• Journal of Information Technology Applications and Management
• /
• 제11권4호
• /
• pp.169-179
• /
• 2004

There are many inductive loop detectors under the highways in Korea. Among the other detectors, some are image detectors. Almost all image detectors are focused one or two lane of the road and are measuring traffic information. This paper proposes to an algorithm for detecting traffic information automatically from CCTV camera images installed on the highway. The information which is counted in one lane or two contains some critical errors by occlusion frequently in case of passing larger vehicles. In this paper, we use a tracking algorithm in which the detection area include all lanes, then the traffic informations are collected from the vehicles individually using difference images in this detection area. This tracking algorithm is better than lane by lane detecting algorithm. The experiment have been conducted two different real road scenes for 20 minutes. For the experiments, the images are provided with CCTV camera which was installed at Kiheung Interchange upstream of Kyongbu highway, and video recording images at Chungkye Tunnel. For image processing, images captured by frame-grabber board 30 frames per second, 640${\times}$480 pixels resolution and 256 gray-levels to reduce the total amount of data to be Interpreted.

• 한국게임학회 논문지
• /
• 제9권2호
• /
• pp.115-123
• /
• 2009

논문에서는 무리 짓기에 대한 공간분할 방법의 성능을 개선하는 알고리즘을 제안한다. 핵심 개념은 무리 속에서 움직이는 개체인 보이드가 지속적으로 자신의 방향과 위치를 변경시키나 자신의 다음 방향의 결정에 영향을 주는 k개의 가장 가까운 이웃인 kNN은 자주 바뀌지 않는다는 사실을 이용하여 성능을 개선하는 것이다. 본 논문에서 이전의 kNN을 이용하여 새로운 kNN이 변경되었는지를 판별하는 방법이 제안되었고, 제안된 방법의 정당성은 정리를 통하여 증명되었다. 제안된 방법은 구현되었으며, 기존의 공간분할 방법과 성능이 비교되었다. 비교 결과로부터 제안된 알고리즘이 초당 프레임 수 관점에서 기존의 알고리즘보다 약 30% 개선 효과를 주는 것을 알 수 있었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권1호
• /
• pp.201-220
• /
• 2020

Trackers, especially long-term (LT) trackers, now have a more complex structure and more intensive computation for nowadays' endless pursuit of high accuracy and robustness. However, computing efficiency of LT trackers cannot meet the real-time requirement in various real application scenarios. Considering heterogeneous CPU-GPU platforms have been more popular than ever, it is a challenge to exploit the computing capacity of heterogeneous platform to improve the efficiency of LT trackers for real-time requirement. This paper focuses on TLD, which is the first LT tracking framework, and proposes an efficient parallel implementation based on OpenCL. In this paper, we firstly make an analysis of the TLD tracker and then optimize the computing intensive kernels, including Fern Feature Extraction, Fern Classification, NCC Calculation, Overlaps Calculation, Positive and Negative Samples Extraction. Experimental results demonstrate that our efficient parallel TLD tracker outperforms the original TLD, achieving the 3.92 speedup on CPU and GPU. Moreover, the parallel TLD tracker can run 52.9 frames per second and meet the real-time requirement.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2014년도 하계학술대회
• /
• pp.163-165
• /
• 2014

In this paper, we propose a world's first programmable video processing platform for video quality enhancement of 8K ($7680{\times}4320$) UHD (Ultra High Definition) TV at 60 frames per second. To support huge computation and memory bandwidth of video quality enhancement for 8K resolution, the proposed platform has unique features like symmetric multi-cluster architecture for data partitioning, ring data-path between clusters to support data pipelining, on-the-fly processing architecture to reduce DDR bandwidth, flexible hardware to accelerating common kernel in video enhancement algorithms. In addition to those features, general programmability of SRP (Samsung reconfigurable processor) as main core of the proposed platform makes it possible to upgrade continuously video enhancement algorithm even after the platform is fixed. This ability is very important because algorithms for 8K DTV is under development. The proposed sub-system has been embedded into SoC (System on Chip) and new 8K UHD TV using the programmable SoC is expected at CES2015 for the first time in the world.

• 한국광학회지
• /
• 제21권5호
• /
• pp.206-213
• /
• 2010

광 간섭 단층촬영 시스템(OCT)을 위한 소형의 광섬유 도관형 주사장치인 엔도스코프(endoscope catheter)를 제작하였다. 깊이방향 주사장치인 원통형 압전소자(PZT)를 이용한 광경로 지연기는 정현파 1 kHz로 구동하여 시간영역에서 엔도스코프 OCT 영상을 구현하였다. 정현파로 구동한 광경로 지연기의 속도는 6 m/s 이고, 깊이방향 스캐닝의 데이터 획득은 3 mm 기준에서 초당 2000 라인이다. 제작한 엔도스코프로 사람의 손가락 및 귀에 대한 초당 10프레임의 OCT 영상을 성공적으로 획득하였다.

• 조명전기설비학회논문지
• /
• 제23권1호
• /
• pp.125-131
• /
• 2009

본 논문에서는 무선랜 환경에서 주행 로봇 플랫폼에 의한 원격 영상 감시 시스템을 제안하였다. 제안된 방법은 ARM9코어기반의 PXA255 프로세서 시스템에 소형 CMOS 카메라를 장착하고 촬영한 영상을 803.11b/g 무선 네트워크를 이용하여 전송하는 이동형 원격 영상 감시 시스템을 구성하였다. 로봇플랫폼의 주행 명령을 원격으로 전송하며, 촬영된 영상은 $640{\times}480$, $320{\times}240$픽셀 등의 정지 영상을 초당 $3{\sim}10$프레임의 속도로 전송하였으며, 시스템을 구현하고 영상에 의한 원격감시기능을 적절히 수행할 수 있음을 실험을 통하여 확인하였다. 제안된 시스템은 리눅스 운영체제를 기반으로 구축하였다.

• 한국조명전기설비학회:학술대회논문집
• /
• 한국조명전기설비학회 2005년도 춘계학술대회논문집
• /
• pp.69-73
• /
• 2005

The arc dispersion and contacts characteristics were analyzed according to switching off Residual Current Protective Device(RCD) switch. Arc dispersion process was taken by high speed imaging system at a rate of 10,000 frames per second. When RCD was switched from on to off, art was observed and it took about 2.3[ms] from the generation of arc to the extinction of arc. When RCD was switched from off to on, arc was not observed. We repeated switching on and off 1000, 3000 and 6000 times. After repetition, the surface characteristics of contacts were taken by stereo microscope and Scanning Electron Microscope(SEM). From the scattering patterns analysis of arc and the analysis of deteriorated contacts, it could be applicable to the research of electric fire and arc suppression.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제31권11호
• /
• pp.1534-1542
• /
• 2004

본 논문에서는 교통 영상에서 실시간 교통 정보를 산출하는 새로운 기법을 소개한다. 각 차선의 검지 영역은 통계적 특징과 형상적 특징을 이용하여 도로, 차량, 그리고 그림자 영역으로 분류한다. 한 프레임에서의 오류는 연속된 프레임에서의 차량 영역의 상관적 특징을 이용하여 시공간 영상에서 교정된다. 국부 검지 영역만을 처리하므로 전용의 병렬 처리기 없이도 초당 30 프레임 이상의 실시간 처리가 가능하며 기상조건, 그림자, 교통량의 변화에도 강건한 성능을 보장할 수 있다.

• International Journal of Automotive Technology
• /
• 제5권3호
• /
• pp.155-164
• /
• 2004

The direct injection gasoline spray-wall interaction was characterized inside a heated pressurized chamber using various visualization techniques, including high-speed laser-sheet macroscopic and microscopic movies up to 25,000 frames per second, shadowgraph, and double-spark particle image velocimetry. Two hollow cone high-pressure swirl injectors having different cone angles were used to inject gasoline onto a heated plate at two different impingement angles. Based on the visualization results, the overall transient spray impingement structure, fuel film formation, and preliminary droplet size and velocity were analyzed. The results show that upward spray vortex inside the spray is more obvious at elevated temperature condition, particularly for the wide-cone-angle injector, due to the vaporization of small droplets and decreased air density. Film build-up on the surface is clearly observed at both ambient and elevated temperature, especially for narrow cone spray. Vapor phase appears at both ambient and elevated temperature conditions, particularly in the toroidal vortex and impingement plume. More rapid impingement and faster horizontal spread after impingement are observed for elevated temperature conditions. Droplet rebounding and film break-up are clearly observed. Post-impingement droplets are significantly smaller than pre-impingement droplets with a more horizontal velocity component regardless of the wall temperature and impingement angle condition.

• IEIE Transactions on Smart Processing and Computing
• /
• 제3권4호
• /
• pp.195-204
• /
• 2014

This paper presents the depth evaluation for object detection by automated assembling robots. Pattern distortion analysis from a structured light system identifies an object with the greatest depth from its background. An automated assembling robot should prior select and pick an object with the greatest depth to reduce the physical harm during the picking action of the robot arm. Object detection is then combined with a depth evaluation to provide contour, showing the edges of an object with the greatest depth. The contour provides shape information to an automated assembling robot, which equips the laser based proxy sensor, for picking up and placing an object in the intended place. The depth evaluation process using structured light for an automated electronics assembling robot is accelerated for an image frame to be used for computation using the simplest experimental set, which consists of a single camera and projector. The experiments for the depth evaluation process required 31 ms to 32 ms, which were optimized for the robot vision system that equips a 30-frames-per-second camera.