Superpixel parameter adaptive selection method for visual perception saturation strategy
An adaptive selection, visual perception technology, applied in the field of computer vision, can solve the problems of lack of compatibility, difficult to adaptively select superpixel parameters, etc., to achieve the effect of low time complexity and reduce the amount of calculation
Active Publication Date: 2022-07-05
CHINA JILIANG UNIV
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
At present, the scale selection in image processing algorithms basically depends on subjective experience, lacks compatibility, and it is difficult to adaptively select superpixel parameters
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0026] The present invention will be further described below with reference to specific embodiments, but the present invention is not limited to these embodiments.
[0027] The present invention covers any alternatives, modifications, equivalent methods and arrangements made within the spirit and scope of the present invention. In order to give the public a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, and those skilled in the art can fully understand the present invention without the description of these details. In addition, the drawings of the present invention are not drawn exactly to actual scale for the purpose of illustration, and are described herein.
[0028] The invention draws on the gaze behavior of human vision and the phenomenon of visual perception saturation, and selects the superpixel parameter most likely to cause perceptual saturation as the best para...
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
The invention discloses a method for self-adaptive selection of superpixel parameters for a visual perception saturation strategy. Superpixel map SPi; 2) superpixel is represented as a single pixel, then each superpixel map can be represented as a reduced image Ii of the original image; 3) saliency map Si is calculated with salient point prediction algorithm for Ii respectively, wherein the saliency is Pixels whose values are greater than the average value are used as fixation points; 4) Kmeans clustering is performed with fixation points to generate multiple clusters Class_j; 5) Each type of fixation point forms its own fixation area and centroid, then the class of fixation points of this class to the centroid The inner distance can be regarded as a parameter of the microsaccade amplitude. 6) Normalize and accumulate the intra-class distances of various types in the whole image, as the microsaccade amplitude AOMi of the scale image; 7) Compare AOMi, the superpixel parameter Ki corresponding to the minimum value is the best parameter.
Description
technical field [0001] The invention relates to the technical field of computer vision, in particular to a method for self-adaptive selection of superpixel parameters of a visual perception saturation strategy. Background technique [0002] With the rapid development of technologies such as microelectronics and the Internet, optical cameras have become a standard information perception unit; at the same time, the image resolution of cameras is constantly improving, and ultra-high-definition devices above 4K are becoming more and more common. The improvement of image resolution makes the number of pixels increase geometrically. In the face of massive video image data, traditional pixel-based image processing algorithms face serious challenges. On the one hand, people are committed to continuously improving the hardware speed of computer systems to alleviate this pressure; on the other hand, it is an effective way to solve the problem by reasonably improving traditional image...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T3/40G06V10/762G06K9/62
CPCG06T3/4053G06F18/23213
Inventor 郭娅茜叶家建徐靓云张纠潘晨
Owner CHINA JILIANG UNIV