Area-of-interest detection method based on Kinect

A technology of region of interest and detection method, which is applied in the direction of instruments, character and pattern recognition, computer components, etc., and can solve problems such as poor accuracy

Inactive Publication Date: 2014-08-06
NORTHWESTERN POLYTECHNICAL UNIV +1
View PDF10 Cites 31 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the shortcomings of the poor accuracy of the existing ROI detection method ba

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
  • Area-of-interest detection method based on Kinect
  • Area-of-interest detection method based on Kinect
  • Area-of-interest detection method based on Kinect

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] refer to figure 1 . The present invention is based on the concrete steps of the region of interest detection method of Kinect as follows:

[0044] (1) Acquisition of images in RGB-D format.

[0045] Use the Kinect3D camera and the API provided by Microsoft to obtain 3D images in RGB-D format.

[0046] Connect the Kinect camera to the computer through the USB interface, and run the application program interface provided by Microsoft to obtain 3D images in RGB-D format. Among them, the RGB image represents the image data of the three channels of R, G and B; D is the depth data, which represents the distance from a certain point in space to the camera plane.

[0047] (2) Calculation of multi-scale feature maps.

[0048] Including the generation of multi-scale images, the extraction of grayscale feature maps, the extraction of color feature maps, the extraction of direction feature maps and the extraction of edge feature maps.

[0049] Generation of multi-scale images:...

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 area-of-interest detection method based on Kinect. The area-of-interest detection method is used for solving the technical problem that an existing area-of-interest detection method based on an improved saliency map model is low in accuracy. According to the technical scheme, a Kinect3D camera lens is used for obtaining a two-dimensional RGB image and depth information; on the basis, the RGB image is used for extracting various visual features and establishing a multi-scale visual feature map; then the feature map and a depth map are fused to generate the saliency map, and a winner-take-all strategy is used for generating a two-value saliency map; finally, dilation is performed on the two-value saliency map to detect a final area of interest. The 3D image, generated by the Kinect camera lens, in a RGB-D format can be used for detecting the area of interest, wherein the area of interest is consistent with the result of perception through the human eyes. Under the same condition, the matching rate of the area of interest is increased to 91.2% from 82.5% in the background technology, which means the matching rate is increased by 8.7%, and the area of interest is automatically detected by the utilization of the method.

Description

technical field [0001] The present invention relates to a method for detecting a region of interest, in particular to a method for detecting a region of interest based on Kinect. Background technique [0002] The ROI detection method based on human visual features has attracted the attention of researchers at home and abroad. [0003] The document "Region of Interest Detection Technology Based on Edge and Depth Features. Xia Zhaoqiang, Feng Xiaoyi, Peng Jinye. Computer Simulation, 2009, (7); 248-251" discloses a region of interest based on an improved saliency map (Saliency Map) model Detection method. This method firstly generates a two-dimensional saliency map from visual features such as grayscale, color, direction and edge extracted from a two-dimensional RGB image, and then uses the saliency map to detect the region of interest that is consistent with the detection results of the human eye. This method collects 100 pictures, and then asks 5 users to mark the region of...

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): G06K9/60
Inventor 彭先霖夏召强冯晓毅彭进业王珺毛晓菲崔明辉胡旭涛
Owner NORTHWESTERN POLYTECHNICAL 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

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