Calibration method for extracting illumination-insensitive information from visible images
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A technology for sensitive information and calibration methods, applied in image analysis, image data processing, instruments, etc., can solve the problems of insufficient stability of online calibration and insensitive information of light, and achieve the effect of simple scheme
Inactive Publication Date: 2010-08-04
HARBIN INST OF TECH
View PDF0 Cites 9 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0004] The purpose of the present invention is to solve the problem that the online calibration based on a single image is not stable enough when extracting one-dimensional illumination constant "gra
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
specific Embodiment approach 1
[0017] Specific implementation mode one: the following combination Figure 1 to Figure 5 Describe this embodiment, the method of this embodiment includes the following steps:
[0018] Step 1. Segment the visible light image based on consistent color to obtain multiple segmented regions C i , where, i=1, 2,..., m, m is a positive integer,
[0019] Step 2. For each segmented area C i The area is calculated if the segmented area C i If the area exceeds 0.0025 of the entire image area, it will be retained, otherwise, the segmented area will be discarded,
[0020] Step 3. For the segmented area C whose area obtained in step 2 exceeds 0.0025 of the entire image area i Verify the smoothness of the texture, and the smoothness meets the segmentation area C with a standard deviation less than 8 i is retained, otherwise, the segmented area is discarded,
[0021] Step 4: Establish a color ratio logarithmic space coordinate system, and divide the region C retained in Step 3 i The RG...
specific Embodiment approach 2
[0048] Embodiment 2: The difference between this embodiment and Embodiment 1 is that α in step 6 is 1 degree, and the others are the same as Embodiment 1.
[0049] If each rotation is 1 degree, the number of projections h=180, a total of 180 straight lines, and finally one of them is determined as the calibration straight line.
specific Embodiment approach 3
[0050] Embodiment 3: The difference between this embodiment and Embodiment 1 is that the criterion for judging the color consistency in step 1 is: the chromaticity value between pixels is less than a threshold T, and the others are the same as Embodiment 1.
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
Login to view more
Abstract
A calibration method for extracting illumination-insensitive information from visible images belongs to the image processing field. The invention aims to solve the problem that online calibration based on single image is not stable enough when gray information with constant one-dimensional illumination is extracted to calibrate the light sensation components of the camera. The method comprises the following steps: 1. segmenting the visible images based on color consistency; 2. keeping the zones with area in excess of 0.0025 of the area of the whole image; 3. keeping the zones with good smoothness; 4. establishing a space coordinate system of color matching numbers; 5. carrying out projection to the straight line which passes through the zero point of the coordinate and forms an included angle theta with the forward direction of the X axis, calculating normal distribution through best fit by adopting maximum likelihood estimation and calculating the similarity degree; 6. rotating alpha angle; 7. judging whether the product of alpha and h is more than 180 degrees, if so, carrying out the step 8, if not, carrying out the step 5; and 8. deciding the straight line with the best similarity degree as the calibration straight line for extracting the illumination-insensitive information through chi-square test.
Description
technical field [0001] The invention relates to a calibration method for extracting illumination insensitive information from visible light images, belonging to the field of image processing. Background technique [0002] Obtaining light-insensitive information from visible light images is an important image processing technology, which has a wide range of applications in the field of computer vision, such as visual monitoring of outdoor environments. [0003] At present, the main way to obtain illumination-insensitive information is to calculate color constancy. One of the methods is to modify multi-channel color information (such as RGB) to make it into image information under a certain standard illumination. Due to multi-dimensional data Recovery itself is a pathological problem, so the application of this method is limited. Another type of method is the extraction of "grayscale" information with constant one-dimensional illumination. This method assumes that the image i...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more