• The Transactions of the Korea Information Processing Society
• /
• v.7 no.10
• /
• pp.3280-3289
• /
• 2000

In this paper,we propose a novel technoque of improving volume rendering quality and speed by integrating volume data and global shape information together. The selective volume rendering method is to generate distance transformed volume using a distance transform to determine the minimum distance to the neaest intercsting part and then render it. The shape information prevents from object occlusions come from similar intensity of each object. Thus it provides effective visual results that enable to get a clear understanding of complex structures. We show the results of selective volume rendering method for left ventricle and right ventricle ans well as the results of selective sampling methods depending on the interpolation from EBCT cardiac images. Our method offers an accelerated technique to accurately visuahze the surfaces of devined objects segmented from the volume.

• Journal of Information Processing Systems
• /
• v.11 no.4
• /
• pp.509-527
• /
• 2015

Wireless Video Sensor Networks (WVSNs) have become a leading solution in many important applications, such as disaster recovery. By using WVSNs in disaster scenarios, the main goal is achieving a successful immediate response including search, location, and rescue operations. The achievement of such an objective in the presence of obstacles and the risk of sensor damage being caused by disasters is a challenging task. In this paper, we propose a fault tolerance model of WVSN for efficient post-disaster management in order to assist rescue and preparedness operations. To get an overview of the monitored area, we used video sensors with a rotation capability that enables them to switch to the best direction for getting better multimedia coverage of the disaster area, while minimizing the effect of occlusions. By constructing different cover sets based on the field of view redundancy, we can provide a robust fault tolerance to the network. We demonstrate by simulating the benefits of our proposal in terms of reliability and high coverage.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.7 no.2
• /
• pp.200-205
• /
• 2006

Abstract This paper presents a personal identification method based on BMME and LDA for images acquired at anterior and posterior occlusion expression of teeth. The method consists of teeth region extraction, BMME, and pattern recognition forthe images acquired at the anterior and posterior occlusion state of teeth. Two occlusions can provide consistent teeth appearance in images and BMME can reduce matching error in pattern recognition. Using teeth images can be beneficial in recognition because teeth, rigid objects, cannot be deformed at the moment of image acquisition. In the experiments, the algorithm was successful in teeth recognition for personal identification for 20 people, which encouraged our method to be able to contribute to multi-modal authentication systems.

• Journal of Korea Multimedia Society
• /
• v.19 no.8
• /
• pp.1310-1319
• /
• 2016

Face detection is the first step in a wide range of face applications. However, detecting faces in the wild is still a challenging task due to the wide range of variations in pose, scale, and occlusions. Recently, many deep learning methods have been proposed for face detection. However, further improvements are required in the wild. Another important issue to be considered in the face detection is the computational complexity. Current state-of-the-art deep learning methods require a large number of patches to deal with varying scales and the arbitrary image sizes, which result in an increased computational complexity. To reduce the complexity while achieving better detection accuracy, we propose a fully convolutional network-based face detection that can take arbitrarily-sized input and produce feature maps (heat maps) corresponding to the input image size. To deal with the various face scales, a multi-scale network architecture that utilizes the facial components when learning the feature maps is proposed. On top of it, we design multi-task learning technique to improve detection performance. Extensive experiments have been conducted on the FDDB dataset. The experimental results show that the proposed method outperforms state-of-the-art methods with the accuracy of 82.33% at 517 false alarms, while improving computational efficiency significantly.

• Journal of Korean Neurosurgical Society
• /
• v.29 no.4
• /
• pp.491-499
• /
• 2000

Objective : In the cerebral aneurysm surgery, the goal is complete circulatory exclusion of the aneurysm without compromise of normal vessels. In an operating room, an operator should confirm the completeness and precision of the surgical result, before closing the wound. Object of this study was to determine which cases require intraoperative angiography. Methods : We reported our experience with 48 intraoperative angiographic studies performed during the surgical treatment of cerebral aneurysm of these 48 cases. There were 5 giant(10.4%), 15 globular(1.5-2.5cm)(31.25%) and 28 saccular(58.3%) aneurysm. We recorded the incidence of unexpected findings, such as residual aneurysms, major vessel occlusions. Using Fischer's exact test, we assessed whether unexpected angiographic findings showed any correlation with aneurysm site, size and clinical findings. Results : In 5 cases(10.4%), we detected unexpected angiographic findings which resulted in clip adjustment. By means of clip adjustment, an operator could restore the flow of two major arterial occlusion(4.2%) and also obliterate three persistent filling aneurysms(6.3%). Globular aneurysm was the only factor to predict unexpected angiographic findings(p<0.05). The subgroup of globular and giant aneurysm has a high risk of occlusion of the parent artery and its branches and/or residual aneurysm. There were two minor complications related to this procedure. Conclusion : Intraoperative assessment makes it possible to recognize and correct the technical defect. Particularly in globular aneurysm, we were able to prevent both the chance for another operation and the risk of postoperative complications.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.8C
• /
• pp.680-688
• /
• 2010

In this paper, we present a dynamic programming(DP)-based stereo matching method using image segmentation algorithm. DP has been a classical and popular optimization method for various computer vision problems including stereo matching. However, the performance of conventional DP has not been satisfactory when it is applied to the stereo matching since the vertical correlation between scanned lines has not been properly considered. In the proposed algorithm, accurate edge information is first obtained from segmented image information then we considers the discontinuity of disparity and occlusions region based on the obtained edge information. The experimental results applied to the Middlebury stereo images demonstrate that the proposed algorithm has better performances in stereo matching than the previous DP based algorithms.

• Korean Journal of Remote Sensing
• /
• v.21 no.3
• /
• pp.229-242
• /
• 2005

Photogrammetry is a current method of GIS data acquisition. However, as a matter of fact, a large manpower and expenditure for making detailed 3D spatial information is required especially in urban areas where various buildings exist. There are no photogrammetric systems which can automate a process of spatial information acquisition completely. On the other hand, LiDAR has high potential of automating 3D spatial data acquisition because it can directly measure 3D coordinates of objects, but it is rather difficult to recognize the object with only LiDAR data, for its low resolution at this moment. With this background, we believe that it is very advantageous to integrate LiDAR data and stereo CCD images for more efficient and automated acquisition of the 3D spatial data with higher resolution. In this research, the automatic urban object recognition methodology was proposed by integrating ultra highresolution stereo images and LiDAR data. Moreover, a method to enable more reliable and detailed stereo matching method for CCD images was examined by using LiDAR data as an initial 3D data to determine the search range and to detect possibility of occlusions. Finally, intellectual DSMs, which were identified urban features with high resolution, were generated with high speed processing.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.1
• /
• pp.305-326
• /
• 2019

Discriminative correlation filter (DCF) based tracking algorithms have recently shown impressive performance on benchmark datasets. However, amount of recent researches are vulnerable to heavy occlusions, irregular deformations and so on. In this paper, we intend to solve these problems and handle the contradiction between accuracy and real-time in the framework of tracking-by-detection. Firstly, we propose an innovative strategy to combine the template and color-based models instead of a simple linear superposition and rely on the strengths of both to promote the accuracy. Secondly, to enhance the discriminative power of the learned template model, the spatial regularization is introduced in the learning stage to penalize the objective boundary information corresponding to features in the background. Thirdly, we utilize a discriminative multi-scale estimate method to solve the problem of scale variations. Finally, we research strategies to limit the computational complexity of our tracker. Abundant experiments demonstrate that our tracker performs superiorly against several advanced algorithms on both the OTB2013 and OTB2015 datasets while maintaining the high frame rates.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.7
• /
• pp.2547-2567
• /
• 2021

It has been widely acknowledged that occlusion impairments adversely distress many face recognition algorithms' performance. Therefore, it is crucial to solving the problem of face image occlusion in face recognition. To solve the image occlusion problem in face recognition, this paper aims to automatically de-occlude the human face majority or discriminative regions to improve face recognition performance. To achieve this, we decompose the generative process into two key stages and employ a separate generative adversarial network (GAN)-based network in both stages. The first stage generates an initial coarse face image without an occlusion mask. The second stage refines the result from the first stage by forcing it closer to real face images or ground truth. To increase the performance and minimize the artifacts in the generated result, a new refine loss (e.g., reconstruction loss, perceptual loss, and adversarial loss) is used to determine all differences between the generated de-occluded face image and ground truth. Furthermore, we build occluded face images and corresponding occlusion-free face images dataset. We trained our model on this new dataset and later tested it on real-world face images. The experiment results (qualitative and quantitative) and the comparative study confirm the robustness and effectiveness of the proposed work in removing challenging occlusion masks with various structures, sizes, shapes, types, and positions.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.2
• /
• pp.559-575
• /
• 2023

3D human pose estimation is widely applied in various fields, including action recognition, sports analysis, and human-computer interaction. 3D human pose estimation has achieved significant progress with the introduction of convolutional neural network (CNN). Recently, several researches have proposed the use of multiview approaches to avoid occlusions in single-view approaches. However, as the number of cameras increases, a 3D pose estimation system relying on a CNN may lack in computational resources. In addition, when a single host system uses multiple cameras, the data transition speed becomes inadequate owing to bandwidth limitations. To address this problem, we propose a distributed real-time 3D pose estimation framework based on asynchronous multiple cameras. The proposed framework comprises a central server and multiple edge devices. Each multiple-edge device estimates a 2D human pose from its view and sendsit to the central server. Subsequently, the central server synchronizes the received 2D human pose data based on the timestamps. Finally, the central server reconstructs a 3D human pose using geometrical triangulation. We demonstrate that the proposed framework increases the percentage of detected joints and successfully estimates 3D human poses in real-time.