a moving object area in a foreground is obtained by the adoption of background subtraction; secondly, scaling is conducted on images of the roughly-segmented moving objects in an original drawing, gradient histogram features of the images are extracted, a support vector machine is used for training to obtain an object segmentation classifier; finally, screening is conducted on positions of obtained moving objects, wrong objects which have large-area overlapping positions and are inconsistent in size are removed, and therefore segmentation of adhesion objects is completed.

Description

【Technical field】 [0001] The present invention relates to the technical field of a method for segmenting a cohesive target in target detection, in particular to the technical field of a method for segmenting a cohesive target based on VIBE in target detection. 【Background technique】 [0002] Moving object segmentation refers to the process of detecting moving objects from video sequences and separating them from the background. In the moving target segmentation of video sequences, according to the information it depends on, it can be divided into three types: time domain segmentation, spatial domain segmentation and joint spatio-temporal segmentation. Time-domain segmentation mainly uses the detection of adjacent frame differences to obtain the position and size of moving objects, mainly including frame difference method, background subtraction method and optical flow method. The principle of background subtraction is simple and the operation speed is fast, but the segmenta...

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): G06T7/20G06K9/62
Inventor 蒋云良刘红海侯向华黄旭
Owner HUZHOU TEACHERS COLLEGE
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
Eureka Blog
Learn More
PatSnap group products