• Journal of Korean Society for Geospatial Information Science
• /
• v.25 no.1
• /
• pp.55-61
• /
• 2017

The V-world, korean type spatial information open platform, provides various services to easily utilize 2D, 3D map and administrative information of the country. Among them, V-world 3D map service, modeled in individual building unit, require requests for each building model file and the draw calls for drawing models on the screen by the request. This causes a large number of model requests and draw calls to occur that increase the latency occurring during the transmission and conversion process between the central processing unit(CPU) and the graphic processing unit(GPU), which lead to the performance degradation of the 3D map service. In this paper, we propose a performance improvement plan to reduce the performance degradation of 3D map service caused by multiple model requests and draw calls. Therefore, we tried to reduce the number of requests and draw calls for the model file by applying a 3D tile model that combined multiple building models to single tile. In addition, we applied the quadtree algorithm to reduce the time required to load the model file by shortening the retrieval time of the model. This is expected to contribute to improving the performance of 3D map service of V-world.

• Journal of information and communication convergence engineering
• /
• v.9 no.3
• /
• pp.266-270
• /
• 2011

The advancement of technology enables smart phones or handheld devices to render complex 3D graphics. However, the processing power and memory of smart phones remain very limited to render high polygon and details 3D models especially on games which requires animation, physic engine, or augmented reality. In this paper, several techniques will be introduced to speed up the computation and reducing the number of vertices of the 3D meshes without losing much detail.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.06a
• /
• pp.9-12
• /
• 2019

지난 수 년 동안 계속해서 일반 실상 카메라를 이용한 영상분석기술에 대한 연구가 활발히 진행되고 있다. 최근에는 딥러닝 기술을 적용한 지능형 영상분석기술로 발전해 왔으며 국방기지방호, CCTV, 사용자 얼굴인식, 머신비전, 자동차, 드론 산업이 활성화되면서 많은 시너지를 효과를 일으키고 있다. 그러나 어두운 밤과 안개, 날씨, 연기 등 다양한 여건에서 따라서 카메라의 영상분석 정확성 감소와 오류가 수반될 수 있으며 일반적으로 딥러닝 기술을 활용하기 위해서는 고사양의 GPU를 필요로 하기 때문에 다른 추가적인 시스템이 요구된다. 이에 본 연구에서는 열적외선 영상의 객체 검출에 적용하기 위해 SSD(Single Shot MultiBox Detector) 기반의 경량적인 MobilNet 네트워크로 재구성하여, 모바일 기기 등 낮은 사양의 낮은 임베디드 시스템에서도 활용 할 수 있는 방법을 제안한다. 모의 실험결과 제안된 방식의 모델은 적외선 열화상 카메라에서 객체검출과 학습시간이 줄어든 것을 확인 할 수 있었다.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.1
• /
• pp.46.2-46.2
• /
• 2019

We propose a deep learning model that can generate a waveform of coalescing binary black holes in merging and ring-down phases in less than one second with a graphics processing unit (GPU) as an approximant of gravitational waveforms. Up to date, numerical relativity has been accepted as the most adequate tool for the accurate prediction of merger phase of waveform, but it is known that it typically requires huge amount of computational costs. We present our method can generate the waveform with ~98% matching to that of the status-of-the-art waveform approximant, effective-one-body model calibrated to numerical relativity simulation and the time for the generation of ~1500 waveforms takes O(1) seconds. The validity of our model is also tested through the recovery of signal-to-noise ratio and the recovery of waveform parameters by injecting the generated waveforms into a public open noise data produced by LIGO. Our model is readily extendable to incorporate additional physics such as higher harmonics modes of the ring-down phase and eccentric encounters, since it only requires sufficient number of training data from numerical relativity simulations.

• Korean Journal of Remote Sensing
• /
• v.38 no.3
• /
• pp.237-250
• /
• 2022

In this study, we propose a method to estimate the biomass of invertebrate grazers from the videos with underwater drones by using a multi-object tracking model based on deep learning. In order to detect invertebrate grazers by classes, we used YOLOv5 (You Only Look Once version 5). For biomass estimation we used DeepSORT (Deep Simple Online and real-time tracking). The performance of each model was evaluated on a workstation with a GPU accelerator. YOLOv5 averaged 0.9 or more mean Average Precision (mAP), and we confirmed it shows about 59 fps at 4 k resolution when using YOLOv5s model and DeepSORT algorithm. Applying the proposed method in the field, there was a tendency to be overestimated by about 28%, but it was confirmed that the level of error was low compared to the biomass estimation using object detection model only. A follow-up study is needed to improve the accuracy for the cases where frame images go out of focus continuously or underwater drones turn rapidly. However,should these issues be improved, it can be utilized in the production of decision support data in the field of invertebrate grazers control and monitoring in the future.

• Journal of the Korea Computer Graphics Society
• /
• v.22 no.3
• /
• pp.53-61
• /
• 2016

In this paper, we propose an algorithm for generating lightning paths, which are more realistic than those of random tree based algorithm and faster than a physically based simulation algorithm. Our approach utilizes physically based Dielectric Breakdown Method (DBM) and approximates the electric potential field dramatically to generate the lightning path. We also show a guide path method for the lightning to avoid obstacles in a complex scene. Finally, our method renders fast and realistic lightning by considering physical characteristics for the thickness and brightness of the lightning stream. Our result of the lightning path shares similarity to natural phenomenon by having about 1.56 fractal dimensions, and we can generate the lightning path faster than a previous physically based algorithm. On the other hand, our method is difficult to apply on the real-time games yet, but our approach can be improved by performing the path generation algorithm with GPU in future.

• Journal of KIISE
• /
• v.44 no.6
• /
• pp.573-580
• /
• 2017

Despite the recent remarkable advances in the computing power of mobile devices, the heat and battery problems still restrict their performances, particularly compared to PCs. Therefore, in the application of the ray-tracing technique for high-quality rendering, the consideration of a method that traces only the secondary rays while the effects of the primary rays are generated through rasterization-based OpenGL ES rendering is worthwhile. Given that most of the rendering time is for the secondary-ray processing in such a method, a new volume-grid technique for dynamic scenes that enhances the tracing performance of the secondary rays with a low coherence is proposed here. The proposed method attempts to model all of the possible spatial secondary rays in a fixed number of sampling rays, thereby alleviating the visitation problem regarding all of the cells along the ray in a uniform grid. Also, a hybrid rendering pipeline that speeds up the overall rendering performance by exploiting the mobile-device CPU and GPU is presented.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.4C
• /
• pp.277-282
• /
• 2012

In this paper, we present a real-time eye contact system for realistic telepresence using a Kinect depth camera. In order to generate the eye contact image, we capture a pair of color and depth video. Then, the foreground single user is separated from the background. Since the raw depth data includes several types of noises, we perform a joint bilateral filtering method. We apply the discontinuity-adaptive depth filter to the filtered depth map to reduce the disocclusion area. From the color image and the preprocessed depth map, we construct a user mesh model at the virtual viewpoint. The entire system is implemented through GPU-based parallel programming for real-time processing. Experimental results have shown that the proposed eye contact system is efficient in realizing eye contact, providing the realistic telepresence.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.6
• /
• pp.313-330
• /
• 2021

In an autonomous driving system equipped with a camera and lidar, depth completion techniques enable dense depth estimation. In particular, using self-supervised learning it is possible to train the depth completion network even without ground truth. In actual autonomous driving, such depth completion should have very short latency as it is the input of other algorithms. So, rather than complicate the network structure to increase the accuracy like previous studies, this paper focuses on network latency. We design a U-Net type network with RegNet encoders optimized for GPU computation. Instead, this paper presents several techniques that can increase accuracy during the process of self-supervised learning. The proposed techniques increase the robustness to unreliable lidar inputs. Also, they improve the depth quality for edge and sky regions based on the semantic information extracted in advance. Our experiments confirm that our model is very lightweight (2.42 ms at 1280x480) but resistant to noise and has qualities close to the latest studies.

• Journal of Navigation and Port Research
• /
• v.46 no.3
• /
• pp.243-250
• /
• 2022

The purpose of this study was to propose technology to detect the wave in the image in real-time, and calculate the height of the wave-overtopping through image analysis using artificial intelligence. It was confirmed that the proposed wave overtopping detection system proposed in this study could detect the occurring of wave overtopping, even in severe weather and at night in real-time. In particular, a filtering algorithm for determining if the wave overtopping event was used, to improve the accuracy of detecting the occurrence of wave overtopping, based on a convolutional neural networks to catch the wave overtopping in CCTV images in real-time. As a result, the accuracy of the wave overtopping detection through AP50 was reviewed as 59.6%, and the speed of the overtaking detection model was 70fps based on GPU, confirming that accuracy and speed are suitable for real-time wave overtopping detection.