Unlock instant, AI-driven research and patent intelligence for your innovation.

Shadow detection method based on color constancy characteristic and visual attention mechanism

A technology of visual attention mechanism and color constancy, applied in image data processing, instrumentation, computing, etc.

Active Publication Date: 2016-06-08
HOHAI UNIV
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In each type of method, researchers have proposed different ideas and specific implementation algorithms. According to the research results, each type of method has its own advantages and disadvantages. Therefore, so far there is no robust and general shadow detection. method

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
  • Shadow detection method based on color constancy characteristic and visual attention mechanism
  • Shadow detection method based on color constancy characteristic and visual attention mechanism
  • Shadow detection method based on color constancy characteristic and visual attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0078] The present invention will be specifically introduced below in conjunction with the accompanying drawings and specific embodiments.

[0079] The original image used in the present invention is an RGB true color image, denoted as Img. Among them, the three channels of red, green, and blue are recorded as R, G, and B respectively; the position of the pixel is represented by row and column numbers, for example, the pixel in row y and column x of the image Img is recorded as Img[y,x].

[0080] (1) The luminance feature (luminance) is extracted from the original Img, which is denoted as Lum.

[0081] Specifically: first extract the grayscale image of the original image, such as figure 1 As shown, then the logarithmic reciprocal of the grayscale image is used as the lum feature, such as figure 2 As shown, the calculation formula is as follows:

[0082] Gray=(R+G+B) / 3

[0083] Lum=1.0 / [5+log(Gray+1)]

[0084] Among them, Gray represents the average value of R, G, and B c...

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 novel effective shadow detection method based on the invariance characteristic of multiple colors of a shadow by introducing a visual attention mechanism of the field of computer vision. The shadow detection method comprises the following beneficial effects that 1) the invariance characteristic of multiple colors of the shadow is extracted according to the research result of color constancy, and multiple shadow characteristics are combined together by adopting a characteristic salient figure model in a visual attention model so that a shadow salient figure is generated to act as the basic data of shadow detection, and then shadow detection is performed based on the data; and 2) super-pixel segmentation is performed on an image by adopting an SLIC algorithm, and an object-based self-adaptive threshold growth algorithm is provided to correct the preliminary result of shadow detection so that a more complete shadow detection result can be obtained.

Description

technical field [0001] The invention relates to a shadow detection method based on the color constancy characteristics of shadows on a color image and a visual attention mechanism, belongs to the technical field of digital image processing and target recognition, and can be used for shadow detection of ground objects on color photos and remote sensing images. Background technique [0002] The shadow of ground objects is an inevitable phenomenon in natural photos, videos and remote sensing images, but the existence of shadows will bring many difficulties to computer vision tasks, often causing errors in image segmentation, edge detection and object recognition. Therefore, shadow detection is currently a research hotspot in the field of image processing and computer vision, and it is also a difficult problem. In shadow detection, it is mainly divided into two categories: video-based dynamic image shadow detection and single image-based static image shadow detection. . Because...

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): G06T7/00
Inventor ้™ˆไปๅ–œ
Owner HOHAI UNIV