Image region of interest extraction method based on eye tracking and auto-focus system
An area of interest and auto-focus technology, applied in the field of image recognition, can solve the problems of inability to accurately determine the area of interest, unreasonable encoding method of the area of interest, and rough division of the area of interest, so as to improve the subjective experience and save The effect of storage space and faster focusing speed
Inactive Publication Date: 2018-08-17
罗天明 +1
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0006] In the patent "A Video Encoding and Decoding Method and System" (CN102905136A), a scheme is proposed to divide and encode the region of interest through the focus of the viewer's eyeballs. However, the region of interest division scheme proposed in this patent is relatively rough and cannot Accurately determine the region of interest, the proposed encoding method based on the region of interest is unreasonable, it is mentioned that the original video needs to be divided into several independent videos and then encoded independently, which will introduce high-frequency information at the edge of the image, which is not conducive to compression
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
[0049] Embodiment: a method for extracting a region of interest in an image based on an eye tracking and autofocus system
[0050] The camera or video camera used to obtain images or video frames is equipped with an eye tracking sensor that can determine where the eye is concerned; figure 1 The specific steps are as follows:
[0051] The first step is to establish an image or video frame matrix
[0052] According to the image or video frame size of the camera or video camera, an image or video frame matrix R is established correspondingly.
[0053] The second step, get the focus
[0054] The eye-tracking sensor is used to obtain the focus point of the eyeball on the camera or the viewfinder screen of the camera. The coordinates of the focus point in the matrix R are (x, y), which is the focus point. Attached figure 2 Describes a scene in which a shooting device 5 such as a mobile phone or a tablet computer is used to shoot a video. When the photographer 7 holds the shooting device 5 t...
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
Disclosed is an image interest area extraction method based on eyeball tracking and an automatic focus system. The method has the advantages that a focus point of an image or a video frame is obtained by means of eyeball tracking, an interest area is computed on the basis of the focus point, different coding strategies are adopted for the interest area and a non-interest area, the interest area is coded by more code rates while the non-interest area is coded by less code rates, and thereby compression is benefited, storage space is saved greatly, and subjective experience of video coding is improved more beneficially.
Description
Technical field [0001] The invention belongs to the technical field of image recognition, and specifically relates to an image interest region extraction method based on an eye tracking and auto-focusing system. Background technique [0002] At present, high-definition video formats (High Definition, HD) are increasingly used in various video recording and real-time video communications. However, storing and transmitting HD video streams has brought great challenges to storage devices and network bandwidth. Especially for portable video recording devices, such as smart phones and DV machines, the limited storage space limits the widespread use of HD video. An effective solution is to divide the region of interest and the region of non-interest in the video, use different coding strategies for different regions, and use more bit rates to encode the region of interest, and vice versa. [0003] In traditional video coding methods based on regions of interest, most of them use face r...
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): H04N5/232
Inventor 罗天明程飞
Owner 罗天明