Point of regard detection method based on multilayer information fusion

A detection method and gaze point technology, applied in the field of gaze point detection, can solve problems such as inability to obtain detection results

Inactive Publication Date: 2017-06-09
DALIAN UNIV OF TECH
View PDF3 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is: there are many kinds of images in natural scenes, and the detection method using a single feature information cannot obtain better detection results. Feature information can be well detected

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
  • Point of regard detection method based on multilayer information fusion
  • Point of regard detection method based on multilayer information fusion
  • Point of regard detection method based on multilayer information fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0059] Step 1: Generate pyramids for the L, A, and B channels of the image, and the scale of each layer of the image is half that of the previous layer. The bottom of the pyramid is the original high-resolution image, and as the number of pyramid layers increases, the image resolution decreases. The image in each layer is obtained after filtering and downsampling the image in the previous layer. The filtering part of the present invention adopts Gaussian filtering, the template is [5*5], and the Gaussian template with a standard deviation of 1.6. The model constructs a 9-layer Gaussian pyramid. Taking the L component as an example, the pyramid is recorded as L(σ), σ∈[0, 8]. The difference map is computed using the "central-peripheral" operator, and then normalized by the non-linear normalization operator N(·). Finally, the three color channels are superimposed to obtain the underlying information detection map.

[0060] Step 2: First, use the edge multi-scale combination gr...

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 present invention belongs to the computer vision field, and relates to a point of regard detection method based on the multilayer information fusion. The point of regard detection method is characterized by obtaining a bottom-layer information detection result diagram by the bottom-layer information, such as the colors, etc.; utilizing the spatial position to obtain a center prior diagram; extracting a candidate target frame and the CNN depth features of an original image, utilizing a bag-of-word model to encode, sending the encoded visual features in a trained multi-instance RMI-SVM classifier to mark, and carrying out the Gaussian smoothing on the center of the frame and then carrying out the weighted stack according to the mark of the target frame to obtain a detection result diagram of a target grade; extracting the features describing the overall content of the original image itself, training a softmax regression device to obtain the fusion weight, and adopting the weight to carry out the weighted fusion on the above result diagram. The point of regard detection method of the present invention comprehensively utilizes the information at the three aspects of the color contrast, the significant target and the spatial position, adjusts the proportion of various information aiming at different images, and can have a better detection rate aiming at the image containing various content.

Description

technical field [0001] The invention belongs to the field of computer vision, relates to relevant image processing knowledge, and in particular relates to a gaze point detection method. Background technique [0002] In the current rapidly developing society, surveillance cameras can be seen everywhere in the city, which brings a serious problem of information overload. The task of computer vision technology is to quickly find the target of interest in a variety of images and video files, so the research on gaze point detection is very meaningful. The reason for the point of fixation is that the candidate foreground object and the background in the scene form a novel stimulus that attracts the attention of the human eye in a specific contrast. Image gaze point detection is an important branch in image processing. In image processing, gaze point detection is often used as a pre-operation in image segmentation, adaptive image compression, content-based image editing, target d...

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): G06K9/62
CPCG06F18/254G06F18/253
Inventor 李建华肖迪卢湖川
Owner DALIAN UNIV OF TECH
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