Sliding Window Search Method Based on Hierarchical Segmentation

A technique for hierarchical segmentation and search methods, applied in the field of computer vision

Inactive Publication Date: 2017-05-10
WUCHANG INST OF TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the above three strategies have accelerated the target detection speed to varying degrees, they still cannot fundamentally overcome the problem that the number of candidate windows is too large

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
  • Sliding Window Search Method Based on Hierarchical Segmentation
  • Sliding Window Search Method Based on Hierarchical Segmentation
  • Sliding Window Search Method Based on Hierarchical Segmentation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0029] Such as figure 1 with figure 2 As shown, a kind of sliding window search method based on hierarchical segmentation of the present invention comprises:

[0030] S100. Perform superpixel segmentation on image I, and denote the segmented superpixel set as

[0031] Image segmentation is to subdivide an image into subregions or objects that make it up, and propose objects of interest from them. The degree of segmentation depends on the problem to be solved. In this embodiment, the degree of segmentation is an adjustable and important indicator: if the segmentation is too fine, it can almost guarantee that an area corresponds to only one target, but a complete target will be divided into multiple parts. This increases the computational burden of subsequent processing; if the segmentation is too rough, it is difficult to ensure ...

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 a method for searching for a sliding window based on layered segmentation. According to the method, firstly, superpixel segmentation is conducted on an image; secondly, a layered segmentation algorithm of the image is run on the basis of a superpixel segmentation result of the image and a definition of region similarity; thirdly, initial windows are generated according to the layered segmentation result of the image, and the windows are screened according to the priori knowledge of a target; lastly, target candidate windows are collected densely around the remaining windows. By means of the method, on the premise that the target is not missed, only a small number of candidate target positions are generated, and the problem of a large calculated amount of feature extraction and classifier judgment in a target detection task can be effectively relieved.

Description

technical field [0001] The invention belongs to the technical field of computer vision, relates to image segmentation technology, is an important part of target detection, and is mainly applied to the target detection task of computer vision intelligent systems. Background technique [0002] Object detection is one of the most active research directions in the field of computer vision. Most of the existing object detection systems regard object detection as a binary classification problem, that is, to judge whether the object appears in all candidate positions. The target detection task is mainly divided into a training phase and a testing phase. The training phase includes feature extraction and target modeling, while the testing phase mainly includes three parts: target hypothesis, feature extraction and target judgment. Feature extraction is to quantify the training samples, that is, to convert the image into a vector for further analysis. Target modeling is to use train...

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): G06K9/46G06K9/62
Inventor 蔡静韩丹张琰张荆沙龚义建李道清
Owner WUCHANG INST OF TECH
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