• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.110-113
• /
• 2022

인터넷을 통해 주위 사물과 연결된 차량은 사용자에게 편리성을 제공하기 위해 다양한 콘텐츠를 요구하는데 클라우드로부터 가져오는 시간이 비교적 오래 걸리기 때문에 차량과 물리적으로 가까운 위치에 캐싱하는 기법들이 등장하고 있다. 본 논문에서는 기반 시설이 밀집하게 설치된 도시 환경에서 maximum distance separable(MDS) 코딩을 사용해 road side unit(RSU)에 캐싱하는 방법에 대해 연구하였다. RSU의 중복된 서비스 커버리지 지역을 고려하여 차량의 콘텐츠 요구에 대한 RSU hit ratio를 높이기 위해 deep Q-learning(DQN)를 사용하였다. 실험 결과 비교 알고리즘보다 hit raito 측면에서 더 높은 성능을 보이는 것을 증명하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.507-509
• /
• 2023

최근 딥러닝은 도로 CCTV 동영상의 교통사고 검출에 널리 사용되지만 일인칭 동영상의 교통사고 검출은 분명히 어렵다. 일인칭 동영상은 역동적이고 시야가 제한되어 있기 때문이다. 본 논문에서는 일인칭 동영상을 분석하여 교통사고를 검출하는 방법을 제시한다. 이 방법은 교통 표현 특성을 분석하는 것 외에도 의미를 이해하고 교통 장면을 인코딩한다. 프레임의 표현 특징은 각 프레임 상의 물체의 특징과 물체의 위치 관계의 공간적 숨겨진 특진을 학습함으로써 얻어진다. 그 후에 프레임 표현 특징과 교통 장면의 특징이 연결되어 GRU 실행기에 공급된다. 여러 GRU 실행기는 분석한 후 사고가 발생했는지 확인된다. 이 방법은 높은 역학과 제한된 시야 문제를 효과적으로 해결한다.

• The KIPS Transactions:PartB
• /
• v.15B no.4
• /
• pp.259-268
• /
• 2008

In an effort to increase the data capacity of one-dimensional symbology, 2D barcodes have been proposed a decade ago. In this paper, we present an effective 2D barcode detection algorithm from gray-level images, especially for the handheld 2D barcode recognition system. To locate the symbol inside the image, a criteria based on the block contrast is adopted, and a gray-scale projection with sub-pixel operation is utilized to segment the symbol precisely from the region of interest(ROI). Finally, the segmented ROI is normalized using the inverse perspective transformation for the following decoding processes. We also introduce the post-processing steps for decoding the QR-code. The proposed method ensures high performances under various lighting/printing conditions and strong perspective deformations. Experiments shows that our method is very robust and efficient in detecting the code area for the various types of 2D barcodes in real time.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.12
• /
• pp.159-167
• /
• 2013

In stereo-view system, variations of target camera position or lighting conditions cause discrepancies on the luminance and chrominance components of stereo views. These discrepancies lead to inaccurate frame view prediction and low quality of 3 D video coding. In this paper, an efficient histogram interval calibration method is proposed for stereo-view coding, so as to compensate for the luminance component of target view. First the proposed method is analyzed by the histogram of the target image frame. Then, it divide two sections of histogram of that frame to correct the color discrepancies. Secondly, each section of the target frame is corrected the luminance component by identify the maximum matching region between the reference frame and the target frame. We have verified our proposed histogram matching method in comparison with the other color correction ones. Experimental results show that it can correct better luminance calibration results of PSNR(Peak Signal to Noise Ratio) and has less computation time.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.7
• /
• pp.97-106
• /
• 2012

Management of biosignal data in mobile devices causes many problems in real-time transmission of large volume of multimedia data or storage devices. Therefore, this research paper intends to suggest an m-Health system, a clinical data processing system using mobile in order to provide quick medical service. This system deployed health system on IP network, compounded outputs from many bio sensing in remote sites and performed integrated data processing electronically on various bio sensors. The m-health system measures and monitors various biosignals and sends them to data servers of remote hospitals. It is an Android-based mobile application which patients and their family and medical staff can use anywhere anytime. Medical staff access patient data from hospital data servers and provide feedback on medical diagnosis and prescription to patients or users. Video stream for patient monitoring uses a scalable transcoding technique to decides data size appropriate for network traffic and sends video stream, remarkably reducing loads of mobile systems and networks.

• Progress in Medical Physics
• /
• v.17 no.4
• /
• pp.260-267
• /
• 2006

A retinal ganglion cell's receptive field is defined as that region on the retinal surface In which a light stimulus will produce a response. A retinal ganglion cell peers out at a small patch of the visual scene through its receptive field and encodes local features with action potentials that pass through the optic nerve to higher centers. Therefore, defining the receptive field of a retinal ganglion cell is essential to understand the electrical characteristics of a ganglion cell. Distribution of receptive fields over retinal surface provides us an Insight how the retinal ganglion cell processes the visual scene. In this paper, we provide the details how to reconstruct the receptive field of a retinal ganglion cell. We recorded the ganglion cell's action potential with multielectrode array when the random checkerboard stimulus was applied. After classifying the retinal waveform Into ON-cell, OFF-cell, ON/OFF-cell, we reconstructed the receptive field of retinal ganglion cell with Matlab. Here, we show the receptive fields of ON-cell and OFF-cell.

• Journal of Broadcast Engineering
• /
• v.16 no.2
• /
• pp.190-206
• /
• 2011

We propose an adaptive combination scheme of intra and inter prediction modes, where uni-directional intra prediction, bi-directional intra prediction, and inter prediction method are adaptively selected in an EMB (extended macro block). For each EMB, after all inter blocks have been encoded and decoded, the reconstructed blocks are used as reference data for bi-directional intra prediction of other blocks. Whereas conventional intra coding scheme does not use the right and below side pixels of the current block as reference data, the proposed method uses those for bi-directional intra prediction mode. In this paper, we propose three advanced techniques; (a) filter design for bi-directional prediction, (b) adaptive coding order scheme which increases the chance to use the bi-directional intra prediction mode, (c) modification of syntax to represent coding order. The information for the coding order is informed to the decoder by using the modified syntax structure without adding any additional flag. The simulation results show that the proposed scheme reduces the BD-Rate by 0.5%, on average, compared to KTA.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.2C
• /
• pp.172-181
• /
• 2010

In this paper, we propose an adaptive block quantization method. The propose method perfrect reconstructs side information without high complexity in the encoder side, as transmitting motion vectors from a decoder to an encoder side. Also, at the encoder side, residual signals between reconstructed side information and original frame are adaptively quantized to minimize parity bits to be transmitted to the decoder. The proposed method can effectively allocate bits based on bit error rate of side information. Also, we can achieved bit-saving by transmission of parity bits based on the error correction ability of the LDPC channel decoder, because we can know bit error rate and positions of error bit in encoder side. Experimental results show that the proposed algorithm achieves bit-saving by around 66% and delay of feedback channel, compared with the convntional algorithm.

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.4
• /
• pp.87-94
• /
• 2007

Imbalances in focus, luminance and color between stereo Pairs could cause disparity vector estimation error and increment of transmission data. If the distribution of errors in residual image is large, it may influence to lowering of compression performance. Therefore, in this paper, we propose an efficient balancing method between stereo pairs to reduce the effect. For this, we registrated stereo images using a FFT based method to consider the pixels in the occluded region, we eliminated the pixels of blocks which has large error of disparity vector estimation in balancing function estimation. The balancing function has estimated using histogram specification, local information of target image and residual image between stereo images. Experiments show that the proposed method is effective in error distribution, PSNR and disparity vector estimation. We expect that our method can be improving compression efficiency in stereo coding system.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.10
• /
• pp.1887-1894
• /
• 2016

In the RFID system, the reader transmits a query message to tags in order to identify a unique ID of tags within its detection range. The procedures for arbitrating a collision is essential because the multiple tags can response simultaneously in the same to the query of the Reader. This procedure is known as conflict resolution algorithm and it is a key technology in the RFID system. In this paper, we proposed a variable bits M-ary QT algorithm based on Manchester coding techniques. The proposed algorithm use the location information of the collision bits in the reader and tags. The proposed algorithm can reduce the number of the query-response cycle because it is capable of recognizing discontinuous bits and a variable number of bits. From computer simulation, the proposed method give better performance than the conventional M-ary QT techniques in terms of response, recognition efficiency, communication overhead.