• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.10
• /
• pp.1731-1737
• /
• 2016

In this paper, a method is proposed to recognize human actions as nonverbal expression; the proposed method is composed of two steps which are action representation and action recognition. First, MHI(Motion History Image) is used in the action representation step. This method includes segmentation based on depth information and generates spatio-temporal templates to describe actions. Second, CNN(Convolution Neural Network) which includes feature extraction and classification is employed in the action recognition step. It extracts convolution feature vectors and then uses a classifier to recognize actions. The recognition performance of the proposed method is demonstrated by comparing other action recognition methods in experimental results.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.5-7
• /
• 1996

We propose a triangulation method based on stereo vision angles. We setup stereo vision systems which extract the depth information to a moving object by detecting a moving object using difference image method and obtaining the depth information by the triangulation method based on stereo vision angles. The feature point of a moving object is used the geometrical center of the moving object, and the proposed vision system has the accuracy of 0.2mm in the range of 400mm.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.181.5-181
• /
• 2001

This paper presents the method of 3D reconstruction of the depth information from the endoscopic stereo scopic images. After camera modeling to find camera parameters, we performed feature-point based stereo matching to find depth information. Acquired some depth information is finally 3D reconstructed using the NURBS(Non Uniform Rational B-Spline) algorithm. The final result image is helpful for the understanding of depth information visually.

• ETRI Journal
• /
• v.44 no.6
• /
• pp.1034-1046
• /
• 2022

The learning-based multiview stereo (MVS) methods for three-dimensional (3D) reconstruction generally use 3D volumes for depth inference. The quality of the reconstructed depth maps and the corresponding point clouds is directly influenced by the spatial resolution of the 3D volume. Consequently, these methods produce point clouds with sparse local regions because of the lack of the memory required to encode a high volume of information. Here, we apply the atrous spatial pyramid pooling (ASPP) module in MVS methods to obtain dense feature maps with multiscale, long-range, contextual information using high receptive fields. For a given 3D volume with the same spatial resolution as that in the MVS methods, the dense feature maps from the ASPP module encoded with superior information can produce dense point clouds without a high memory footprint. Furthermore, we propose a 3D loss for training the MVS networks, which improves the predicted depth values by 24.44%. The ASPP module provides state-of-the-art qualitative results by constructing relatively dense point clouds, which improves the DTU MVS dataset benchmarks by 2.25% compared with those achieved in the previous MVS methods.

• Journal of the Korea Computer Graphics Society
• /
• v.20 no.2
• /
• pp.13-24
• /
• 2014

In this study, a graphics-processing-unit (GPU)-based acceleration technique is proposed for the feature-based image morphing. This technique uses the depth-buffer of the graphics hardware to calculate efficiently the shortest distance between a pixel and the control lines. The pairs of control lines between the source image and the destination image are determined by user's input, and the distance function of each control line is rendered using two rectangles and two cones. The distance between each pixel and its nearest control line is stored in the depth buffer through the graphics pipeline, and this is used to conduct the morphing operation efficiently. The pixel-unit morphing operation is parallelized using the compute unified device architecture (CUDA) to reduce the morphing time. We demonstrate the efficiency of the proposed technique using several experimental results.

• Journal of The Korean Astronomical Society
• /
• v.54 no.5
• /
• pp.139-155
• /
• 2021

We present an updated version of the multilayer spectral inversion (MLSI) recently proposed as a technique to infer the physical parameters of plasmas in the solar chromosphere from a strong absorption line. In the original MLSI, the absorption profile was constant over each layer of the chromosphere, whereas the source function was allowed to vary with optical depth. In our updated MLSI, the absorption profile is allowed to vary with optical depth in each layer and kept continuous at the interface of two adjacent layers. We also propose a new set of physical requirements for the parameters useful in the constrained model fitting. We apply this updated MLSI to two sets of Hα and Ca II line spectral data taken by the Fast Imaging Solar Spectrograph (FISS) from a quiet region and an active region, respectively. We find that the new version of the MLSI satisfactorily fits most of the observed line profiles of various features, including a network feature, an internetwork feature, a mottle feature in a quiet region, and a plage feature, a superpenumbral fibril, an umbral feature, and a fast downflow feature in an active region. The MLSI can also yield physically reasonable estimates of hydrogen temperature and nonthermal speed as well as Doppler velocities at different atmospheric levels. We conclude that the MLSI is a very useful tool to analyze the Hα line and the Ca II 8542 line spectral daya, and will promote the investigation of physical processes occurring in the solar photosphere and chromosphere.

• Journal of Periodontal and Implant Science
• /
• v.35 no.3
• /
• pp.761-776
• /
• 2005

The purpose of the present study was to examine the relationship between the form of the clinical crowns in the maxillary anterior segment and the clinical feature of gingiva such as morphological characteristics and the gingival thickness. Fifty periodontally healthy subjects were clinically examined regarding the probing depth, the thickness of the free gingiva, and the width of the keratinized gingiva. From study models of the maxillary anterior region, the width at cervical third(CW) and the length(CL) of the clinical crown, the papillary height, and the gingival angle of the 6 anterior teeth were measured. Each tooth was classified into 4 groups (longnarrow, NL; narrow, N; wide, W; short-wide, WS) according to CW/CL ratio and all the data were compared between groups NL and WS using independent t-test. Stepwise multiple regression analysis was performed for each tooth region with the gingival thickness at the level of sulcus bottom, the width of keratinized gingiva, and gingival angle as the dependent variables. As the results, the NL group of the upper anterior teeth displayed, higher papilla height, and narrower keratinized gingiva, more acute gingival angle resulting in pronounced "scalloped" contour of the gingival margin, compared to the WS group. There was no significant difference between groups NL and WS with respect to probing depth and the gingival thickness. The regression analyses demonstrated that the gingival thickness in central incisors was significantly associated to the mesio-distal width and bucco-lingual width of the crown, and labial probing depth. The width of keratinized gingiva was significantly associated with labial probing depth in central incisors and with proximal probing depth and gingival angle in lateral incisors, and with labial and proximal probing depth, and gingival angle in canines. The gingival angle was significantly associated with papillary height and CW/CL ratio and additionally with proximal probing depth in central incisors, with the width of keratinized gingiva in lateral incisors, and with labial probing depth and the width of keratinized gingiva in canines. These results indicate that the form of clinical crown in upper anterior region could influence the clinical feature of gingiva and the influencing factors might be different according to the tooth region.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.9 no.1
• /
• pp.141-150
• /
• 2013

This study proposes technology using Active Shape Model to track the object separating it by depth-sensors. Unlike the common visual camera, the depth-sensor is not affected by the intensity of illumination, and therefore a more robust object can be extracted. The proposed algorithm removes the horizontal component from the information of the initial depth map and separates the object using the vertical component. In addition, it is also a more efficient morphology, and labeling to perform image correction and object extraction. By applying Active Shape Model to the information of an extracted object, it can track the object more robustly. Active Shape Model has a robust feature-to-object occlusion phenomenon. In comparison to visual camera-based object tracking algorithms, the proposed technology, using the existing depth of the sensor, is more efficient and robust at object tracking. Experimental results, show that the proposed ASM-based algorithm using depth sensor can robustly track objects in real-time.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.594-596
• /
• 2022

Over the last decades, deep neural networks have demonstrated significant success in various tasks. To address the special vision task, choosing a hot network as backbone to extract feature is a common way in both research and industry project. However, the choice of backbone usually requires the expert experience and affects the performance of the classification task. In this work, we propose a novel idea to support backbone decision-making by exploring the feature attribution and weights distribution of hidden layers from various backbones. We first analyze the visualization of feature maps on different size object and different depth layers to observe learning ability. Then, we compared the variance of weights and feature in last three layers. Based on analysis of the feature and wights, we summarize the traits and commonalities of existing networks.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.3
• /
• pp.1121-1139
• /
• 2015

In texture-plus-depth format, depth map compression is an important task. Different from normal texture images, depth maps have less texture information, while contain many homogeneous regions separated by sharp edges. This feature will be employed to form an efficient depth map coding scheme in this paper. Firstly, the histogram of the depth map will be analyzed to find an appropriate threshold that segments the depth map into the foreground and background regions, allowing the edge between these two kinds of regions to be obtained. Secondly, the two regions will be encoded through rate distortion optimization with a shape adaptive wavelet transform, while the edges are lossless encoded with JBIG2. Finally, a depth-updating algorithm based on the threshold and the depth range is applied to enhance the quality of the decoded depth maps. Experimental results demonstrate the effective performance on both the depth map quality and the synthesized view quality.