JBE Vol Research Articles

DCT와 Guided 필터를 이용한 실시간 영상 분류

In this paper, we present a novel segmentation method that can extract new foreground objects from a current frame in real-time. It is performed by detecting differences between the current frame and reference frame taken from a fixed camera. We minimize computing complexity for real-time video processing. First DCT (Discrete Cosine Transform) is utilized to generate rough binary segmentation maps where foreground and background regions are separated. DCT shows better result of texture analysis than previous methods where texture analysis is performed in spatial domain. It is because texture analysis in frequency domain is easier than that in special domain and intensity and texture in DCT are taken into account at the same time. We maximize run-time efficiency of DCT by considering color information to analyze object region prior to DCT process. Last we use Guided filter for natural matting of the generated binary segmentation map. In general, Guided filter can enhance quality of intermediate result by incorporating guidance information. However, it shows some limitations in homogeneous area. Therefore, we present an additional method which can overcome them. Keyword : DCT, matting, segmentation, Guided Filter a) 경희대학교 전자정보대학 (Kyung Hee University) b) kt 융합기술원 (kt fusion technology institute) ‡Corresponding Author : 김원하(Wonha Kim) E-mail: hjk1017@ssu.ac.kr Tel: +82-2-826-9063 ※ 본 연구는 산업통상지원부의 재원으로 산업핵심기술개발사업의 지원을 받아 수행 되었습니다.(10052967, 재난재해 대응용 특수목적기계 통합제어시스 템 개발) ・Manuscript received August 17, 2015; revised September 22, 2015; accepted September 22, 2015. 특집논문 (Special Paper) 방송공학회논문지 제20권 제5호, 2015년 9월 (JBE Vol. 20, No. 5, September 2015) http://dx.doi.org/10.5909/JBE.2015.20.5.718 ISSN 2287-9137 (Online) ISSN 1226-7953 (Print) 신현학 외 2인 : DCT와 Guided 필터를 이용한 실시간 영상 분류 719 (Hyunhak Shin et al.: Video Segmentation Using DCT and Guided Filter in real time)

방송 및 개인 콘텐츠 편집을 위한 온라인 콘텐츠 편집 시스템

! # $%&'() *+,. *+%- $./%012%& 12!3#4567 89$:;  ?,. @A $,)(BCD |*}~fP,. AbstractIn this paper, we propose a new online content editing system to edit the broadcasting and personal contents. The proposed editing system consists of the content management server and the content editor, in which the content management server is used for storing the contents, while the content editor is used for editing the contents via the user interface. Unlike the existing content editing methods which edit the downloaded contents, the proposed editing system edits the contents stored in the content management server while the content editor plays them by using the streaming technology. However, it is not effective to edit the whole segments of contents while playing them by using the streaming technology. To resolve the problem, the proposed editing system performs the scene detection of the contents, and the detected scene information is used for playing and editing of contents. After completing the content editing, the edited information is uploaded to the content management server as a metadata format. In the proposed editing system, both scene and edited information are represented only as the metadata format, and the physical content segmentation according to the scene and edited information is not performed. The implementation results show that the proposed editing system provides similar performances with the existing content editing methods which use the content download and editing methods.Keyword : Online, Content Editing, Editing System, Broadcasting Contents, Personal Contents€ (Regular Paper)} ‚ w*20ƒ*4„, 2015 7†(JBE Vol. 20, No. 4, July 2015)http://dx.doi.org/10.5909/JBE.2015.20.4.619ISSN 2287-9137 (Online) ISSN 1226-7953 (Print)

무선 인지 중계 네트워크에서 이차 사용자의 중계기가 에너지 하베스팅을 사용할 때 처리량을 최대화하기 위한 최적의 하베스팅 시간 분배 방법

 2345)6789:; ?(@A8BC2D. $E4FG 23HIJHK:LMNO@PQ(D. %R)SM*+C6(time switching, TS) TCU, (power splitting, PS) 27D. VWX3  ;<C= 'Y 2  $) *+ ,-8./ 4F(D.  8*+C62 Z=:<[:LMNO;<\@C]^8D. _*)!# $%&'Z  *+ $)&(D. `aO*bcd 9YJ;G *+ 8.e<DVWX4F(./SMf($) *+ 8ghi_*)!# Aj k lD.AbstractEnergy harvesting technique is an energy charging technique for communication device in energy-constrained environment. Recently, energy harvesting technique that harvests energy from wireless radio frequency signal is proposed. Representatively, there are time switching technique and power splitting technique. This paper proposes an optimal harvesting time allocation scheme in a wireless cognitive relay network when secondary user relay uses energy harvesting technique to transmit information. Secondary user relay receives information and energy simultaneously from the secondary user source’s signal via time switching technique. We aim to maximize the instantaneous throughput by optimizing harvesting time of the secondary user relay. Simulation results show that using optimized harvesting time gets larger instantaneous throughput compared to using constant harvesting time.Keyword : Energy harvesting, time switching, cognitive radio, amplify-and-forward relayingmnWX(Special Paper).=opqWX420r42L, 2015s3t(JBE Vol. 20, No. 2, March 2015)http://dx.doi.org/10.5909/JBE.2015.20.2.215ISSN 2287-9137 (Online) ISSN 1226-7953 (Print)

상위깊이의 Sub-CU 부호화 정보를 이용한 HEVC의 고속 PU 결정 기법

HEVC(High Efficiency Video Coding)-'./012345678(CU: Coding Unit)9:CU; ?@8(PU: Prediction Unit) A !, B-CD$EFG)/CU 45679PU H1 # IFGJKLMBNONPQ-ERSTUV WXYZA- ZQ=. [ ;<-$STU \]^_$`  =abZ PU H1!# $%N c =. def% LCUsub-CBF(Coded Block Flag)  Agh'CU;<PU H1 7$# AgPU ijN! =. kef% LRl(Intra) ?@! AgCUsub-Intra B-CDm N Agh';<Rl?@Nno =. p q% FG-Rl?@! Agh'CUsub-CBF Irs AgA;<Rl?@Nno =. tu#v c% LHM 14.0 wm::1.2%, 0.11%, 0.9%BD-rate YZ;31.4%, 2.5%, 23.4%^x\]Mv ONPQy=. cz3Z % LRx{Rl?@;/ |-}FG#~Ag/ PQF€, ‚1.9%BD-rate YZ;34.2%^x\] Oy=.AbstractHEVC (High Efficiency Video Coding) achieves high coding efficiency by employing a quadtree-based coding unit (CU) block partitioning structure and various prediction units (PUs), and the determination of the best CU partition structure and the best PU mode based on rate-distortion (R-D) cost. However, the computation complexity of encoding also dramatically increases. In this paper, to reduce such encoding computational complexity, we propose three fast PU mode decision methods based on encoding information of upper depth as follows. In the first method, the search of PU mode of the current CU is early terminated based on the sub-CBF (Coded Block Flag) of upper depth. In the second method, the search of intra prediction modes of PU in the current CU is skipped based on the sub-Intra R-D cost of upper depth. In the last method, the search of intra prediction modes of PU in the lower depth’s CUs is skipped based on the sub-CBF of the current depth’s CU. Experimental results show that the three proposed methods reduce the computational complexity of HM 14.0 to 31.4%, 2.5%, and 23.4% with BD-rate increase of 1.2%, 0.11%, and 0.9%, respectively. The three methods can be applied in a combined way to be applied to both of inter prediction and intra prediction, which results in the complexity reduction of 34.2% with 1.9% BD-rate increase. Keywords : HEVC, fast encoding, CU, PU, fast mode decision, sub-CBF ( (Regular Paper) 20 2, 20153(JBE Vol. 20, No. 2, March 2015)http://dx.doi.org/10.5909/JBE.2015.20.2.340ISSN 2287-9137 (Online) ISSN 1226-7953 (Print)

SIMD 명령어 기반 HEVC RExt 복호화기 고속화

In this paper, we introduce the fast decoding method with the SIMD (Single Instruction Multiple Data) instructions for HEVC RExt (High Efficiency Video Coding Range Extensions). Several tools of HEVC RExt such as intra prediction, interpolation, inverse-quantization, inverse-transform, and clipping modules can be classified as the proper modules for applying the SIMD instructions. In consideration of bit-depth increasement of RExt, intra prediction, interpolation, inverse-quantization, inversetransform, and clipping modules are accelerated by SSE (Streaming SIMD Extension) instructions. In addition, we propose effective implementations for interpolation filter, inverse-quantization, and clipping modules by utilizing a set of AVX2 (Advanced Vector eXtension 2) instructions that can use 256 bits register. The evaluation of the proposed methods were performed on the private HEVC RExt decoder developed based on HM 16.0. The experimental results show that the developed RExt decoder reduces 12% average decoding time, compared with the conventional sequential method. Keyword : HEVC, RExt, HEVC Range extensions, SIMD, Parallelization 특집논문 (Special Paper) 방송공학회논문지 제20권 제2호, 2015년 3월 (JBE Vol. 20, No. 2, March 2015) http://dx.doi.org/10.5909/JBE.2015.20.2.224 ISSN 2287-9137 (Online) ISSN 1226-7953 (Print) 목정수 외 3인 : SIMD 명령어 기반 HEVC RExt 복호화기 고속화 225 (Jung-Soo Mok et al.: SIMD Instruction-based Fast HEVC RExt Decoder)

깊이맵 업샘플링을 이용한 객관적 메트릭과 3D 평가의 비교

89:; ?@(ABCDEF'GHIJ K. (LM8NOPC, QRS(3D NOT%UV W'XK. PSNR Y( !#$Z;(LM &'[\, ]L@NOPC8^ !&'E_B`NOTaGb!c;DEd+ K. ef(^ !&'Ig!h!fi jk;[Ilmn, of( !#$8p!qrZ;st!puv wxyK. z:`^ !&'{|8C WE' I !#$^ !&'E}O~pXKmGA jk;[I^ !&''€jk[K. EB‚ n`IKƒ !#$%3D ^ !&'+( WEd+ en,  #$n„l ^ &'{C W'|8 !#$ K. @(LM †s[„BKƒ ‡dPCaˆ‡dPC&'#$‰  [ŠK. ^ !&'IDSCQS NOPC‹Œ#;pŽK. ‘’(C W(“ a”• _B`, SSIM%Edge-PSNR^ !&'E}O~pXI!– !#$— ˜™ _B`šF[ŠK.AbstractDepth map upsampling is an approach to increase the spatial resolution of depth maps obtained from a depth camera. Depth map quality is closely related to 3D perception of stereoscopic image, multi-view image and holography. In general, the performance of upsampled depth map is evaluated by PSNR (Peak Signal to Noise Ratio). On the other hand, time-consuming 3D subjective tests requiring human subjects are carried out for examining the 3D perception as well as visual fatigue for 3D contents. Therefore, if an objective metric is closely correlated with a subjective test, the latter can be replaced by the objective metric. For this, this paper proposes a best metric by investigating the relationship between diverse objective metrics and 3D subjective tests. Diverse reference and no-reference metrics are adopted to evaluate the performance of upsampled depth maps. The subjective test is performed based on DSCQS test. From the utilization and analysis of three kinds of correlations, we validated that SSIM and Edge-PSNR can replace the subjective test.Keyword : Depth map, Upsampling, Objective metric, 3D subjective test, Correlation ›œ (Special Paper) 20 2, 20153(JBE Vol. 20, No. 2, March 2015)http://dx.doi.org/10.5909/JBE.2015.20.2.204ISSN 2287-9137 (Online) ISSN 1226-7953 (Print)

IEEE 802.11n의 2-레벨 집적 방식에서 최소 MPDU 시작 간격을 이용하는 새로운 재전송 방법

IEEE 802.11n 23456789:%; ?@AB @(MAC) CD6A-MSDU(Aggregate-MAC Service Data Unit)EA-MPDU(Aggregate-MAC Protocol Data Unit)FG%HIJ. KLM(, A-MPDU&3G*+;NO$%;P A-MSDUQJ56789RNQ#HIJ. STUA-MPDUV3G*+;NO$WXYA-MPDU Z[MPDU\;V MPDU !\;QJ 6MPDU]^&_>(dummy) MPDU.`ab(delimiter)cV(.d*+efghP 789i%jk#lm%noJ. pXk; qrs%;<%=A-MPDU Z[MPDU\;V MPDU !\;QJ 6]^A-MPDU Z[MPDUV`ab(Ftu2- , ;{*+, 6e|A-MPDU}r~*+€%HI~  ‚%&*+, &*+ƒ#„\;V MPDU !\;QJ 6]^- MSDU†‡*+MSDU†ˆ‰%=*+€dJ. pX ‚d*+, #;{*+, QJ_Š6789RNV‹J.AbstractIn IEEE 802.11n WLANs(Wireless Local Area Networks), to support high throughput, MAC(Media Access Control) layer adopts A-MSDU(Aggregate-MAC Service Data Unit) and A-MPDU(Aggregate-MAC Protocol Data Unit). Generally, as the A-MPDU uses a selective retransmission capability, A-MPDU provides higher throughput than A-MSDU. However, although A-MPDU uses the selective re-transmission capability, if the size of MPDU within A-MPDU is smaller than the size of minimum MPDU starting spacing, A-MPDU can reduce throughput because of the overhead of retransmission owing to the addition of delimiter, that is a dummy MPDU. Therefore, to overcome the above problem, two-level Aggregation method, where the small MPDU within A-MPDU is replaced by not delimiter but A-MSDU, has been introduced. In the two-level Aggregation method, the existing re-transmission scheme retransmits only A-MPDU, but if the size of retransmission data is smaller than the size of the minimum MPDU starting spacing, the proposed retransmission scheme retransmits the aggregated retransmission data and MSDUs. Therefore, we know that the proposed retransmission scheme have better throughput that the existing retransmission scheme.Keywords: IEEE 802.11n, A-MPDU, A-MSDU, Retransmission, Two-level Aggregation, ThroughputŒ (Regular Paper) 20 2, 20153(JBE Vol. 20, No. 2, March 2015)http://dx.doi.org/10.5909/JBE.2015.20.2.300ISSN 2287-9137 (Online) ISSN 1226-7953 (Print)

안드로이드 기반 자연과학 교육용 디지털 앱북 개발을 위한 사용자 상호작용 라이브러리

The digital app-book is an advanced form of the electronic book (e-book), which attracts a lot of interests by the help of video, sound, sensors and a variety of interactions. As mobile devices have evolved, the demand of digital app-books is also rising substantially. However, the distribution of digital app-book contents is hard to meet the demand because the digital app-book requires a lot of programming cost for the interaction. To resolve this problem, Was verified and implementation as a library function of the interaction between device and user. The proposed library consists of three parts (user action recognition, device action, and content action) and provides various user-device interaction functions by combining methods of each part, which can support source code reusability, easy understanding and availability, and wide expandibility. The library was used in the development of natural science education app-book contents. As a result, it could reduce a lot of code lines and facilitate more rapid app-book development. Keyword : E-Book, Digital App-Book, Mobile Application 정규논문 (Regular Paper) 방송공학회논문지 제20권 제1호, 2015년 1월 (JBE Vol. 20, No. 1, January 2015) http://dx.doi.org/10.5909/JBE.2015.20.1.110 ISSN 2287-9137 (Online) ISSN 1226-7953 (Print) 이강운 외 2인 : 안드로이드 기반 자연과학 교육용 디지털 앱북 개발을 위한 사용자 상호작용 라이브러리 111 (Kang-Woon Lee et al. : User Interaction Library for Natural Science Education Digital App-Book on Android Platform)

이용자의 UHDTV에 대한 인지된 유용성과 용이성이 UHD 채택에 미치는 영향에 관한 연구

(# )*+,-.)/012 3456UHDTV748 .'9:;UHD , , UHD ?@AB CD4EFG$ HI CJK1LMNOP. #QRSTUV56W.+XUHDTV.WY'4UHDTV 01Z4[+\].^_+\`P. (#Q abc de RUHD  . UHDTV!f 7, gh i)j 3456, 2!klm.no_pqD\]. Rhn\P. AbstractThis study looks deep into how user’s individual personality and his or her media experiences affect perceived usefulness and perceived ease of use about UHDTV based on Technology Acceptance Model using survey methodology. This study also focuses on how the purchase intention of terminal equipments and the willingness to pay for UHD contents will make different choices. The result of this study shows that, whether user is an exhibitionist or not or has frequently encountered a big screen, these factors affect both the perceived usefulness and the perceived ease of use about UHDTV. When user is an exhibitionist with more experience with big screens, it was clear that user tended to choose UHDTV with higher perception of usefulness and ease of use about UHDTV. This study also implies that when supplying the next generation broadcasting service, it is needed to consider the users' perceived usefulness and ease of use about UHD as well as the individuals' media experiences and characteristics.Keyword : UHDTV, UHD, Technology Acceptance Model, perceived ease, Perceived use2r(Special Paper) 20 1 , 2015 1(JBE Vol. 20, No. 1, January 2015)http://dx.doi.org/10.5909/JBE.2015.20.1.48ISSN 2287-9137 (Online) ISSN 1226-7953 (Print)

공통경보프로토콜을 대한민국 경보시스템에 적용하기 위한 프로파일 요구사항 연구

When a disaster occurs, effective alerts will reduce human life and property loss. The Integrated Emergency Alert System is a national disaster management system which integrates existing alert systems to deliver effective disaster alerts. Alert message exchange protocol is the essential technology for the System. In Korea, the first specification for “Common Alerting Protocol Profile for Integrated Emergency Alert System” was established in 2014. In this paper, we derive two additional requirements for more enhanced alert service and propose revision of the specification: multilingual alert service for foreigners and more flexible representation of target area. We review the associated foreign profile specifications as well as the domestic specifications to analyze these requirements. Finally, we propose the most efficient way to deliver multilingual alert message and to represent target area. Keyword : Emergency Alert System(EAS), Common Alerting Protocol(CAP) 특집논문 (Special Paper) 방송공학회논문지 제19권 제6호, 2014년 11월 (JBE Vol. 19, No. 6, November 2014) http://dx.doi.org/10.5909/JBE.2014.19.6.847 ISSN 2287-9137 (Online) ISSN 1226-7953 (Print) 848 방송공학회논문지 제19권 제6호, 2014년 11월 (JBE Vol. 19, No. 6, November 2014)

패럴랙스 배리어를 사용한 무안경식 휴대용 3차원 디스플레이의 수평위치에 따른 크로스톡 및 3차원 시각 피로의 측정과 모형 구축

The 3D technology has been spread slowly and the reason would be attributed to the fact that most commercialized 3D displays require 3D glasses. There have been various researches on human factors of glass type 3D display. In this study we measured and modeled crosstalk as well as 3D visual fatigue induced by mobile glassless 3D display. Crosstalk as well as visual fatigue varied depending on horizontal position of the 3D mobile display. Measured crosstalk was relative low around the center of the display and it increased at the side of the display. Similar results were found in the measurement of 3D visual fatigue and discomfort. These results imply that human factors should be considered in the process of design and evaluation of mobile 3D displays. Keyword : Mobile 3D display, glassless, crosstalk, horizontal position 정규논문 (Regular Paper) 방송공학회논문지 제19권 제2호, 2014년 3월 (JBE Vol. 19, No. 2, March 2014) http://dx.doi.org/10.5909/JBE.2014.19.2.215 ISSN 2287-9137 (Online) ISSN 1226-7953 (Print) 216 방송공학회논문지 제19권 제2호, 2014년 3월 (JBE Vol. 19, No. 2, March 2014)

소프트웨어 기반 실시간 HEVC 인코더 구현을 위한 병렬화 기법에 관한 연구

ISO/IEC MPEG+ITU-T VCEG!,-./JCT-VC (Joint Collaborative Team on Video Coding)01)2 3HEVC (High Efficiency Video Coding)4H.264/AVC 567289:;!% ?@A1.1)0BCDE. FGH, IJK2L40MN OP<Q+RSKTUVW <XYZ[04\]^_`abc-.GKCdeE. HEVC  <XYZ2f g FhEidjkdlmn!bC de-o, djkdlm-.pqe4jZr%H-.HEVC  </stF 4uv!eE. wxay4R1)0z{|HEVC  <FhSIMD }~2!!€q) , CPU GPU2!‚ƒ„ † +‡:Ei  E. ˆ, !‰ nHEVC  KF ^KŠ ‹ ŒŽ5Fh E. w ybHM (HEVC reference model) 10.0K+832×480 ‘%<’“20~30fps<TUjZ2o”•-–, 1920×1080 ‘%<’“5~10fps<TUjZ2o”—DE.AbstractJoint Collaborative Team on Video Coding (JCT-VC), which have founded ISO/IEC MPEG and ITU-T VCEG, has standardized High Efficiency Video Coding (HEVC). Standardization of HEVC has started with purpose of twice or more coding performance compared to H.264/AVC. However, flexible and hierarchical coding block and recursive coding structure are problems to overcome of HEVC standard. Many fast encoding algorithms for reducing computational complexity of HEVC encoder have been proposed. However, it is hard to implement a real-time HEVC encoder only with those fast encoding algorithms. In this paper, for implementation of software-based real-time HEVC encoder, data-level parallelism using SIMD instructions and CPU/GPU multi-threading methods are proposed. And we also proposed appropriate operations and functional modules to apply the proposed methods on HM 10.0 software. Evaluation of the proposed methods implemented on HM 10.0 software showed 20-30fps for 832×480 sequences and 5-10fps for 1920×1080 sequences, respectively. Keyword : HEVC, encoder, real-time, parallelization˜#xa(Regular Paper)™,š›xaGb18œb6U, 201311ž(JBE Vol. 18, No. 6, November 2013)http://dx.doi.org/10.5909/JBE.2013.18.6.835ISSN 2287-9137 (Online) ISSN 1226-7953 (Print)

디지털 홀로그램 비디오를 위한 인터랙티브 서비스 시스템의 프로토타입 설계

-./0   1234 5678495:; 842?@A43?@$/  84BC, DE FG, HI, JK, 2L, M@NO5 PQR=STO=. 0AUVW5X;8Y WZ[\84 5 84 +]^_5`a8S34E, ^_5[UVWZ[\84T$W$Obcd8S,  <&efgh=. -./Z4 ij+]&5`a84 5k)8l, Z4E FG5mno, mnopIB qN$bO, r stu^$ vwxy, z{W$cd, cd, |B qN}~€Z $M@^_5`a=. 67 5k)NBC 5cd8S|B qZ[$ 5M@84E‚ƒ352msT„j †<l, |B qM@PL}~€M@1‡ˆ4ƒ183ms{ „j †=.AbstractThe purpose of this paper is to propose a service system for a digital hologram video, which has not been published yet. This system assumes the existing service frame for 2-dimensional or 3-dimensional image/video, which includes data acquisition, processing, transmission, reception, and reconstruction. This system also includes the function to service the digital hologram at the viewer’s view point by tracking the viewer’s face. For this function, the image information at the virtual view point corresponding to the viewer’s view point is generated to get the corresponding hologram. Here in this paper, only a prototype that includes major functions of it is implemented, which includes camera system for data acquisition, camera calibration and image rectification, depth/intensity image enhancement, intermediate view generation, digital hologram generation, and holographic image reconstruction by both simulation and optical apparatus. The proposed prototype system was implemented and the result showed that it takes about 352ms to generate one frame of digital hologram and reconstruct the image by simulation, or 183ms to reconstruct image by optical apparatus instead of simulation.Keyword : digital hologram video, computer-generated hologram (CGH), interactive system, prototype, intermediate view point image generation O‰./(Regular Paper)ŠK‹~Œ./61764, 2012Ž7(JBE Vol. 17, No. 4, July 2012)http://dx.doi.org/10.5909/JBE.2012.17.4.695

정밀하지 않은 깊이정보와 2D움직임 정보를 이용한 사용자 검출과 주요 신체부위 추정

‘$%&’'()$*+,-. //01234. 56789:; $%&?@ABCDE$FG2H'IJK=LM*NOPQRH4. S LMK7T / / U [`abc(KdR, 3D 1D eBaf>&ghABij].K-kl, mT  >noZ RfpabKdIJ)$q4. r IJK7WXYK7'2D s t 3D u -)vk>w 'IJ)$q4. jxy$qzT IJ 2D {) 'IJK|}[`ab~cfpKdR, * Z p<KZ T )2P€ 4. r$qz I J 2D s t { Gp<‚ ƒK=„* R, †_ 'IJ [`:fpK‡ˆ3‰)Š~h)ZG2H4.Abstract'Gesture' is the most intuitive means of communication except the voice. Therefore, there are many researches for method that controls computer using gesture input to replace the keyboard or mouse. In these researches, the method of user detection and main body parts estimation is one of the very important process. in this paper, we propose user objects detection and main body parts estimation method on inaccurate depth information for pose estimation. we present user detection method using 2D and 3D depth information, so this method robust to changes in lighting and noise and 2D signal processing 1D signals, so mainly suitable for real-time and using the previous object information, so more accurate and robust. Also, we present main body parts estimation method using 2D contour information, 3D depth information, and tracking. The result of an experiment, proposed user detection method is more robust than only using 2D information method and exactly detect object on inaccurate depth information. Also, proposed main body parts estimation method overcome the disadvantage that can`t detect main body parts in occlusion area only using 2D contour information and sensitive to changes in illumination or environment using color information.Keyword : Depth Information, Object Detection, Body Parts Estimation‹ XY(Regular Paper)IŒŽXY $17$4e, 2012‘7’(JBE Vol. 17, No. 4, July 2012)http://dx.doi.org/10.5909/JBE.2012.17.4.611