Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Recognition method for objects in two-dimensional images

An object recognition and object technology, which is applied in the field of object recognition of robust object structure learning methods, and can solve problems such as inability to recognize complex images.

Active Publication Date: 2013-04-03
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF4 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The technical problem solved by the present invention is to propose an object recognition method based on a visual mechanism-based robust object structure learning method, which overcomes the problem that existing recognition methods cannot recognize complex images.

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
  • Recognition method for objects in two-dimensional images
  • Recognition method for objects in two-dimensional images
  • Recognition method for objects in two-dimensional images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0110] In order to describe the specific implementation of the invention in detail, the vehicle detection system in a certain monitoring scene is taken as an example for description below. This system can judge whether there is a vehicle in the monitoring scene.

[0111] Step A, first collect a large number of vehicle images (1000) and non-vehicle images (1000), these images are used to train the vehicle recognition model.

[0112] Step B, the training steps are as follows:

[0113] Step B0, training process initialization: SIFT feature extraction is performed on 1000 vehicle images (positive samples) and 1000 non-vehicle images (negative samples) to generate 2000 sets of SIFT features. Based on an average of 2000 SIFT features per group, a total of 4,000,000 (2000×2000) SIFT features were extracted. Then, a clustering operation is performed on 4,000,000 SIFT features to generate a visual dictionary containing 1,000 visual words. Finally, use the visual dictionary model and...

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 object recognition method of a vision mechanism based robust object structural learning method. The method includes a training process and a recognition process and includes the steps: subjecting target objects with marked types and positions in images to information feedback of a vision mechanism, and training to obtain a feedback model; and preliminarily predicating object types and object positions of objects in a to-be-recognized image, and using the feedback model obtained by training to robustly learning structural information of the target objects. Since robust object structures and the vision mechanism have invariance in object recognition, the vision mechanism based robust object structural learning method is adopted for improving object recognition precision, and types and positions of targets in recognition scenes can be accurately recognized by the method. In addition, the object recognition method can be widely applied to safety inspection, internet search, digital entertainment and the like.

Description

technical field [0001] The invention belongs to the fields of pattern recognition and computer vision, and specifically relates to an object recognition method in a two-dimensional image, in particular to an object recognition method based on a visual mechanism-based robust object structure learning method. Background technique [0002] In recent years, researchers have devoted themselves to finding an invariant object representation. Extensive physiological studies have shown that robust object structure can play an important role in the invariance of object representation. At the same time, the researchers also found that the invariance of object representation can also be verified by visual mechanisms. Therefore, it is conceivable that there is a close connection between robust object structures and visual mechanisms. [0003] Furthermore, psychological experiments have shown that robust object structures can be described by the object's constituent parts, which consist...

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 Applications(China)
IPC IPC(8): G06K9/66
Inventor 黄凯奇谭铁牛王冲
Owner INST OF AUTOMATION CHINESE ACAD OF SCI
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com