Image segmentation method and device

An image segmentation and color image technology, applied in the field of image processing, can solve problems such as the inability to achieve high-precision object segmentation, and achieve the effects of improving object segmentation, reducing ambiguity, and ensuring integrity

Inactive Publication Date: 2014-10-22
HISENSE VISUAL TECH CO LTD
View PDF3 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For the above scenarios, object segmentation through color images cannot achieve high-precision object segmentation

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
  • Image segmentation method and device
  • Image segmentation method and device
  • Image segmentation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] like figure 1 As shown, a flow chart of an image segmentation method provided by Embodiment 1 of the present invention includes the following steps:

[0049] Step 101, segmenting the color image to obtain segmented object blocks in the color image;

[0050] Step 102. Determine the depth value of the segmented object block according to the depth image;

[0051] Step 103, when the segmented object blocks with the same depth value satisfy the set condition in the depth image and the color image, merge the segmented object blocks with the same depth value to obtain an object with a depth value.

[0052] Figure 2A Represents a red, green, blue or RGB image of an example scene captured by a visible light camera device, wherein each image element represents a visible light color value (for example, RGB intensity) for that point of the image, and in this embodiment, it is represented by a bar line Colors in color images. In the figure, the colors of each teapot are differe...

Embodiment 2

[0078] In actual operation, when the same object in the same scene is segmented, each object can be projected as a whole to form a new viewpoint. like image 3 As shown, a viewpoint generation method provided by an embodiment of the present invention includes the following steps:

[0079] Step 201, acquiring the depth value of each object in the depth image, and dividing each object into a foreground object and a background object according to the relationship between the depth value of each object and the depth value of the focus layer in the depth image;

[0080] Step 202, projecting the foreground object and the background object respectively as a whole to obtain a reference viewpoint;

[0081] Step 203, the increase value of the depth value of the foreground object after projection is greater than the increase value of the depth value of the background object after projection, and the position offset of the foreground object after projection is greater than the position o...

Embodiment 3

[0178] Embodiment 3 of the present invention provides a 3D projection method, such as Figure 7 shown, including the following steps:

[0179] Step 301, input image;

[0180] Step 302, judging whether the input book is a 3D virtual image, if it is a 3D virtual image, then directly execute step 310, otherwise, execute step 303;

[0181] Step 303, the image captured by the camera includes a 2D image of a color image and a depth image; the color image is executed according to step 304, and the depth image is executed according to step 307;

[0182] Step 304, obtain a color image;

[0183] Step 305, pre-segmenting the color image;

[0184] Step 306, marking each segmented object block in the pre-segmented color image;

[0185] Step 307, obtaining a depth image;

[0186] Step 308, pre-segmenting the depth image;

[0187] Step 309, marking each segmented object block in the segmented depth image;

[0188] Step 310, combining the relationship between the segmented object block...

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 an image segmentation method and device. The image segmentation method and device are used for solving the problem that the prior art is difficult to confirm whether objects in the same scene belongs to the same object. The image segmentation method includes that carrying out pre-segmentation treatment on a colored image, and confirming all the segmented object blocks in the colored image; confirming the depth value of each segmented object block according to a depth image which is located in the same scene with the colored image; confirming the segmented object blocks with the same depth value in the segmented object blocks; when the positions of the segmented object blocks with the same depth value in the depth image meet a set condition, confirming that the segmented object blocks with the same depth value belong to the same object. The image segmentation method is capable of improving the precision of a colored image object segmentation method.

Description

technical field [0001] The present invention relates to the field of image processing, and more specifically relates to an image segmentation method and device. Background technique [0002] An image often contains many different types of objects, such as pedestrians, vehicles, traffic signs, etc. in a road environment, or objects such as tables, stools, and computers in an office environment. In the field of image processing, high-precision object segmentation for images is of great help to object analysis and subsequent processing. [0003] In the existing image segmentation methods, the color difference of different objects is usually utilized, and the segmentation is performed according to the color image. However, the same object often has different colors. According to the segmentation method of the color image, the same object is divided into different object blocks. For example, if a person's face and hair are of different colors, the face and hair will be separated...

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): G06T7/00
Inventor 骆俊谕高语函陈辉高维嵩张钦泉
Owner HISENSE VISUAL TECH CO LTD
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap