• Journal of Korea Society of Industrial Information Systems
• /
• v.20 no.2
• /
• pp.45-56
• /
• 2015

In this paper we propose a very rapid moving object tracking method for an object-based auto focus on a smart phone camera. By considering the limit of non-learning approach on low-performance platforms, we use a sliding-window detection technique based on histogram features. By adapting the integral histogram, we solve the problem of the time-consuming histogram computation on each sub-window. For more speed up, we propose a local candidate search, and an adaptive scaling template method. In addition, we propose to apply a stabilization term in the matching function for a stable detection location. In experiments on our dataset, we demonstrated that we achieved a very rapid tracking performance demonstrating over 100 frames per second on a PC environment.

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 1985.10a
• /
• pp.109-112
• /
• 1985

This paper proposes a algorithm of phonemes extraction in korean character pattern recognition. The phonemes are classified into the patterns which are separable and connected with each other. The former is extracted by means of pattern matching in consideration of topological structure of ponemes and direction of stroke sequentially. The latter is extracted by means of index and window algorithm which are performed by a 3$\times$3 sequential local operation in the thinned character pattern.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.12
• /
• pp.27-34
• /
• 1994

Block matching motion estimation is the most widely used method for motion compensated coding of image sequences. Based on a two dimensional systolic array, VLSI architecture and implementation of the full search block matching algorithm are described in this paper. The proposed architecture improves conventional array architecture by designing efficient processing elements that can control the data prodeuced by efficient search window division method. The advantages are that 1) it allows serial input to reduce pin counts for efficient composition of local memories but performs parallel processing. 2) It is flexible and can adjust to dimensional changes of search windows with simple control logic. 3) It has no idel time during the operation. 4) It can operate in real/time for low and main level in MPEG-2 standard. 5) It has modular and regular structure and thus is sutiable for VLSI implementation.

• Journal of Sensor Science and Technology
• /
• v.19 no.2
• /
• pp.99-111
• /
• 2010

This paper proposes an efficient hardware architecture to estimate disparities between 2D images for generating 3D depth images in a stereo vision system. Stereo matching methods are classified into global and local methods. The local matching method uses the cost functions based on pixel windows such as SAD(sum of absolute difference), SSD(sum of squared difference) and NCC(normalized cross correlation). The NCC-based cost function is less susceptible to differences in noise and lighting condition between left and right images than the subtraction-based functions such as SAD and SSD, and for this reason, the NCC is preferred to the other functions. However, software-based implementations are not adequate for the NCC-based real-time stereo matching, due to its numerous complex operations. Therefore, we propose a fast pipelined hardware architecture suitable for real-time operations of the NCC function. By adopting a block-based box-filtering scheme to perform NCC operations in parallel, the proposed architecture improves processing speed compared with the previous researches. In this architecture, it takes almost the same number of cycles to process all the pixels, irrespective of the window size. Also, the simulation results show that its disparity estimation has low error rate.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.8
• /
• pp.81-87
• /
• 1999

In general, feature detection and tracking algorithms is classified by EBGM using Garbor-jet, NNC-R and STK algorithm using pixel eigenvalue. In those algorithms, EBGM and NCC-R detect features with feature model, but STK algorithm has a characteristics of an automatic feature selection. In this paper, to solve the initial problem of NR tracking in STK algorithm, we detected features using STK algorithm in modelled feature region and tracked features with NR method. In tracking, to improve the tracking accuracy for features by NR method, we proposed BMA-NR method. We evaluated that BMA-NR method was superior to NBMA-NR in that feature tracking accuracy, since BMA-NR method was able to solve the local minimum problem due to search window size of NR.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.10C
• /
• pp.1000-1009
• /
• 2007

This paper presents a content adaptive interpolation (CAI) for intra deinterlacing. The CAI consists of three steps: pre-processing, content classification, and adaptive interpolation. There are also three main interpolation methods in our proposed CAI, i.e. modified edge-based line averaging (M-ELA), gradient directed interpolation (GDI), and window matching method (WMM). Each proposed method shows different performances according to spatial local features. Therefore, we analyze the local region feature using the gradient detection and classify each missing pixel into four categories. And then, based on the classification result, a different do-interlacing algorithm is activated in order to obtain the best performance. Experimental results demonstrate that the CAI method performs better than previous techniques.

• IEIE Transactions on Smart Processing and Computing
• /
• v.4 no.4
• /
• pp.237-250
• /
• 2015

This paper describes a hardware-oriented algorithm and its conceptual implementation in a real-time speed limit traffic sign detection system on an automotive-oriented field-programmable gate array (FPGA). It solves the training and color dependence problems found in other research, which saw reduced recognition accuracy under unlearned conditions when color has changed. The algorithm is applicable to various platforms, such as color or grayscale cameras, high-resolution (4K) or low-resolution (VGA) cameras, and high-end or low-end FPGAs. It is also robust under various conditions, such as daytime, night time, and on rainy nights, and is adaptable to various countries' speed limit traffic sign systems. The speed limit traffic sign candidates on each grayscale video frame are detected through two simple computational stages using global luminosity and local pixel direction. Pipeline implementation using results-sharing on overlap, application of a RAM-based shift register, and optimization of scan window sizes results in a small but high-performance implementation. The proposed system matches the processing speed requirement for a 60 fps system. The speed limit traffic sign recognition system achieves better than 98% accuracy in detection and recognition, even under difficult conditions such as rainy nights, and is implementable on the low-end, low-cost Xilinx Zynq automotive Z7020 FPGA.

• Journal of the Korean Society of Visualization
• /
• v.17 no.2
• /
• pp.48-57
• /
• 2019

A straightforward strategy for particle image velocimetry (PIV) interrogation and post-processing has been proposed, aiming at reducing errors and clarifying vortex structures. The interrogation window size should be kept small to reduce bias error and improve spatial resolution. A spatial filter is then applied to the velocity field to reduce random error and clarify flow structure. The performance of three popular spatial filters were assessed: box filter, median filter, and local quadratic polynomial regression filter. In order to quantify random uncertainty, the image matching (IM) method is applied to an experimental dataset of homogeneous and isotropic turbulence (HIT) obtained by 2D-PIV. We statistically analyze the uncertainty propagation through the spatial filters, and verify the reduction in random uncertainty. Moreover, we illustrate that the spatial filters help clarify vortex structures using vortex identification criteria. As a result, PIV random uncertainty was reduced and the vortex structures became clearer by spatial filtering.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2017.05a
• /
• pp.23-23
• /
• 2017

기상레이더는 강우량을 바로 추정하지 못하는 특성으로 인해 정량적 강우산출 과정 중에 다양한 원인으로 인해 불확실성 발생 요소가 존재하나 이를 정량화하고 저감하는데 많은 어려움이 있다. 원인을 살펴보면, 첫째, 기상레이더의 관측에서부터 정량적 강우량 추정까지 일련의 과정에 대한 포괄적으로 불확실성 정량화와 분석이 이루어지지 못하며, 둘째, 전체 불확실성이 어느 정도 되는지 제시하지 못하므로 각 단계별 불확실성이 전체 불확실성 대비 어느 정도 비율이 되는지 제시하지 못한다. 마지막으로 기존 연구들은 불확실성을 줄이고자 여러 방법을 사용하고 있으나 어느 정도 효용성이 있는지 불확실성 측면에서 제시하지 못하고 있다. 따라서 본 연구에서는 Maximum Entropy(ME)와 Uncertainty Delta Method(UMD)를 이용한 접근방법을 제안하여 기상레이더를 활용하여 정량적 강우량을 추정하는 일련의 과정에서 단계별로 불확실성이 어떻게 전파되는지 추정하였다. 본 연구에서는 한반도 전역을 대상으로 2012년 여름철(6~8월)에 발생한 18개 강우사례를 이용하여 품질관리(Open Radar Product Generator 품질관리 알고리즘, fuzzy 알고리즘), 강우추정(Window Probability Matching Method, Marshall-Palmer 관계식), 후처리보정(Local Gauge Correction 기법, Gauge to Radar ratio 기법)단계만을 수행하였으며, 이 결과를 바탕으로 기상레이더 정량적 강우추정 단계별 불확실성을 정량화하였다. 정량화결과, 최종적으로 관측단계의 불확실성보다 최종 불확실성이 줄어들었으나, 강우추정 단계에서 불확실성이 증가하는 것으로 나타났다. 이는 어떤 강우추정식을 적용하느냐에 따라 레이더 강우추정결과가 매우 달라질 수 있음을 의미한다. 따라서 본 연구에서 제시한 불확실성 정량화 방법을 통하여 첫째, 전체 및 단계별 불확실성을 정량화할 수 있고, 둘째, 최종 불확실성 대비 각 단계별 불확실성을 비율을 제시할 수 있으며, 마지막으로 수행단계별로 불확실성 전파과정을 파악할 수 있다. 이는 향후 정량적 레이더 강우추정 과정에 있어서 불확실성을 발생시키는 주요 원인파악과 이에 대한 집중적인 투자를 가능하게 한다. 이러한 과정을 통하여 보다 정확한 정량적 레이더 강우추정이 가능할 것으로 판단된다.