公开(公告)号：US20150304617A1

公开(公告)日：2015-10-22

申请号：US14688982

申请日：2015-04-16

Applicant: Electronics and Telecommunications Research Institute

Inventor： Ji Ho CHANG ,  Dae Hwan HWANG ,  Kwang Ho YANG ,  Eul Gyoon LIM ,  Jae IL CHO

IPC: H04N9/31 ,  H04N17/00

CPC classification number: H04N9/3191 ,  G06T7/80 ,  G06T2207/10012 ,  G06T2207/10028 ,  H04N9/3185 ,  H04N13/246 ,  H04N13/254 ,  H04N17/004

Abstract: Disclosed are a system and method for performing distortion correction and calibration using a pattern projected by a projector. The system for performing distortion correction and calibration includes a projector that projects a pattern, at least one camera that generates a photographed pattern image by photographing an image onto which the pattern is projected, and an image processing device that calculates a calibration parameter by comparing an original pattern image projected by the projector and the photographed pattern image. Thus, it is possible to obtain an accurate depth image by easily utilizing an image for the pattern projected by the projector. In addition, when obtaining the depth image, the calibration parameter for correcting image distortion according to camera lens and a calibration state of cameras may be efficiently obtained using the pattern projected by the projector.

Abstract translation: 公开了一种使用由投影仪投射的图案进行失真校正和校准的系统和方法。 用于执行失真校正和校准的系统包括投影图案的投影仪，通过拍摄投影了图案的图像来生成拍摄图案图像的至少一个照相机，以及通过将图像进行比较来计算校准参数的图像处理装置 由投影仪投射的原始图案图像和拍摄的图案图像。 因此，可以通过容易地利用投影仪投射的图案的图像来获得准确的深度图像。 此外，当获得深度图像时，可以使用由投影仪投射的图案有效地获得用于根据相机透镜校正图像失真的校准参数和照相机的校准状态。

公开(公告)号：US20160037121A1

公开(公告)日：2016-02-04

申请号：US14811070

申请日：2015-07-28

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Ji Ho CHANG ,  Jae Chan JEONG ,  Ho Chul SHIN ,  Dae Hwan HWANG ,  Seung Min CHOI ,  Eul Gyoon LIM ,  Jae IL CHO ,  Kuk Jin YOON

IPC: H04N5/911 ,  H04N13/02

CPC classification number: H04N5/911 ,  G06T7/521 ,  G06T7/593 ,  G06T2207/10012 ,  G06T2207/10152 ,  H04N13/239 ,  H04N13/254 ,  H04N2013/0081

Abstract: There are provided a stereo matching method capable of increasing a resolution and precision of an object and a device for performing the method. The method includes investigating a pattern according to a predetermined period; obtaining left and right stereo images in which the investigated pattern is included or not included; determining whether each of the stereo image obtained according to the predetermined period and a buffering image that is a previous frame image of the stereo image includes the pattern; and generating a final cost volume by performing different image processing according to whether each of the stereo image and the buffering image includes the pattern. Therefore, it is possible to increase precision of a disparity of a thin object and increase accuracy and precision of an object at a long distance.

Abstract translation: 提供了能够提高对象的分辨率和精度的立体匹配方法以及用于执行该方法的装置。 该方法包括根据预定时段调查模式; 获得其中包括或不包括所研究图案的左和右立体图像; 确定根据预定周期获得的每个立体图像和作为立体图像的先前帧图像的缓冲图像是否包括图案; 以及通过根据每个立体图像和缓冲图像是否包括图案执行不同的图像处理来生成最终成本量。 因此，可以提高薄物体的视差的精度并提高物体在远距离处的精度和精度。

公开(公告)号：US20140219549A1

公开(公告)日：2014-08-07

申请号：US14021956

申请日：2013-09-09

Applicant: Electronics and Telecommunications Research Institute

Inventor： Seung Min CHOI ,  Dae Hwan HWANG ,  Eul Gyoon LIM ,  HoChul SHIN ,  Jae-Chan JEONG ,  Jae IL CHO ,  Kwang Ho YANG ,  Jiho CHANG

IPC: G06T7/00

CPC classification number: G06T7/593

Abstract: An active stereo matching method includes extracting a pattern from a stereo image, generating a depth map through a stereo matching using the extracted pattern, calculating an aggregated cost for a corresponding disparity using a window kernel generated using the extracted pattern and a cost volume generated for the stereo image, and generating a disparity map using the depth map and the aggregated cost.

Abstract translation: 主动立体匹配方法包括从立体图像提取图案，通过使用提取的图案的立体匹配产生深度图，使用使用提取的图案生成的窗口内核计算相应视差的聚合成本，以及为 立体图像，并使用深度图和聚合成本生成视差图。