Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method and device for obtaining scene boundary

A technology of scene boundaries and boundaries, applied in image data processing, instruments, calculations, etc., can solve problems such as time-consuming, high manual participation, poor interaction, etc., to avoid mis-segmentation, low manual participation, and improve accuracy sexual effect

Inactive Publication Date: 2011-10-26
TSINGHUA UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] 1) The manual extraction method has a high degree of manual participation, low processing efficiency, and takes a lot of time; and relies on manual experience and technology, poor portability
[0008] 2) For the same scene with rich surface texture, the image segmentation algorithm often divides it into different scenes, and the accuracy is poor; moreover, it is difficult to manually intervene, and the interaction is poor

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
  • Method and device for obtaining scene boundary
  • Method and device for obtaining scene boundary
  • Method and device for obtaining scene boundary

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0029] see figure 1 , an embodiment of the present invention provides a method for obtaining a boundary of a scene, the method comprising:

[0030] 101: Obtain discrete boundary points of each single-channel grayscale information in multiple single-channel grayscale information of the image;

[0031] 102: Obtain multiple key points on the boundary of the scene, and arrange the multiple key points in order;

[0032] 103: According to the discrete boundary points of each single-channel grayscale information, use the shortest path search algorithm to search and obtain the effective boundary between every two adjacent key points;

[0033] 104: Connect the effective boundaries between every two adjacent key points to obtain the boundary of the scene.

[0034] Specifically, acquiring discrete boundary points of each single-channel grayscale information of multiple single-channel grayscale information of an image may include:

[0035] Perform color space transformation on the imag...

Embodiment 2

[0053] see figure 2 , an embodiment of the present invention provides a method for obtaining a boundary of a scene, the method comprising:

[0054] 201: Perform color space transformation on the image to obtain multiple single-channel grayscale information.

[0055] Wherein, the image is the received image from which the boundary of the scene needs to be extracted, and may be various images such as a color image and a grayscale image. And an image is generally a combination of information of multiple channels, for example, an image is a combination of information of three channels R (Red, red), G (Green, green), and B (Blue, blue). By performing color space transformation on the image, the gray values ​​under each single channel such as R, G, B, X, Y, Z, H (Hue, hue), S (saturation, saturation) and V (value, lightness) can be obtained. For ease of description, the grayscale information under a single channel is called single-channel grayscale information, that is, the singl...

Embodiment 3

[0092] see image 3 , an embodiment of the present invention provides a device for acquiring a scene boundary, the device comprising:

[0093] The first acquiring module 301 is configured to acquire discrete boundary points of each single-channel grayscale information in a plurality of single-channel grayscale information of the image;

[0094] The second acquisition module 302 is configured to acquire a plurality of key points on the boundary of the scene, and arrange the plurality of key points in order;

[0095] The search module 303 is used to search and obtain the effective boundary between every two adjacent key points by using the shortest path search algorithm according to the discrete boundary points of each single-channel grayscale information obtained by the first acquisition module 301;

[0096] The connection module 304 is configured to connect the effective boundaries between every two adjacent key points after the search module 303 obtains the effective boundar...

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 invention discloses a method and a device for obtaining scene boundary, and belongs to the field of computer multimedia. The method comprises the steps of obtaining divergent boundary points of each piece of single-channel gray information of multiple pieces of single-channel gray information of an image; obtaining multiple key points at the scene boundary and arranging the multiple key points according to sequence; searching to obtain the effective boundary between two adjacent key points using a shortest path search algorithm according to the divergent boundary point of each piece of single-channel gray information; and connecting the effective boundary between two adjacent key points to obtain the boundary of the scene. The device comprises a first obtaining module, a second obtaining module, a searching module and a connecting module. The invention avoids the wrong segmentation phenomenon caused by complex scene texture by comprehensively utilising multiple pieces of single-channel scene boundary information and setting the key points, improves accuracy for obtaining the scene boundary, improves the efficiency for obtaining the scene boundary and can save lots of time. Thehuman intervention in the process of obtaining the scene boundary is low.

Description

technical field [0001] The invention relates to the field of computer multimedia, in particular to a method and device for acquiring the boundary of a scene. Background technique [0002] With the development of computer multimedia, converting flat video to stereoscopic video has received extensive attention and attention. The key to converting a planar video into a stereoscopic video is the extraction of the depth map. Since the scene and the background in the image have different depths, when generating the depth map, it is often necessary to obtain the scene boundary first, separate the scene from the background, and then Depth values ​​are assigned to the scene and background respectively to generate a depth map. [0003] In the prior art, there are mainly two methods for obtaining the scene boundary: [0004] 1) Use Photoshop and other drawing software to manually extract the scene on the image to obtain the scene boundary. [0005] 2) Segment the image through the 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
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/00G06T7/136
Inventor 戴琼海邓岳谢鹏
Owner TSINGHUA UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products