Clustering-Based Multi-Object Detection Method in Images

A detection method and technology in images, applied in the field of pattern recognition, can solve the problem of not effectively improving object detection results, and achieve the effect of reducing computational complexity

Inactive Publication Date: 2016-01-13
SHANGHAI JIAOTONG UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The definition of spatial relationship in the second method is too simple, which does not effectively improve the detection results of objects

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
  • Clustering-Based Multi-Object Detection Method in Images
  • Clustering-Based Multi-Object Detection Method in Images
  • Clustering-Based Multi-Object Detection Method in Images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The present invention will be described in detail below in conjunction with specific embodiments. The following examples will help those skilled in the art to further understand the present invention, but do not limit the present invention in any form. It should be noted that those skilled in the art can make several modifications and improvements without departing from the concept of the present invention. These all belong to the protection scope of the present invention.

[0023] Such as figure 1 As shown, this embodiment can be divided into the following steps.

[0024] (1) Statistically cluster the relationship between objects and visual idioms in the image, and use the local model to get the window of objects and visual idioms

[0025] Because visual idioms generally contain two kinds of objects, and the relative positions of these two objects compared with the visual idioms are basically fixed. Therefore, the relative horizontal and vertical positions of objec...

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 belongs to the technical field of pattern recognition and discloses a clustering based detection method for multiple objects in an image. The method includes the steps: (1) carrying out statistic of relationship of the objects in the image with visual idioms prior to clustering, and using a partial model for obtaining windows of the objects and the visual idioms; and (2) constructing space relationship features according to a prototype, and using a structured support for training and testing a vector machine. The method is superior to various existing object detection methods, and computation complexity is slightly lowered.

Description

technical field [0001] The invention relates to a multi-object detection method, in particular to a multi-object detection method based on clustering in an image, and belongs to the technical field of pattern recognition. Background technique [0002] In traditional object detection schemes, many of them are identified based on the local features of the image, without considering the relationship between objects in the image. This method relies on the invariance of the object itself, and the detection effect on objects with variable poses is poor. In the object detection scheme considering the spatial relationship, firstly, the possible position of the object in the image is obtained through local feature recognition, and is marked as a window, and the weight is assigned to the window. Then define a series of objects and the spatial relationship between objects, and identify the spatial relationship existing in the image. Increase the weight of certain windows through spat...

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): G06K9/62
Inventor 张瑞朱玉琨朱俊邹维嘉仇媛媛付赛男
Owner SHANGHAI JIAOTONG UNIV
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
Try Eureka
PatSnap group products