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

Image color space transformation method with unchanged illumination

A color space transformation, illumination invariant technology, applied in the field of computer vision, can solve the problems of loss of color and texture information, low computational complexity, insufficient shadow processing effect, etc., to achieve robust object recognition and meet real-time effects.

Active Publication Date: 2017-11-03
ZHEJIANG UNIV
View PDF7 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In contrast, the method based on image transformation has low computational complexity and is convenient for real-time calculation, but the shadow processing effect is not good enough, and a lot of color and texture information in the original image is lost during the transformation process.

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
  • Image color space transformation method with unchanged illumination
  • Image color space transformation method with unchanged illumination
  • Image color space transformation method with unchanged illumination

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] The present invention will be described in detail below in conjunction with specific embodiments.

[0055] Embodiments of the present invention are as follows:

[0056] In the case of digital camera parameter determination in the example, the six transformation parameters γ gr ,γ br ,γ rg ,γ bg ,γ rb ,γ gr Obtained by solving the system of equations.

[0057] The transformation factor γ obtained by solving gr ,γ br ,γ rg ,γ bg ,γ rb ,γ gr They are:

[0058] gamma gr =0.6,γ br =0.6,γ rg =0.48,γ bg =0.57,γ rb =0.4,γ gb = 0.4.

[0059] Therefore, the following formula is used to transform the image color space invariant to illumination:

[0060]

[0061] Such as figure 1 In order to illustrate the reconstruction results of scenes with strong shadows, for a road scene strongly affected by shadows, in the image obtained after light-invariant color transformation, the effect caused by shadows is basically eliminated, which can be beneficial to the road...

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 image color space transformation method with unchanged illumination. According to the invention, based on a camera imaging model, an original image is converted into a color space which is free from effects of illumination intensity and mainly affected by a light reflecting feature of the surface of an object; the color space with the unchanged illumination is defined into red, green and blue channels, wherein the value of each channel is obtained by use of a linearity relation of the three channels in the original image; and a transformation factor can be determined according to parameters of the camera. Thus, effects on the image imposed by complex illumination and shadows are eliminated; the image only representing the surface feature of the object is obtained; and the method can be widely applicable to all kinds of vision recognition tasks.

Description

technical field [0001] The invention belongs to the field of computer vision, and relates to an image color space transformation method with constant illumination. Background technique [0002] With the rapid development of computer technology, computer vision is widely used in environmental perception tasks of robots and intelligent vehicles, such as road recognition, obstacle recognition, etc. However, in the outdoor environment, the effect of the visual algorithm is affected by complex environmental factors, such as lighting conditions, shadows, etc., which directly affect the appearance and shape of the object in the image, which increases the difficulty of the recognition task and increases the difficulty of the visual recognition algorithm. of complexity. [0003] In previous studies, there are a series of image processing algorithms to deal with complex lighting situations, including methods based on statistical learning (R.Guo, Q.Dai, D.Hoiem. Paired regions for sha...

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): G06K9/46G06T7/90
CPCG06T7/90G06V10/56
Inventor 陈剑贾丙西张凯祥
Owner ZHEJIANG UNIV