• Journal of the Korea Society of Computer and Information
• /
• v.19 no.3
• /
• pp.25-35
• /
• 2014

This paper proposes a method of boosting-based classification for the purpose of real-time face detection. The proposed method uses depth images to ensure strong performance of face detection in response to changes in lighting and face size, and uses the depth difference feature to conduct learning and recognition through the I-MCTBoost classifier. I-MCTBoost performs recognition by connecting the strong classifiers that are constituted from weak classifiers. The learning process for the weak classifiers is as follows: first, depth difference features are generated, and eight of these features are combined to form the weak classifier, and each feature is expressed as a binary bit. Strong classifiers undergo learning through the process of repeatedly selecting a specified number of weak classifiers, and become capable of strong classification through a learning process in which the weight of the learning samples are renewed and learning data is added. This paper explains depth difference features and proposes a learning method for the weak classifiers and strong classifiers of I-MCTBoost. Lastly, the paper presents comparisons of the proposed classifiers and the classifiers using conventional MCT through qualitative and quantitative analyses to establish the feasibility and efficiency of the proposed classifiers.

• Journal of Korea Water Resources Association
• /
• v.34 no.5
• /
• pp.459-472
• /
• 2001

The objective of this study is to evaluate the filtration efficiency of deep-bed filters by comparing to single and dual media filters. Pilot-plant tests using four-filter columns were conducted for the comparison of head loss development and filtered water quality. The dual-media filter showed greater initial head loss, but less rate of head-loss development than those of the coarse-sand-0deep-bed filters. For 180 m/day of filtration rate, the dual-media filter produces larger unit production rate by 30-40%, and the turbidities of filtered water were below 0.1 NTU. The initial breakthrough could be effectively controlled by the dual-media filter rather than coarse-sand-deep-bed filters.

• Journal of Broadcast Engineering
• /
• v.23 no.1
• /
• pp.3-10
• /
• 2018

Depth map has been utilized in a varity of fields. Recently research on generating depth map by artificial neural network (ANN) has gained much interest. This paper validates the feasibility of implementing the ready-made depth map generation by convolutional neural network (CNN). First, for a given image, a depth map is generated by the weighted average of a saliency map as well as a motion history image. Then CNN network is trained by test images and depth maps. The objective and subjective experiments are performed on the CNN and showed that the CNN can replace the ready-made depth generation method.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2014.06a
• /
• pp.81-83
• /
• 2014

This paper provides the performance comparison of selected post filters for depth map in 3D video system. In the performance comparison, the dilation filter which is currently adopted in 3D-ATM reference S/W, the bilateral filter, and the depth-oriented depth boundary reconstruction filter. In the paper, we first introduce those filters in details, and show the experimental results as post filter in 3D video system.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.67-70
• /
• 2009

This paper proposes an algorithm for creating stereoscopic video from a monoscopic video. A viewer uses depth perception clues called a vanishing point which is the farthest from a viewer's viewpoint in order to perceive depth information from objects and surroundings thereof to the viewer. The viewer estimates the vanishing point with geometrical features in monoscopic images, and can perceive the depth information with the relationship between the position of the vanishing point and the viewer's viewpoint. In this paper, we propose a method to estimate a vanishing point with edge direction histogram in a general monoscopic image and to create a depth map depending on the position of the vanishing point. With the conversion method proposed through the experiment results, it is seen that stable stereoscopic conversion of a given monoscopic video is achieved.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2012.07a
• /
• pp.44-46
• /
• 2012

Depth map를 구하는 방법 중 많이 사용되어지는 방법으로 stripe 패턴을 이용하는 방법이 존재한다. 이 방법은 Pro-Cam 시스템을 이용하며 프로젝터로 조사한 패턴을 카메라로 촬영하여 원래의 패턴과 촬영된 패턴간의 기하학적인 관계를 구하여 depth map를 구하는 방법이다. 본 논문에서는 이와 같이 구조광을 이용하여 depth map 획득 시스템을 효과적으로 multi-thread를 사용하여 실시간 처리하는 것을 제안한다. 일반적으로 자주 사용되는 multi-threading 기법에는 CPU의 thread를 이용하는 OpenMP와 GPU의 thread를 이용하는 CUDA가 있다. 이 두 가지 기법은 수행하는데 차이점이 존재하기 때문에 상황에 따라 OpenMP가 더 좋은 효율을 보이는 부분이 있고 CUDA가 더 좋은 효율을 보이는 부분이 있다. 때문에 우리는 이 두 가지에 대해서 각 부분의 특성에 맞게 더 좋은 효율을 보이는 multi-thread를 이용하였다. 결과적으로 우리는 $1280{\times}800$의 영상에 대해 25fps 이상의 depth map를 획득하였다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.07a
• /
• pp.452-454
• /
• 2015

This paper provides the coding performance comparisons of depth map resolution in 3D video system. In multiview plus depth map system, depth map is used for synthesis view rendering, and affects to synthesis views quality. In the paper, we show the experimental results as depth map resolution in 3D video system, and show performance variation as dilation filter.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.275-278
• /
• 2021

영상 스티칭은 다수의 영상을 넓은 시야각을 갖는 하나의 영상으로 합성하여 사용자들에게 몰입감과 현장감을 제공하는 기술이다. 그러나 영상에 시차(Parallax)가 존재하는 경우 스티칭된 영상에서 왜곡이 발생할 수 있는데 이는 사용자의 몰입을 방해할 수 있다. 따라서 스티칭 영상의 다양한 활용을 위해서는 시차로 인한 왜곡을 최소화하여 자연스러운 스티칭 영상을 만드는 것이 중요하다. 기존 호모그래피 추정 방법으로 발생할 수 있는 고스트 현상을 최소화하기 위해서 seam 기반 스티칭 방법이 사용되었지만, 단순히 작은 특징값을 따라 생성된 seam은 사물 영역 정보가 반영되지 않아 seam이 특징이 있는 부분을 지나가면서 시차 왜곡이 발생할 수 있다. 이에 본 논문에서는 딥러닝 기반의 MegaDepth를 활용한 depth 예측 정보를 에너지 함수 기반의 seam 생성 행렬의 가중치로 사용하여 seam이 사물을 피해 생성되면서 시차가 작은 영역으로 유도되도록 하는 seam optimization 기법을 제안한다.

• Journal of Korean Society of Water and Wastewater
• /
• v.21 no.6
• /
• pp.763-770
• /
• 2007

There are many design parameters affecting filtration efficiency such as filteration rate, media packing depth, size distribution, and so on. The sphericity, the ratio of the surface area of an equal volume sphere to the real surface area of the particles, is one of major physical characters of media. The effect of sphericity on the performance of anthracite filter has been investigated. Media from eight water treatment plants have been collected. The sphericity of each media has been calculated by using well known headloss equations such as Kozeny equation, Dahmarajah equation etc.. Columns packed with anthracite media having different sphericity have been used to compare headloss development, floc accumulation in the bed, particles in bed water, filtrate turbidities after backwash and so on. The repeated experiments have indicated that the sphericity of anthracite media may not have remarkable influence on the filter performance as it has been suspected. It also has been prospected in the experiment that the media of higher sphericity would store more particles in the bed and give better filtrate quality, if provided that the effective size and the size distribution of media would be the same.

• Journal of Broadcast Engineering
• /
• v.9 no.3
• /
• pp.185-195
• /
• 2004

This paper presents a multi-depth map fusion method for the 3D scene reconstruction. It fuses depth maps obtained from the stereo matching technique and the depth camera. Traditional stereo matching techniques that estimate disparities between two images often produce inaccurate depth map because of occlusion and homogeneous area. Depth map obtained from the depth camera is globally accurate but noisy and provide a limited depth range. In order to get better depth estimates than these two conventional techniques, we propose a depth map fusion method that fuses the multi-depth maps from stereo matching and the depth camera. We first obtain two depth maps generated from the stereo matching of 3-view images. Moreover, a depth map is obtained from the depth camera for the center-view image. After preprocessing each depth map, we select a depth value for each pixel among them. Simulation results showed a few improvements in some background legions by proposed fusion technique.