Check patentability & draft patents in minutes with Patsnap Eureka AI!

Image target detection method based on sparse learning variable model

A target detection and learning model technology, applied in the field of intelligent information processing and target detection, can solve problems such as target detection errors and changes in target appearance characteristics, and achieve the effect of eliminating interference and achieving good detection results.

Active Publication Date: 2018-09-11
OCEAN UNIV OF CHINA
View PDF8 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

That is, the main problems in the existing technology: (1) In the real scene, the image object is affected by factors such as illumination, viewing angle and scale change, and the appearance characteristics of the object change greatly; (2) due to the lack of Context information, in the case of partial occlusion or deformation of the image target, will lead to the problem of target detection error

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
  • Image target detection method based on sparse learning variable model
  • Image target detection method based on sparse learning variable model
  • Image target detection method based on sparse learning variable model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] In order to make the purpose, implementation and advantages of the present invention clearer, the present invention will be further described below in conjunction with the accompanying drawings and through specific examples.

[0037] An embodiment employs an underwater image dataset.

[0038] The specific flow chart of this embodiment is as follows figure 1 As shown, as follows:

[0039] (1) Get the training image {I n ,n=1,2,...,N}, preprocessing the training image by filtering, denoising and contrast enhancement.

[0040] (2) Image background measurement: use the linear iterative clustering method to divide each training image into N grids, and calculate the ratio of the area connected to the image boundary of each area in the image to the square root of the overall area of ​​the area:

[0041]

[0042] Among them, B is the set of image boundary blocks, R is the set of target region blocks, and p is the image block. The number of grids connected between the targe...

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 image target detection method based on a sparse learning variable model. The visual color contour detection model based on background measurement is introduced, the interference of the background on the image target is eliminated, and the contour information of the training target is effectively extracted by combining the visual color contour detection model; the image target detection method based on the sparse learning variable model has a good detection effect on the easily deformed, large posture and scale variable, and shielded image target. The image target detection method is good in firmness and high in robustness.

Description

technical field [0001] The invention relates to an image target detection research method based on sparse learning variable models, and belongs to the technical field of intelligent information processing and target detection. Background technique [0002] Object detection is an important link in the vision system. Object detection technology has broad application prospects in video surveillance, intelligent robot navigation, automatic driving, gesture recognition, shape retrieval and other fields. In real scenes, due to the influence of factors such as deformation, partial occlusion, illumination changes, viewing angle changes, and scale changes of the target, the appearance characteristics of the target change greatly, which brings great challenges to image target detection. [0003] The methods of target detection include target detection based on texture features and target detection methods based on contour features according to the features used. The target detection ...

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): G06T7/73G06T7/13G06T7/194G06T7/62G06T7/90G06K9/62
CPCG06T7/13G06T7/194G06T7/62G06T7/75G06T7/90G06T2207/20081G06V2201/07G06F18/214
Inventor 年睿王致远
Owner OCEAN UNIV OF CHINA
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