Depth information generating device, depth information generating method, and stereo image converter

A technology of information generation and depth map, which is applied in image enhancement, image analysis, stereo system, etc. It can solve the problems of flickering between frames, non-disclosure and hints, incongruous sense of viewers, etc., and achieve low real-time action, less memory, The effect of low memory

Active Publication Date: 2012-09-26
秉熙富策有限公司
View PDF7 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0017] Next, in the method disclosed in Patent Document 3, objects such as people are recognized as foreground images, but in time-series images (videos), objects are not necessarily recognized as foreground images, so there are occurrence frames flickering problem
In addition, in order to avoid this flickering, a time-series smoothing method of the depth map is required, but there is no disclosure or suggestion of this technology in Patent Document 3.
[0018] Finally, in the SFM method, which is another known method, there is a problem that a 3D object cannot be created in a still image or a part with relatively no motion.
[0019] In this way, when converting a 2D image into a 3D image using the depth map generated by the above-mentioned conventional method, there is a problem that the 3D pop-up effect is insufficient and the viewer feels uncomfortable.

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
  • Depth information generating device, depth information generating method, and stereo image converter
  • Depth information generating device, depth information generating method, and stereo image converter
  • Depth information generating device, depth information generating method, and stereo image converter

Examples

Experimental program
Comparison scheme
Effect test

Deformed example 1

[0212] In the above-described embodiment, the description has been made assuming that the area extraction unit 10 extracts the person area, but the present invention is not limited thereto. As long as it can be detected statistically, it is not limited to persons. For example, objects detectable by a computer including cats, dogs, birds, and food may be extracted as attention objects instead of person areas.

[0213] In this case, specifically, the following configurations are sufficient. That is, as long as the area extracting unit 10 includes an object area detecting unit, a temporary area setting unit, and an area determining unit, and detects an object area that is a statistically detectable area among objects of interest from a two-dimensional image, based on the detection The object region of interest within the region of the two-dimensional image may be extracted from the obtained object region.

[0214] Here, the object area detecting unit detects an object area in t...

Deformed example 2)

[0219] In the above-mentioned embodiment, it is assumed that the area extracting unit 10 detects the face of a person from the input two-dimensional image or the two-dimensional image constituting the input video, and extracts the person in the area representing the two-dimensional image based on the detected face. The character area has been described, but it is not limited to this.

[0220] Such as Figure 19 ~ Figure 21 As shown, in order to optimize the speed at which the area extracting unit 10 detects target areas such as faces, that is, the detection speed, the input 2D image or the 2D images constituting the input video may be down-sampled.

[0221] here, Figure 19 ~ Figure 21 It is a flowchart for explaining the outline of the processing of the depth information generating device according to Modification 2 of the embodiment of the present invention. Additionally, for figure 2 The same elements are given the same symbols, and detailed descriptions are omitted.

...

Deformed example 3)

[0231] In the above-described embodiment, first, the region extracting unit 10 recognizes the person region and the region (background) other than the person region of the two-dimensional image using color information such as a color histogram. Next, it was described that a depth map is generated by assigning different depth values ​​to the recognized person area and the background, but the present invention is not limited thereto. The depth values ​​assigned to the background and person regions may be changed according to the characteristics of the regions, so that the 3D pop-up effect (depth perception) of the background or person regions can be further improved.

[0232] Figure 22 It is a diagram showing an example of a process of extracting a person area and a background of a two-dimensional image and dividing it into different layers based on color information.

[0233] A depth value added to increase the depth of an object of interest separated from a plane representin...

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

A depth information generator of the present invention is provided with: a region extraction unit (10) which detects the face of a person from a 2D image, and based on the detected face extracts a person region that indicates a person within a region of the 2D image; and a depth map generator (11) which generates a depth map for separating the person region and regions other than the person region by providing the extracted person region with a depth value different from the depth values of the regions other than the person region. As a result, a depth map can be generated for displaying a 3D pop-out which is not incongruous to the viewer.

Description

technical field [0001] The present invention relates to a depth information generation device, a depth information generation method and a stereoscopic image conversion device, in particular to a depth information generation device, a depth information generation method and a stereoscopic image conversion device for generating a depth map from a two-dimensional image. Background technique [0002] There is known a method of generating depth information (hereinafter, referred to as a depth map) in a two-dimensional image (2D image), and converting a stereo pair (left-eye image and right-eye image) corresponding to the 2D image using the generated depth map. Synthesis is performed to transform a 2D image into a three-dimensional image (3D image). [0003] For example, Patent Document 1 discloses a method of creating a 3D image based on a 2D image including parallax information. Specifically, in Patent Document 2, a 2D image is input, an image of a person's face is extracted f...

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): G06T1/00H04N13/02
CPCG06K9/00362H04N13/02G06T7/0081G06T1/00G06T7/0051G06T2207/30201G06T2207/10024G06T2207/20104G06T2207/30196G06T7/50G06T7/11G06T7/187G06T7/194H04N13/128H04N13/261G06V40/10
Inventor 山田整T·图马农塔瓦特P·拉桑申省梅
Owner 秉熙富策有限公司
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