• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.2
• /
• pp.259-265
• /
• 2012

Recently, many research works are focusing on DVC (Distributed Video Coding) system for low complexity encoder. Most DVC systems need feedback channel for parity bit control to achieve the good RD performances, however, this causes the system to have high decoding latency and is considered as one of the most critical problems for real implementation. In order to overcome this problem, this paper proposes an effective distributed video decoding method using adaptive LDPCA frame-based parity bit request estimation. The proposed method applies for the pixel-domain Wyner-Ziv system and exploits the statistical characteristics between adjacent LDPCA frames to estimate adaptively the parity bit request. Through computer simulations, it is shown that the proposed method achieves about 80% of latency reduction compared to the conventional no-estimation DVC system.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39B no.2
• /
• pp.95-101
• /
• 2014

Scalable video coding (SVC) encodes multimedia data into a base layer and enhancement layers to cope with variable network conditions in an adaptive manner. In SVC, enhancement layers can be decoded only when the base layer is successively received. However, existing works on SVC transmissions in IEEE 802.11 WLANs do not fully investigate this characteristic and thus their performance can be degraded. In this paper, we propose a SVC-aware retransmission (SAR) scheme in IEEE 802.11 WLANs. The SAR scheme applies different retransmission policies for base and enhancement layers by obtaining the optimal number of frames to be retransmitted. As a result, the SAR scheme can reduce unnecessary retransmissions and minimize the transmission latency. Simulation results demonstrate that the SAR scheme can reduce unnecessary data transmission by 12.6% and the transmission latency by 6.6~19.1% compared to conventional retransmission schemes.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.23 no.4
• /
• pp.821-835
• /
• 1998

The Digital Audio-Visual Council(DAVIC) that was established to develop useful multimedia communication services has completed the specifications for providing on-demand services such as Movie on Demand(MoD), Teleshopping and accepting Internet service. And then they are proceeding the works to suport converstional communcation services like Plain Old Telecphone Service(POTS), Video telephone, Video teleconferencing. In this paper, we prpose an efficient terminal architecture which can provide conversational multimedia communication services on DAVIC Set-Top Box (STB) environments. To apply the implemented conversational terminal to the multipoint communication environment, we considered the factors of Qurlity of Services(QoS) that determine grade of conversational communication service. We also present the inter-working scheme and that system structure to satisfy QoS by using new MPEG video bridge which gurantees end to end delay requirements as major element of QoS for achieving the real time communication and does not accompany visual quality degradation.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.1
• /
• pp.33-45
• /
• 2011

In this paper, we present a method for extracting video objects efficiently by using the modified graph cut algorithm based on contour information. First, we extract objects at the first frame by an automatic object extraction algorithm or the user interaction. To estimate the objects' contours at the current frame, motion information of objects' contour in the previous frame is analyzed. Block-based histogram back-projection is conducted along the estimated contour point. Each color model of objects and background can be generated from back-projection images. The probabilities of links between neighboring pixels are decided by the logarithmic based distance transform map obtained from the estimated contour image. Energy of the graph is defined by predefined color models and logarithmic distance transform map. Finally, the object is extracted by minimizing the energy. Experimental results of various test images show that our algorithm works more accurately than other methods.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.4 s.36
• /
• pp.113-121
• /
• 2005

Face detection in real-time video constitutes one of the major trend in face recognition. In this paper, we propose a face detection algorithm using the skin color and Haar-like feature in real-time video. The proposed algorithm is followed by three sequences; First, moving objects are detected by difference-method in YCbCr coordinates, and then by using Haar-like features, face candidate regions of the moving objects is selected. Finally we extract the most possible face candidates by comparing the pixel values of face candidates with the skin color. In order to prevent a mistake. we use similar features or skin color to detect a face by selecting a adaptive ROI and improve the processing speed in real-time video. The computer simulation shows the validity of the proposed method that the processing speed is improved by 30% than previous works and the detection success rate is 96.8%.

• Proceedings of the Korea Contents Association Conference
• /
• 2008.05a
• /
• pp.116-120
• /
• 2008

Smart Camera provides intelligent vision functionalities which can interpret captured video, extract context-aware information and execute a necessary action in real-timeliness in addition to the functionality of network cameras which transmit the compressed acquired videos through networks. Intelligent vision algorithms demand tremendous computations so that real-time processing of computation of intelligent vision algorithms as well as compression and transmission of videos simultaneously is too much burden for a single CPU. Davinci processor of Texas Instruments is a popular ASSP(Application Specific Standard Product) which has dual core architecture of ARM core and DSP core and provides various I/O interfaces as well as networking interface and video acquiring interface necessary for developing digital video embedded applications. In this paper, we report the results of designing and implementing S/W for Davinci-based smart camera. We implement a face detection as an example of vision application and verify the implementation works well. In the future, for the development of a smart camera with more broad and real-time vision functionalities, it is necessary to study about more efficient vision application S/W architecture and optimization of vision algorithms on DSP core of Davichi processor.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.2
• /
• pp.355-363
• /
• 2011

Recently, as one of several methods to improve the performance of DVC(Distributed Video Coding) system, many research works are focusing on the iterative refinement of side information. Most of the conventional techniques are mainly based on the relationship between the reconstruction level and side information, or the vector median filtering of motion vectors, but, their performance improvements are restricted. In order to overcome the performance limit of the conventional schemes, in this paper, a side information generation scheme is designed by measuring the block-cost estimation. Then, by adaptively selecting the compensation mode using the received bit-plane information, we propose a block-adaptive iterative refinement which is efficient for non-symmetric moving objects. Computer simulations show that, by using the proposed refinement method, the performance can be improved up to 0.2 dB in rate-distortion.

• Journal of Broadcast Engineering
• /
• v.27 no.4
• /
• pp.561-568
• /
• 2022

Most deep learning-based video object segmentation methods perform the segmentation with past prediction information stored in external memory. In general, the more past information is stored in the memory, the better results can be obtained by accumulating evidence for various changes in the objects of interest. However, all information cannot be stored in the memory due to hardware limitations, resulting in performance degradation. In this paper, we propose a method of storing new information in the external memory without additional memory allocation. Specifically, after calculating the attention score between the existing memory and the information to be newly stored, new information is added to the corresponding memory according to each score. In this way, the method works robustly because the attention mechanism reflects the object changes well without using additional memory. In addition, the update rate is adaptively determined according to the accumulated number of matches in the memory so that the frequently updated samples store more information to maintain reliable information.

• Journal of Korea Society of Industrial Information Systems
• /
• v.14 no.5
• /
• pp.139-148
• /
• 2009

In this paper, I propose an automatic analysis method of golf swine from single-camera video sequences. I define necessary swing features for automatic swing analysis in 2-dimensional environment and present efficient swing analysis methods using various image processing techniques including line and edge detection. The proposed method has two characteristics compared with previous swing analysis systems and related studies. First, the proposed method enables an automatic swing analysis in 2-dimension while previous systems require 3-dimensional environment which is relatively complex and expensive to run. Second, swing analysis is done automatically without human intervention while other 2-dimensional systems necessarily need analysis by a golf expert. I tested the method on 20 swing video sequences and found the proposed method works effective for automatic analysis of golf swing.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.52 no.1
• /
• pp.56-64
• /
• 2016

This study analyzed characteristics of officers' watch-keeping during fishing operation at the fisheries training ship KAYA (GT: 1,737 tons, Pukyong National University). It observed fishing works of three officers in wheel house of KAYA. The observations were carried out at the fishing ground 45 miles away from east of Jeju from 7 to 8 January 2010. The works and movements of the officers were recorded with three common video cameras and a 4-channel MPEG-4 Triplex DVR. Recorded data of the working circulation was analyzed by using the post-processing method. As a result of the traffic lines, the average (${\pm}S.D$) of working hour (min) and moving frequency (times), distance (m) and speed (m/min) during setting the net was 11.8 (0.9), 43.7 (8.1), 133.9 (35.8) and 10.5 (0.6), respectively. During trawling the net, it was 100, 241 (39.8), 615.7 (194.6) and 5.2 (1.6), respectively. During hauling the net, it was 17.6 (1.4), 41.0 (7.2), 196.9 (37.6) and 10.7 (0.8), respectively. In addition, it has a different tendency of the instrument usage frequency by the fishing works. During setting, the usage priority was CCTV, ECDIS, RPM and pitch controller, net monitor, GPS plotter, chart room, X-band radar, fish finder and public addressor. During trawling, it was CCTV, ECDIS, fish finder, X-band radar, net monitor, chart room, GPS plotter, RPM and pitch controller, auto pilot and steering, interphone, wind speed and direction indicator, No.1. VHF, navigation light control panel and public addressor. During hauling, it was CCTV, RPM and pitch controller, GPS plotter, public addressor, chart room, net monitor, X-band radar, auto pilot and steering and fish finder.