• The Journal of the Acoustical Society of Korea
• /
• v.25 no.4
• /
• pp.184-190
• /
• 2006

Recently, Lee et al. have proposed an algorithm utilizing the signals from different paths by using bottom mounted simple linear array to estimate 3-D location of oceanic target. But this algorithm assumes that sound velocity is constant along depth of sea. Consequently, serious performance loss is appeared in real oceanic environment that sound speed is changed variously. In this paper, we present a 3-D near field localization algorithm for inhomogeneous sound speed. The proposed algorithm adopt localization function that utilize ray propagation model for multipath environment with linear sound speed profile(SSP), after that, the proposed algorithm searches for the instantaneous azimuth angle, range and depth from the localization cost function. Several simulations using linear SSP and non linear SSP similar to that of real oceans are used to demonstrate the performance of the proposed algorithm. The estimation error in range and depth is decreased by 100m and 50m respectively.

• Journal of Digital Contents Society
• /
• v.13 no.2
• /
• pp.255-262
• /
• 2012

Human motion tracking algorithm is receiving attention from many research areas, such as human computer interaction, video conference, surveillance analysis, and game or entertainment applications. Over the last decade, various tracking technologies for each application have been demonstrated and refined among them such of real time computer vision and image processing, advanced man-machine interface, and so on. In this paper, we introduce cost-effective and real-time human motion tracking algorithms based on depth image 3D point matching with a given superellipsoid body representation. The body representative model is made by using parametric volume modeling method based on superellipsoid and consists of 18 articulated joints. For more accurate estimation, we exploit initial inverse kinematic solution with classified body parts' information, and then, the initial pose is modified to more accurate pose by using 3D point matching algorithm.

• The KIPS Transactions:PartB
• /
• v.10B no.2
• /
• pp.157-162
• /
• 2003

In this paper, in-depth considerations are given to various techniques suggested for photographic 3D modelling and possible enhancements of the techniques are discussed. It is found that both the improvement of fundamental matrix estimation techniques and the stereo image rectification processing stage are necessary for more accurate 3D modelling.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.4
• /
• pp.674-679
• /
• 2006

In this paper a gesture recognition system using 3D feature data is described. The system relies on a novel 3D sensor that generates a dense range mage of the scene. The main novelty of the proposed system, with respect to other 3D gesture recognition techniques, is the capability for robust recognition of complex hand postures such as those encountered in sign language alphabets. This is achieved by explicitly employing 3D hand features. Moreover, the proposed approach does not rely on colour information, and guarantees robust segmentation of the hand under various illumination conditions, and content of the scene. Several novel 3D image analysis algorithms are presented covering the complete processing chain: 3D image acquisition, arm segmentation, hand -forearm segmentation, hand pose estimation, 3D feature extraction, and gesture classification. The proposed system is tested in an application scenario involving the recognition of sign-language postures.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.3
• /
• pp.384-390
• /
• 2020

The reverberation effect on the sound when producing movies or VR contents is a very important factor in the realism and liveliness. The reverberation time depending the space is recommended in a standard called RT60(Reverberation Time 60 dB). In this paper, we propose a scene recognition technique for automatic reverberation editing. To this end, we devised a classification model that independently trains color images and predicted depth images in the same model. Indoor scene classification is limited only by training color information because of the similarity of internal structure. Deep learning based depth information extraction technology is used to use spatial depth information. Based on RT60, 10 scene classes were constructed and model training and evaluation were conducted. Finally, the proposed SCR + DNet (Scene Classification for Reverb + Depth Net) classifier achieves higher performance than conventional CNN classifiers with 92.4% accuracy.

• Geotechnical Engineering
• /
• v.14 no.5
• /
• pp.143-162
• /
• 1998

In the present study, a procedure to predict the depth from the ground surface to the center of bulging failure zone in each of the square granular group piles under a rigid mat foundation is proposed. This analytical procedure is established on the basis of the conical modeling of bulging failure shape and the replacement ratio of soft foundation soils. considering the effect of a share of procedure to estimate the ultimate cylindrical pressure in the area reinforced with granular piles and the ultimate bearing capacity of each of granular piles in group. This analytical procedure is also established on the basis of the pre-determined depth to the zone of bulging failure and an iterative solution technique. Finally the analytical procedures proposed in this study are verified by analyzing the results of 3D finite element analyses, and the predictions of ultimate bearing capacity of granular piles are compared with the results obtained from the tests, empirical equation and 3D finite element analyses.

• Geomechanics and Engineering
• /
• v.31 no.3
• /
• pp.305-318
• /
• 2022

Permeable reactive barriers used for groundwater treatment require proper estimation of the reactive material behavior regarding the emplacement method. This study evaluates the dry emplacement of zeolite (clinoptilolite) to be used as a reactive material in the barrier by carrying out several geotechnical laboratory tests. Dry zeolite samples, exhibited higher wetting-induced compression strains at the higher vertical stresses, up to 12% at 400 kN/m². The swelling potential was observed to be limited with a 3.5 swell index and less than 1% free swelling strain. Direct shear tests revealed that inundation reduces the shear strength of a dry zeolite column by a maximum of 10%. Falling head permeability tests indicate decreasing permeability values with increasing the vertical effective stress. Regarding self-loading and inundation, the porosity along the zeolite column was calculated using a proposed 1D numerical model to predict the permeability with depth considering the laboratory tests. The calculated discharge efficiency was significantly decreased with depth and less than 2% relative to the top for barrier depths deeper than 20 m. Finally, the importance of directional dependence in the permeability of the zeolite medium for calibrating 2D finite element flow analysis was highlighted by bench-scale tests performed under 2D flow conditions.

• Proceedings of the IEEK Conference
• /
• 2000.11d
• /
• pp.167-170
• /
• 2000

In this paper, we present a fast algorithm for the motion estimation using the efficient selection of an initial search position. In the method, we select the initial search position using the motion vector from the subsmpled images, the predicted motion vector from the neighbor blocks, and the (0,0) motion vector. While searching the candidate blocks, we use the spiral search pattern with the successive elimination algorithm(SEA) and the partial distortion elimination(PDE). The experiment results show that the complexity of the proposed algorithm is about 2∼3 times faster than the three-step search(TSS) with the PSNR loss of just 0.05［dB］∼0.1［dB］ than the full search algorithm PSNR. The search complexity can be reduced with quite a few PSNR loss by controling the number of the depth in the spiral search pattern.

• Proceedings of the IEEK Conference
• /
• 2002.07c
• /
• pp.1404-1407
• /
• 2002

Although we look at objects as 2D images through our eyes, we can reconstruct the shape and/or depth of objects. In order to realize this ability using computers, it is required that the method which can estimate the 3D features of object from 2D images. As feature which represents 3D shapes effectively, three dimensional vector autoregressive model is pro- posed. If this feature is associated other feature of 2D shape, then above aim might be achieved. On the other hand, as feature which represents 2D shapes, quasi moment features is proposed. As the first step of association of these features, we constructed real time simulator that computes both of two features concurrently from object data (3D curves) . This simulator can also rotate object and estimate the rotation The method using 3D VAR model estimates the rotation correctly, but the estimation by quasi moment features includes much errors. This reason would be that projected images are constructed by the points only, and doesn't have enough sizes to estimate the correct 3D rotation parameters.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.826-829
• /
• 2024

3D 사람 자세 추정 기술은 다양한 응용 분야에서의 높은 활용성으로 인해 대량의 학습 데이터가 수집되어 딥러닝 모델 연구가 진행되어 온 반면, 동물 자세 추정의 경우 3D 동물 데이터의 부족으로 인해 관련 연구는 극히 미진하다. 본 연구는 동물 자세 추정을 위한 예비연구로서, 3D 학습 데이터가 없는 상황에서 단일 이미지로부터 3D 사람 자세를 추정하는 딥러닝 기법을 제안한다. 이를 위하여 사전 훈련된 다중 시점 학습모델을 사용하여 2D 자세 데이터로부터 가상의 다중 시점 데이터를 생성하여 훈련하는 연역적 학습 기반 교사-학생 모델을 구성하였다. 또한, 키포인트 깊이 정보 대신 2D 이미지로부터 레이블링 된 순서 깊이 정보에 기반한 손실함수를 적용하였다. 제안된 모델이 동물데이터에서 적용 가능한지 평가하기 위해 실험은 사람 데이터를 사용하여 이루어졌다. 실험 결과는 제안된 방법이 기존 단안 이미지 기반 모델보다 3D 자세 추정의 성능을 개선함을 보여준다.