Non-rigid target detection method and system thereof

A target detection, non-rigid body technology, applied to instruments, character and pattern recognition, computer components, etc., can solve problems such as limited effect and unsatisfactory mAP value, and achieve fast running speed, enhanced detection effect, and strong characterization ability Effect

Active Publication Date: 2015-04-08
ENC DATA SERVICE CO LTD
View PDF3 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, although there are some methods to reduce the target retrieval space, such as Efficient Subwindow Search, etc., the effect is limited, and the final mAP value is not ideal

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
  • Non-rigid target detection method and system thereof
  • Non-rigid target detection method and system thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] Such as figure 1 As shown, a non-rigid object detection method, including:

[0033] S101. Using the selective search region proposals algorithm to perform object-like detection on the input image, and find out a rectangular region in the input image where there may be an object-like target.

[0034] Specifically, the following algorithm can be used to find out the rectangular area:

[0035] Selective search region proposals algorithm (Selective search for object recognition. IJCV, 2013);

[0036] objectness algorithm (Measuring the objectness of image windows.TPAMI, 2012);

[0037] category-independent object proposals algorithm (Category independent object proposals.In ECCV2010);

[0038] onstrained arametric min-cuts (CPMC) algorithm (Automatic object segmentation using constrained parametric min-cuts.TPAMI, 2012.).

[0039] S102. Before using the non-rigid object model to extract features from the rectangular area, you can first extend the edge of each rectangula...

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

A non-rigid target detection method comprises the following steps of performing like-object detection on an input image and finding out rectangular areas which are possibly provided with like-object targets in the input image; performing characteristic extraction on every obtained rectangular area through a pre-trained non-rigid target model and obtaining HSC characteristics and textural features of every rectangular area; forming into a characteristic pyramid; performing PCA projection on the characteristic pyramid and classifying modes on characteristic pyramid space at the low latitude; convolving every scale of the pyramid through every root and obtaining a root scoring chart of every layer of the pyramid; convolving every corresponding part layer of the root layer through part filters and obtaining a root score chart of all parts; performing distance transformation to reconstruct all part scores of every root, comparing and judging a threshold value of the same model and obtaining a position of a non-rigid target of the rectangular areas. The non-rigid target detection method is good in detection effect, rapid in speed and low in leak detection rate.

Description

technical field [0001] The invention belongs to the technical field of target detection, and in particular relates to a non-rigid body target detection method and system thereof. Background technique [0002] Object detection is a fundamental work in the field of computer vision. This work is somewhat complicated by the fact that the appearance of objects to be detected may vary widely. Moreover, the variation comes not only from brightness and viewing angle, but also from deformation due to non-rigid objects, as well as shape and other visual changes of the same type of objects. For example, people may wear different clothes and do different poses, and cars may have different shapes and colors. At present, the commonly used object detection methods often use some simple models, such as fixed rigid body templates or feature bag models to represent objects, which are obviously not enough to represent a non-rigid body object with rich changes. [0003] In the field of targe...

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): G06K9/00G06K9/62
Inventor 邱志明张如高赵晓萌虞正华彭莉张伟
Owner ENC DATA SERVICE CO LTD
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap