• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2006.04a
• /
• pp.165-169
• /
• 2006

Purpose of this research is estimation of water depth by hyperspectral remote sensing in area that access of ship is difficult This research used EO-1 Hyperion satellite imagery. Atmospheric and geometric correction is executed. Compress of band used MNF transforms. Diffuse Attenuation Coefficient of target area is decided in imagery for water depth estimation. Determination of Emdmember in pixel is using Linear Spectral Unmixing techniques. Water depth estimated using this result.

• IEIE Transactions on Smart Processing and Computing
• /
• v.3 no.6
• /
• pp.382-387
• /
• 2014

A computational approach to depth estimations using a color over lapped integral imaging system is presented. The proposed imaging system acquires multiple color images simultaneously through a single lens with an array of multiple pinholes that are distributed around the optical axis. This paper proposes a computational model of the relationship between the real distance of an object and the disparity among different color images. The proposed model can serve as a computational basis of a single camera-based depth estimation.

• Aerospace Engineering and Technology
• /
• v.7 no.1
• /
• pp.216-222
• /
• 2008

Purpose of this research is estimation of water depth by hyperspectral remote sensing in area that access of ship is difficult. This research used EO-l Hyperion satellite imagery. Atmospheric and geometric correction is executed. Compress of band used MNF transforms. Diffuse Attenuation Coefficient of target area is decided in imagery for water depth estimation. Determination of Emdmember in pixel is using Linear Spectral Unmixing techniques. Water depth estimated using this result.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.01a
• /
• pp.277-278
• /
• 2021

최근 손동작 인식에 대한 연구들이 활발하다. 하지만 대부분 Depth 정보를 포함한3D 정보를 필요로 한다. 이는 기존 연구들이 Depth 카메라 없이는 동작하지 않는다는 한계점이 있다는 것을 의미한다. 본 프로젝트는 Depth 카메라를 사용하지 않고 2D 이미지에서 Hand Keypoint Detection을 통해 손동작 인식을 하는 방법론을 제안한다. 학습 데이터 셋으로 Facebook에서 제공하는 InterHand2.6M 데이터셋[1]을 사용한다. 제안 방법은 크게 두 단계로 진행된다. 첫째로, Object Detection으로 Hand Detection을 수행한다. 데이터 셋이 어두운 배경에서 촬영되어 실 사용 환경에서 Detection 성능이 나오지 않는 점을 해결하기 위한 이미지 합성 Augmentation 기법을 제안한다. 둘째로, Keypoint Detection으로 21개의 Hand Keypoint들을 얻는다. 실험을 통해 유의미한 벡터들을 생성한 뒤 Annoy (Approximate nearest neighbors Oh Yeah) Tree를 생성한다. 생성된 Annoy Tree들로 후처리 작업을 거친 뒤 최종 Pose Estimation을 완료한다. Annoy Tree를 사용한 Pose Estimation에서는 NN(Neural Network)을 사용한 것보다 빠르며 동등한 성능을 냈다.

• Korean Journal of Materials Research
• /
• v.12 no.8
• /
• pp.682-687
• /
• 2002

The three-dimensional estimation on the depth and height of flaw by using the difference of radiographic contrast density was studied. First, the specimens having artificial flaws of various depths and heights were prepared and the radiographic testing was performed. The radiographic depth of flaw was investigated and estimated on the effect of the scattered radiation with the change of distance between flaw and film. The height of flaw was estimated from the radiographic test with the reference specimen. The radiographic contrast with flaw depth decreased with increasing the flaw depth. The scattered radiation increased with increasing flaw depth and varied with the location between flaw and film. However, in the case of flaw height, the contrast density increased with increasing flaw height. It is thought due to the change in volume generating the scattered radiation which reaches a film.

• Journal of Korea Multimedia Society
• /
• v.20 no.7
• /
• pp.1014-1023
• /
• 2017

In this paper, we propose a method for estimating the human height by using downward depth images. We detect a point with the lowest depth value in an object as top of the head and estimate the height by calculating the depth difference with the floor. Since the depth of the floor varies depending on the angle of the camera, the correction formula is applied. In addition, the binarization threshold is variably applied so that height can be estimated even when several people are adjacent. Simulation results show that the proposed method has better performance than the conventional methods. The proposed method is expected to be widely used in body measurement, intelligent surveillance, and marketing.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.583-587
• /
• 2009

In this paper we propose a new method of Depth-Image-Based Rendering (DIBR) for Free-viewpoint TV (FTV). In the proposed method, virtual viewpoint images are rendered with 3D warping instead of estimating the view-dependent depth since depth estimation is usually costly and it is desirable to eliminate it from the rendering process. However, 3D warping causes some problems that do not occur in the method with view-dependent depth estimation; for example, the appearance of holes on the rendered image, and the occurrence of depth discontinuity on the surface of the object at virtual image plane. Depth discontinuity causes artifacts on the rendered image. In this paper, these problems are solved by reconstructing disparity information at virtual camera position from neighboring two real cameras. In the experiments, high quality arbitrary viewpoint images were obtained.

• Journal of Information Processing Systems
• /
• v.19 no.4
• /
• pp.483-497
• /
• 2023

Depth estimation is one of the most complicated and difficult problems to deal with in the light field. In this paper, a compound attention convolutional neural network (CAttNet) is proposed to extract depth maps from light field images. To make more effective use of the sub-aperture images (SAIs) of light field and reduce the redundancy in SAIs, we use a compound attention mechanism to weigh the channel and space of the feature map after extracting the primary features, so it can more efficiently select the required view and the important area within the view. We modified various layers of feature extraction to make it more efficient and useful to extract features without adding parameters. By exploring the characteristics of light field, we increased the network depth and optimized the network structure to reduce the adverse impact of this change. CAttNet can efficiently utilize different SAIs correlations and features to generate a high-quality light field depth map. The experimental results show that CAttNet has advantages in both accuracy and time.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.1
• /
• pp.78-84
• /
• 2015

Depth estimation is often required for robot vision, 3D modeling, and motion control. Previous method is based on the focus measures which are calculated for a series of image by a single camera at different distance between and object. This method, however, has disadvantage of taking a long time for calculating the focus measure since the mask operation is performed for every pixel in the image. In this paper, we estimates the depth by using the focus measure of the boundary pixels located between the objects in order to minimize the depth estimate time. To detect the boundary of an object consisting of a straight line and a circle, we use the Hough transform and estimate the depth by using the focus measure. We performed various experiments for PCB images and obtained more effective depth estimation results than previous ones.

• Proceedings of the KIEE Conference
• /
• 1989.11a
• /
• pp.484-487
• /
• 1989

A fast stereo algorithm for 3D depth estimation is presented. We propose an on-line stereo matching technique, by which the flows of stereo image signals are dynamically controlled to satisfy the matching condition of intensity functionals. The disparity is rapidly estimated from the control of. the signal flows and 3D depth is determined from the disparity.