한국차 례 제 15 권제 2 호 2017 년 2 월 Big Data/Cloud Computing, - --, ReLU ELM, Embedded System/Robotics SFM DC-DC Fail-Safe, Future Network/Mobile Communication 3 ADC Signal Processing/IoT IoT Almanac, SUMO VANET A Case Study on the Propagation Interference Effect of the LLZ/GP Facility : Modeling and Basic Materials Research IT Convergence/Platform,,,, KMS,,, Dominant CS-LBP A Comparative Study on TVWS Regulation Policy: the U.S., the U.K., and South Korea, 경북대학교 IP: 155.***.17.165 Accessed 2017/03/01 20:49(KST)
CONTENTS Vol. 15, No. 2 Feb. 2017 Big Data/Cloud Computing A Study on the Direction of Light Using Intensity Distribution in Single Image Je-Jin Ryu, Hong-Ki Min Design of Master-Slave-Slave Replication Model to Balance Master Overhead for Key-value Database Kyung-Tae Song, Sang-Hyun Park Image Classification Using Convolutional Neural Network and Extreme Learning Machine Classifier Based on ReLU Function Jung-Soo Han, Keun-Chang Kwak Embedded System/Robotics Design of DC-DC Converter for Light-Load with Variable Output Voltage Using SFM Hak-Yun Kim, Myeong-Hak Lee, Young-Ho Shin, Ho-Yong Choi Implementation of Fail-Safe During Drone's Flight Hyung-Su Kim, Young-Hwan Han Improvement of Luminous Efficiency in AC Plasma Display Panel with Long Distance between Top Plate Electrodes Seung Seob Park, Byung-Gwon Cho A Study on Discharge Delay Time in AC Plasma Display Panel with Linear Gray Scale Byung-Gwon Cho Future Network/Mobile Communication Strategies to Reduce Isolated Node Ratio for Wireless Sensor Networks with Mobile Sink Bongsue Suh Development of the ADC for Mobile Communication Repeater with in 3 Delay Time Jong-Dae Park A Cell-Based Mobility Model for Mobile Ad-hoc Networks Backhyun Kim, Kyeongmo Park Signal Processing/IoT A Secure Almanac Synchronization Method for Open IoT Maritime Cloud Environment Donghyeok Lee, Namje Park Performance Comparison of Routing Protocols in Vehicular Ad Hoc Networks(VANET) Using SUMO Ye-Eun Chae, Seung-Seok Kang A Performance Evaluation of Post-Processing Algorithms for Disparity Refinement of Stereo Vision Jongkil Hyun, Ingyu Lee, Byungin Moon A Case Study on the Propagation Interference Effect of the LLZ/GP Facility : Modeling and Basic Materials Research Kwangsik Cho, Joungil Moon, Yoonsik Kwak, Kyujoung Park IT Convergence/Platform Electromagnetic Transmission Characteristics of Eco-friendly Foamed Concrete Wall Sung-Sil Cho, Jae-Seong Yu, Jin-Man Kim, Ic-Pyo Hong Analysis of the Relationship between the Type of Experience and Blog Texts Hyung Jun Ahn, Youngmok Ha Influence of Organizational Factors and Knowledge Informational Factors of KMS, and Suitability of a Strategy on System Performance Seon-Gyu Yi Phase Mapping Recognition and Modulation Classification Algorithm Using New Higher-order Cumulants Jaeyoon Lee, Seongjin Ahn, Junwon Choi, Dongweon Yoon Face Recognition Based on Dominant CS-LBP Dong-Jin Kwon, Un-Dong Chang A Comparative Study on TVWS Regulation Policy: the U.S., the U.K., and South Korea Maeng-Joo Lee, Boon-Yeon Kim 경북대학교 IP: 155.***.17.165 Accessed 2017/03/01 20:49(KST)
현종길 *, 이인규 *, 문병인 ** 2016. 요약 Abstract Stereo vision is a technique of extracting disparities from a stereo image pair and calculating three-dimensional distance information. Stereo vision is an active research field because it can be used in various applications. Most studies of stereo vision have been focusing on the matching process and paying little attention to the post-processing process which plays a significant role in improving disparity accuracy. Thus, this paper divides the post-processing algorithms into three groups and evaluates and analyzes their performance. According to the experimental results, the left-right consistency check shows the best performance compared with other seed pixel detection methods, the 2-way interpolation method is more efficient than the 1-way interpolation method, and the weight median filter shows outstanding performance to improve disparity accuracy while preserving edge information of disparity maps. Keywords stereo vision, post-processing, disparity refinement, seed pixel, hole filling, filter ) ž Received: Jan. 25, 2017 Revised: Feb. 12, 2017, Accepted: Feb. 15, 2017 ž Corresponding Author: Byungin Moon School of Electronics Engineering, Kyungpook National University, 80 Daehakro, Bukgu, Daegu 41566, Korea, Tel.: +82-53-950-7580, Email: bihmoon@knu.ac.kr
100 2 3. (RADAR) (LIDAR),, [1]-[4]., [5][6]. / (Disparity) (Triangulation),, (Matching), [7]. / [8], /.. (Seed Pixel), (Hole Filling),. [9]. - (Left-Right Consistency Check)[10]-[12] (Uniqueness Check)[13]- [15], (Cost Confidence Check)[16][17].. (Occlusion)., [9][11][12]. [18][19], (Weighted Median Filter)[20][21], - (Joint-Bilateral Filter)[18][22]..,.,, [23]... 2,,. 3 2,. 4.. - /. - /, - (1). - 0. otherwise (1)
(1) ( ).. /.,,.,. ± ± otherwise (2) ( ), 1 (Index). (2)., [23].,,. (3). otherwise (3),. (3) (Scanline) [24].,.,..,., [9][25].., 2 (Mask),.,. (Speckle Noise) [21]., [26]. (Euclidean). exp exp (4)
102 (4) ( ) ( ), ( ), ( ). 3 3, [2, 1, 3; 3, 1, 4; 7, 5, 6], 1.,. [21].. -., -. - [18][22]. -. - (5). (5) (4), ( ), ( ), ( ), (5) 2,. SAD(Sum of Absolute Differences)[27], CT(Census Transform)[28], ASW(Adaptive Support-Weight)[29]. ASW 7 7 (Matching Window) (Color Similarity) 13 (Geometric Proximity) 31. (Middlebury Stereo Datasets) [30] Cones Teddy. 1. Noc, All.
2 3. 2 3, SAD, CT, ASW (CNF), - (LRC). - (UNQ),. SAD. SAD (Absolute Differences),. SAD.. 2 13 13 ASW -,. 2. 2, -, -.. 4 5 13 13. ( 4 5 1-way) ( 4 5 2-way),
104, -., -., -. 13 13 ASW, -. 6 7 Cones Teddy. 6 7, -. (Smoothing),. - (4), (5)., -.., -,,. 13 13 SAD, CT, ASW -, 6.47%., - 9 9
0.78%., -, 7.25%.,,.,,. -,.,..,., -,. -,,.,. [1] W. Van Der Mark and D. M. Gavrila, "Real-Time Dense Stereo for Intelligent Vehicles", IEEE Transactions on Intelligent Transportation Systems, Vol. 7, No. 1, pp. 38-50, Mar. 2006. [2] T. N. Nguyen, B. Michaelis, A. Al-Hamadi, M. Tornow, and M. M. Meinecke, "Stereo-Camera- Based Urban Environment Perception Using Occupancy Grid and Object Tracking", IEEE Transactions on Intelligent Transportation Systems, Vol. 13, No. 1, Mar. 2012. [3] J. I. Woodfill, G. Gordon, and R. Buck, "Tyzx DeepSea High Speed Stereo Vision System", 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshop, Vol. 3, pp. 41-41, Jun. 2004. [4] S. Kwon, J. S. Kim, Y. H. Kim, and Y. H. Lee, "Architecture and Design of Real-Time Depth Map Extraction Hardware Using Stereo Vision", Journal of KIIT, Vol. 12, No. 2, pp. 163-171, Feb. 2014. [5] R. Okuda, Y. Kajiwara, and K. Terashima, "A Survey of Technical Trend of ADAS and Autonomous Driving", 2014 International Symposium on VLSI Technology, Systems and Application, pp. 1-4, Apr. 2014. [6] G. H. Lee, F. Fraundorfer, and M. Pollefeys, "Motion Estimation for Self-Driving Cars with A Generalized Camera", IEEE Conference on Computer Vision and Pattern Recognition, pp. 2746-2753, Jun. 2013. [7] C. Banz, S. Hesselbarth, H. Flatt, H. Blume, and P. Pirsch, "Real-Time Stereo Vision System Using Semi-Global Matching Disparity Estimation: Architecture and FPGA-Implementation", 2010 International Conference on Embedded Computer Systems, pp. 93-101, Jul. 2010. [8] A. Fusiello, E. Trucco, and A. Verri, "A Compact Algorithm for Rectification of Stereo Pairs", Machine Vision and Applications, Vol. 12, No. 1, pp. 16-22, Jul. 2000. [9] X. Sun, X. Mei, S. Jiao, M. Zhou, and H. Wang, "Stereo Matching with Reliable Disparity Propagation", 2011 International Conference on 3D Imaging, Modeling, Processing, Visualization and
106 Transmission, pp. 132-139, May 2011. [10] K. Muhlmann, D. Maier, J. Hesser, and R. Manner, "Calculating Dense Disparity Maps from Color Stereo Images, An Efficient Implementation", International Journal of Computer Vision, Vol. 47, No. 1, pp. 79-88, Apr. 2002. [11] R. A. Hamzah, H. Ibrahim, and A. H. A. Hassan, "Stereo Matching Algorithm Based of Illumination Control to Improve The Accuracy", Image Analysis & Stereology, Vol. 35, No. 1, pp. 39-52, 2016. [12] C. Ttofis and T. Theocharides, "High-Quality Real-Time Hardware Stereo Matching Based on Guided Image Filtering", Proceedings of The Conference on Design, Automation & Test in Europe, pp. 1-6, Mar. 2014. [13] L. D. Stefano, M. Marchionni, and S. Mattoccia, "A Fast Area-Based Stereo Matching Algorithm", Image and Vision Computing, Vol. 22, No. 12, pp. 983-1005, Oct. 2004. [14] C. L. Zitnick and T. Kanade, "A Cooperative Algorithm for Stereo Matching and Occlusion Detection", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 22, No. 7, pp. 675-684, Jul. 2000. [15] P. Zicari, S. Perri, P. Corsonello, and G. Cocorullo, "Low-Cost FPGA Stereo Vision System for Real Time Disparity Maps Calculation", Microprocessors and Microsystems, Vol. 36, No. 4, pp. 281-288, Jun. 2012. [16] X. Hu and P. Mordohai, "A Quantitative Evaluation of Confidence Measures for Stereo Vision", IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol. 34, No. 11, pp. 2121-2133, Nov. 2012. [17] H. Hirschmuller, P. R. Innocent, and J. Caribaldi, "Real-Time Correlation-Based Stereo Vision with Reduced Border Errors", International Journal of Computer Vision, Vol. 47, No.1, pp. 229-246, Apr. 2002. [18] J. Zbontar and Y. LeCun, "Computing The Stereo Matching Cost with A Convolutional Neural Network", IEEE Conference on Computer Vision and Pattern Recognition, pp. 1592-1599, Jun. 2015. [19] H. Jiang, R. Gao, and X. Liu, "Research of Stereo Matching Based on Improved Median Filter", Communication Systems and Information Technology, Vol. 100, pp. 479-486, 2011. [20] L. Yin, R. Yang, M. Gabbouj, and Y. Neuvo, "Weighted Median Filters: A Tutorial", IEEE Transactions on Circuits and Systems Ⅱ: Analog and Digital Signal Processing, Vol. 43, No. 3, pp. 157-192, Mar. 1996. [21] S. Choi, J. C. Jeong, J. Chang, H. Shin, E. G. Lim, J. I. Cho, and D. Hwang, "Implementation of Real-Time Post-Processing for High-Quality Stereo Vision", ETRI Journal, Vol. 37, No. 4, pp. 752-765, Aug. 2015. [22] A. Ansar, A. Castano, and L. Matthies, "Enhanced Real-Time Stereo Using Bilateral Filtering", International Symposium on 3D Data Processing, Visualization and Transmission, pp. 455-462, Sep. 2004. [23] H. Hirschmuller and D. Scharstein, "Evaluation of Cost Functions for Stereo Matching", IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-8, Jun. 2007. [24] L. De-Maeztu, A. Villanueva, and R. Cabeza, "Stereo Matching Using Gradient Similarity and Locally Adaptive Support-Weight", Pattern Recognition Letters, Vol. 32, No. 13, pp. 1643-1651, Oct. 2011. [25] C. Rhemann, A. Hosni, M. Bleyer, C. Rother, and M. Gelautz, "Fast Cost-Volume Filtering for Visual Correspondence and Beyond", IEEE Conference on Computer Vision and Pattern Recognition, pp. 3017-3024, Jun. 2011. [26] T. W. Bae and S. I. Lee, "An Iterative Bilateral Weighted Median Filter for The Removal of High-Density Impulse Noise", Journal of KIIT, Vol. 8, No. 2, pp. 59-65, Feb. 2010.
[27] S. Perri, D. Colonna, P. Zicari, and P. Corsonello, "SAD-Based Stereo Matching Circuit for FPGAs", International Conference on Electronics, Circuits and Systems, pp. 846-849, Dec. 2006. [28] R. Zabih and J. Woodfill, "Non-Parametric Local Transforms for Computing Visual Correspondence", Proceedings of the Third European Conference on Computer Vision, Vol. 2, pp. 151-158, May 1994. [29] K. J. Yoon and I. S. Kweon, "Adaptive Support- Weight Approach for Correspondence Search", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 28, No. 4, pp. 650-656, Apr. 2006. [30] D. Scharstein and R. Szeliski, "High-Accuracy Stereo Depth Maps Using Structured Light", IEEE Conference on Computer Vision and Pattern Recognition, Vol. 1, pp. 195-202, Jun. 2003. 문병인 (Byungin Moon) 현종길 (Jongkil Hyun) 이인규 (Ingyu Lee)