• Smart Media Journal
• /
• v.7 no.1
• /
• pp.31-36
• /
• 2018

In this paper, we propose automatic screen on / off method of OST-HMD screen using gaze depth estimation technique. The proposed method uses MLP (Multi-layer Perceptron) to learn the user's gaze information and the corresponding distance of the object, and inputs the gaze information to estimate the distance. In the learning phase, eye-related features obtained using a wearable eye-tracker. These features are then entered into the Multi-layer Perceptron (MLP) for learning and model generation. In the inference step, eye - related features obtained from the eye tracker in real time input to the MLP to obtain the estimated depth value. Finally, we use the results of this calculation to determine whether to turn the display of the HMD on or off. A prototype was implemented and experiments were conducted to evaluate the feasibility of the proposed method.

• Journal of Digital Convergence
• /
• v.11 no.7
• /
• pp.157-163
• /
• 2013

In this paper, we propose a vision and depth information based real-time hand gesture interface method using finger joint estimation. For this, the areas of left and right hands are segmented after mapping of the visual image and depth information image, and labeling and boundary noise removal is performed. Then, the centroid point and rotation angle of each hand area are calculated. Afterwards, a circle is expanded at following pattern from a centroid point of the hand to detect joint points and end points of the finger by obtaining the midway points of the hand boundary crossing and the hand model is recognized. Experimental results that our method enabled fingertip distinction and recognized various hand gestures fast and accurately. As a result of the experiment on various hand poses with the hidden fingers using both hands, the accuracy showed over 90% and the performance indicated over 25 fps. The proposed method can be used as a without contacts input interface in HCI control, education, and game applications.

• The KIPS Transactions:PartB
• /
• v.18B no.1
• /
• pp.21-28
• /
• 2011

A 3D face shape derived from 2D images may be useful in many applications, such as face recognition, face synthesis and human computer interaction. To do this, we develop a fast 3D Active Appearance Model (3D-AAM) method using depth estimation. The training images include specific 3D face poses which are extremely different from one another. The landmark's depth information of landmarks is estimated from the training image sequence by using the approximated Jacobian matrix. It is added at the test phase to deal with the 3D pose variations of the input face. Our experimental results show that the proposed method can efficiently fit the face shape, including the variations of facial expressions and 3D pose variations, better than the typical AAM, and can estimate accurate 3D face shape from images.

• Korean Journal of Community Nutrition
• /
• v.23 no.3
• /
• pp.202-215
• /
• 2018

Objectives: We conducted a qualitative study to explore the feasibility of mobile applications for self-monitoring of diet. Methods: We conducted in-depth and focus group interviews with eight laymen who had used mobile dietary applications and eight experts. Interviews were audio-recorded and analyzed using an open coding method. Results: The qualitative data of our study revealed two key themes: (1) perceptions, opinions and attitudes towards mobile applications of self-monitoring of diet and (2) future directions to improve mobile applications. Conclusions: Our qualitative study suggested the potential use of mobile applications as a food-tracking and dietary monitoring tool and the need for improved mobile applications for self-monitoring of diet. The results of our study may provide insights into how to technically improve mobile applications for self-monitoring of diet, how to utilize dietary data generated through mobile applications, and how to improve individual's health though mobile applications.

• Journal of Broadcast Engineering
• /
• v.17 no.4
• /
• pp.611-624
• /
• 2012

'Gesture' is the most intuitive means of communication except the voice. Therefore, there are many researches for method that controls computer using gesture input to replace the keyboard or mouse. In these researches, the method of user detection and main body parts estimation is one of the very important process. in this paper, we propose user objects detection and main body parts estimation method on inaccurate depth information for pose estimation. we present user detection method using 2D and 3D depth information, so this method robust to changes in lighting and noise and 2D signal processing 1D signals, so mainly suitable for real-time and using the previous object information, so more accurate and robust. Also, we present main body parts estimation method using 2D contour information, 3D depth information, and tracking. The result of an experiment, proposed user detection method is more robust than only using 2D information method and exactly detect object on inaccurate depth information. Also, proposed main body parts estimation method overcome the disadvantage that can't detect main body parts in occlusion area only using 2D contour information and sensitive to changes in illumination or environment using color information.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.25 no.5
• /
• pp.589-600
• /
• 2019

In order to investigate the flow structures around Geumo archipelago on Southern Waters of Korea, water movements were measured for 25 hours during spring tide in May and neap tide in September 2002 using ADCP (Acoustic Doppler Current Profiler) attached to a running boat. Dominant directions of ebb and flood current at spring tide are SE-NW, representing the average flow rate of approximately 40cm/s in the surface layer. However because of the topographical reason, the direction and speed of the flow in the narrow waterway sea area around the northwest of Gae Island were different. There was no notable baroclinic component of tidal flow at spring tide. This indicates that the sea area has been actively engaged in vertical mixing due to island wake or eddy due to narrow waterways, shallow water depth and rapid flow rate around archipelago. At neap tide, dominant directions of tidal flows are SSE-NNW and the average flow rate in the surface layer is about 85 percent of the spring tide. The duration and intensity of the flow direction are shorter and less dominant than the spring tide. It is expected that asymmetrical tidal mixing will occur due to vertical velocity shear and horizontal eddies. From daily mean tidal flows obtained from the ADCP observation, it was found that the northwest of Gae Island have flows in NW~NE, the west of Geumo Island have the average currents of up to 21 cm/s WSW~SSW and counterclockwise circulation or eddy currents are formed in the west of Sori Island.

• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.12
• /
• pp.84-91
• /
• 2004

A CCD camera with a laser stripe was applied to realize the automatic weld seam tracking in GMAW. It takes relatively long time to process image on-line control using the basic Hough transformation, but it has a tendency of robustness over the noises such as spatter and arc tight. For this reason, it was complemented with adaptive Hough transformation to have an on-line processing ability for scanning specific weld points. The adaptive Hough transformation was used to extract laser stripes and to obtain specific weld points. The 3-dimensional information obtained from the vision system made it possible to generate the weld torch path and to obtain the information such as width and depth of weld line. In this study, a neural network based on the generalized delta rule algorithm was adapted for the process control of GMA, such as welding speed, arc voltage and wire feeding speed.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2013.06a
• /
• pp.284-285
• /
• 2013

Kinect를 통해 Color영상과 Depth영상을 받아온 후, 사람과 사람의 스켈레톤이 검출되도록 했다. 스켈레톤이 검출되면 머리 위치를 중심으로 얼굴 유효영역을 만들고, 효율적인 얼굴 검출로 사용자 인식이 가능하도록 했다. 스켈레톤 검출 및 추적을 통해, 4가지 감정에 대해 제스쳐를 정의했으며, 각 감정에 따른 제스쳐를 취했을 때 정의한 감정이 인식되는지 실험했다. 실험 결과, 제스쳐를 통한 감정 인식 성공률이 86~88% 나왔으며, 이 제스쳐 인식이 다른 감정인식 방법과 융합될 필요가 있다.

• Proceedings of the KIEE Conference
• /
• 2006.07d
• /
• pp.1933-1934
• /
• 2006

이 논문은 비강체 객체에 대한 실시간 추적시 다른 객체에 의한 간섭의 영향을 줄이는 방법을 제시한다. 제시한 방법에서 객체 추적에 대한 알고리즘은 현재 프레임에서 확률적으로 목표의 위치를 찾는 Mean shift 방법에 기초를 두고 있다. 기존의 방법에서는 mean shift 의 파라미터로서 색분포만 사용한다. 하나의 파라미터에만 의존하므로 같은 색분포를 갖는 다른 객체가 추적 영역 내에 들어오게 되면 새로운 객체를 기존 객체로 인식하게 되는 문제가 발생한다. 여기서 우리는 강인한 객체추적을 하기 위해 다른 하나의 파라미터로서 거리정보를 이용을 제안한다. 거리정보에 최적화된 흐름 추정(optical flow estimation)방법을 확장 도입한 강인한 에러 기준(robust error norm) 방법을 사용하여 기존의 객체에게 더 많은 가중치를 주는 방식으로 mean shift 추적 방법을 기초로 하여 강력하게 추적하는 방법을 제안한다.

• Journal of ILASS-Korea
• /
• v.6 no.4
• /
• pp.31-38
• /
• 2001

The Holographic Particle Velocimetry system can be a promising optical tool for the measurements of three dimensional particle velocities. In this study, the holographic panicle velocimetry system was used to measure the sizes and velocities of droplets formed by a commercial full cone spray nozzle. Uncertainty analysis was performed to identify the sources of all relevant errors and to evaluate their magnitude. The droplet velocities ranged from 10.3 to 13.3 m/s with average uncertainty of ${\pm}1.6m/s$, which is ${\pm}14%$ of the mean droplet velocity. Compared with relatively small uncertainties of velocity components in the normal direction to the optical axis, the uncertainty of the optical axis component is ${\pm}3.6m/s$. This is due to the long depth of field of droplet images in the optical axis, which is inherent feature of holographic system using forward-scattering object wave of particles.