Image interest area extraction method based on eyeball tracking and automatic focus system

A region-of-interest and auto-focusing technology, applied in the field of image recognition, can solve the problems of inability to accurately determine the region of interest, unreasonable encoding method of the region of interest, and rough division of the region of interest, so as to improve the subjective experience and save money. Storage space, the effect of speeding up focusing

CN104125405AInactive Publication Date: 2014-10-29罗天明 +1
6 Cites 14 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
Publication Date
2014-10-29
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

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.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the technical field of image recognition, and in particular relates to a method for extracting an image region of interest based on an eye tracking and automatic focusing system. Background technique

[0002] Currently, a high-definition video format (High Definition, HD) is increasingly used in various video recordings and real-time video communications. However, storing and transmitting HD video streams brings great challenges to storage devices and network bandwidth. Especially for portable recording devices, such as smart phones and DV machines, the wide use of HD video is limited due to their limited storage space. 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 ROI-based video coding methods, most of them use face re...

Examples

Embodiment

[0049] Embodiment: A method for extracting an image region of interest based on an eye tracking and auto-focus system

[0050] The camera or video camera used to capture images or video frames is equipped with an eye-tracking sensor that can determine where the eye is focusing; follow the attached figure 1 As shown in the system block diagram, the specific steps are as follows:

[0051] The first step, create an image or video frame matrix

[0052] According to the image or video frame size of the camera or video camera, correspondingly establish an image or video frame matrix R .

[0053] The second step, get the focus point

[0054] Obtain the attention point of the eye on the camera or the viewfinder screen of the camera through the eye tracking sensor, and the attention point is in the matrix R The coordinates in are (x, y), which is the focus point. in the attached figure 2 Describes the scene of using a mobile phone or a tablet computer or other shooting device 5 ...