跳到主要內容

臺灣博碩士論文加值系統

(3.235.227.117) 您好!臺灣時間:2021/08/01 23:16
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:周博倫
研究生(外文):Po-Lun Chou
論文名稱:區塊式立體匹配結合倒傳遞類神經網路應用於雙眼立體視覺自動車導航
論文名稱(外文):Combination of Block-based Stereo Matching and BPNN Applied to ALV Guidance Using Binocular Stereo Vision
指導教授:駱榮欽駱榮欽引用關係
口試委員:吳明川楊靖宇
口試日期:2012-07-29
學位類別:碩士
校院名稱:國立臺北科技大學
系所名稱:電腦與通訊研究所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2012
畢業學年度:100
語文別:英文
論文頁數:88
中文關鍵詞:立體視覺自動車類神經網路物體偵測
外文關鍵詞:Stereo VisionAutonomous Land VehicleNeural networksObject Detection
相關次數:
  • 被引用被引用:0
  • 點閱點閱:124
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
本論文中,我們提出使用區塊式立體匹配結合倒傳遞類神經網路應用於雙眼立體視覺之室外自動導航車。首先我們將左右影像以區塊式比對,經由不同的區塊大小,比對其對應點的周遭資訊,並藉由區域匹配連續的特性,排除不適當的對應點。接著訓練倒傳遞類神經網路將影像轉換為立體資訊。透過倒傳遞類神經網路誤差收斂後所得到的權重值,反應出左右影像對應點與世界座標的關係。最後將對應點輸入至已學習且收斂的倒傳遞類神經網路,對應的特徵點在實際空間中的位置即可獲得。經過實驗測試結果得知此系統可以實際在室外道路上行走,導航策略也可成功的閃避障礙物,以證明所提方法之可行性。

In this research, a method of 3D environmental reconstruction is proposed and it used the block-based stereo matching and Back-Propagation Neural Network (BPNN) with binocular stereo vision for outdoor Autonomous Land Vehicle (ALV) guidance. In the study, first, we get left and right images from the binocular cameras to train a BPNN to convert both 2D images into 3D information. In addition, an improved point correspondence method based on block matching is also proposed. The inappropriate corresponding points will be excluded from the continuous feature of stereo matching. Finally, the corresponding feature points are inputted to BPNN for learning and the positions in the real world can be obtained by the BPNN. Several experiments show the proposed method is feasible to avoid collision with moving objects while ALV moving on the way.

摘 要......................................................i
ABSTRACT..................................................ii
ACKNOWLEDGMENTS..........................................iii
CONTENTS..................................................iv
LIST OF TABLES............................................vi
LIST OF FIGURES..........................................vii
Chapter 1 INTRODUCTION.....................................1
1.1 Research Motivation....................................1
1.2 Survey of Related Researches...........................2
1.2.1 Stereo Corresponding Methods.........................2
1.2.2 Camera Calibration Methods...........................4
1.3 Overview of Proposed Approaches........................5
1.4 Thesis Organization....................................7
Chapter 2 STEREO CORRESPONDENCE............................8
2.1 Matching Cost Computation..............................9
2.2 Cost Aggregation......................................14
2.3 Disparity computation.................................20
2.4 Disparity optimization................................24
2.4.1 Filter..............................................25
2.4.2 Interpolation.......................................26
Chapter 3 CALIBRATION.....................................30
3.1 Coordinate Transformation.............................30
3.2 Back-Propagation Neural Network.......................32
3.2.1 BPNN Algorithm......................................33
3.2.2 BPNN Learning.......................................38
Chapter 4 Navigation and Obstacle Avoidance...............51
4.1 ALV Hardware Architecture.............................52
4.1.1 Hardware Architecture Overview......................52
4.1.2 Camera..............................................53
4.1.3 Servo Motor.........................................54
4.1.4 DC Motor............................................54
4.1.5 Electric Speed Controller and Battery...............55
4.1.6 Motor Control Board.................................56
4.1.7 Computer System.....................................57
4.2 Combination of Stereo Matching and BPNN...............57
4.3 Navigation of Proposed Approach.......................68
4.4 Experimental Results..................................71
Chapter 5 CONCLUSIONS.....................................75
5.1 Conclusion............................................75
5.2 Further Research......................................76
REFFERENCES...............................................77
APPENDIX..................................................81
A. Proves the formula of camera calibration...............82
B. The Table of BPNN Testing Result.......................85

[1] Rostam Affendi Hamzah, Rosman Abd Rahim and Zarina Mohd Noh, “Sum of Absolute Differences Algorithm in Stereo Correspondence Problem for Stereo Matching in Computer Vision Application,” IEEE Int. Conf. on Computer Science and Information Technology, 2010, Vol.1, pp.652-657.
[2] Qingxiong Yang, Liang Wang, Ruigang Yang, Shengnan Wang, Miao Liao and David Nister, “Real-time Global Stereo Matching Using Hierarchical Belief Propagation,” Proc. Int. Conf. The British Machine Vision Conference, 2006.
[3] Bumsub Ham, Dongbo Min and Kwanghoon Sohn, “Cost Aggregation with Anisotropic Diffusion in Feature Space for Hybrid Stereo Matching,” IEEE Int. Conf. on Image Processing, 2011, pp.3365-3368.
[4] Guangming Xiong, Xin Li, Jianwei Gong, Huiyan and Dah-Jye Lee, “Color Rank and Census Transforms using Perceptual Color Contrast,” IEEE Int. Conf. Control Automation Robotics and Vision, 2010, pp.1225-1230.
[5] Te-Hsiu Sun, “Improving Stereo Matching Quality with Scanline-Based Asynchronous Hopfield Neural Networks,” Journal of the Chinese Institute of Industrial Engineers, Vol. 24, no.1, pp. 50-59, 2007.
[6] Te-Hsiu Sun, “Stereo Matching Using Synchronous Hopfield Neural Network,” Journal of the Chinese Institute of Industrial Engineers, Vol. 26, no.4, pp. 276-288, 2009.
[7] Chia-Horng Huang and Jung-Hua Wang, “Stereo correspondence using Hopfield network with multiple constraints,” IEEE Int. Conf. on Systems, Man and Cybernetics, 2000, Vol. 2, pp. 1518-1523.
[8] Hai-feng Hu and Ping Zhang, “Stereo Matching Using 2-D Hopfield Network with Multiple Constraints,” IEEE Int. Conf. on Artificial Reality and Telexistence--Workshops, 2006, pp. 427-431.
[9] Y. V. Venkatesh, S. Kumar Raja and A. Jaya Kumar, “On the Application of a Modified Self-Organizing Neural Network to Estimate Stereo Disparity,” IEEE Trans. on Image Processing, Vol. 16, pp. 2822-2829, Nov. 2007.
[10] 鄭惟元,以灰色理論為基礎運用立體視覺做室內自動車導航之研究,碩士論文,國立臺北科技大學機電整合研究所,台北,2001。
[11] 林俊佑,應用基因演算法於自動車的攝影機參數校正之研究,碩士論文,國立臺北科技大學機電整合研究所,台北,2000。
[12] 葉哲昌,利用鬆弛相關性改進3D對應點匹配與重建應用於室外自動導航車,碩士論文,國立臺北科技大學自動化科技研究所,台北,2006。
[13] F. Angrilli, S. Bastianello and R. Da Forno, “Calibration of Stereo Vision Systems by Neural Networks,” IEEE Int. Conf. Instrumentation and Measurement Technology, 1996, Vol. 2, pp. 839-842.
[14] Bo Zhao, Zhong-Xiang Zhu, En-Rong Mao and Zheng-He Song, “Vision system calibration of agricultural wheeled-mobile robot based on BP neural network,” IEEE Int. Conf. Machine Learning and Cybernetics, 2007, Vol. 1, pp. 340-344.
[15] Yingjie Xing, Jing Sun and Zhentong Chen, “Analyzing and Improving of Neural Networks used in Stereo Calibration,” IEEE Int. Conf. Natural Computation, 2007, Vol. 1, pp. 745-749.
[16] Liu Wan-Yu and Xie Kai, “A Camera Calibration Method based on Neural Network optimized by Genetic Algorithm,” IEEE Int. Conf. Systems, Man and Cybernetics, 2007, pp. 2748-2753.
[17] Li Guo Jin and Li Guang Rui, “Camera Calibration for Monocular Vision System Based on Harris Corner Extraction and Neural Network,” IEEE Int. Conf. Consumer Electronics, Communications and Networks, 2011, pp. 1-4.
[18] 盧振育,基於立體電腦視覺及人工智慧策略搭配雷射光作室外自動車導航之研究,碩士論文,國立臺北科技大學自動化科技研究所,台北,2004。
[19] 張煜青,以雙眼立體電腦視覺配合人工智慧策略作室外自動車導航之研究,碩士論文,國立臺北科技大學自動化科技研究所,台北,2003。
[20] 樊曉軍,羅熊等,複雜環境下基於蟻群優化算法的機器人路徑規劃,2003,25(5):414~418。
[21] W. Y. Jheng, “A Study on Indoor Autonomous Vehicle Navigation Using Binocular Stereo Vision Based on Grey Approach,” Thesis, Graduate Institute of Mechatronic Engineering, National Taipei University of Technology, Taipei, 2001.
[22] J. Y. Lin, “A Study on Camera Calibration of Autonomous Vehicle Based on Genetic Algorithm,” Thesis, Graduate Institute of Mechatronic Engineering, National Taipei University of Technology, Taipei, 2000.
[23] J. C. Ye, “Using Relaxed Correlation to improve Corresponding of 3D Reconstruction for Outdoor Guidance of Autonoomous Land Vehicle,” Thesis, Graduate Institute of Automation Technology, National Taipei University of Technology, Taipei, 2006.
[24] F. Angrilli, S. Bastianello and R. Da Forno, “Calibration of Stereo Vision Systems by Neural Networks,” IEEE Int. Conf. Instrumentation and Measurement Technology Conference, 1996, Vol. 2, pp. 839-842, doi:10.1109/IMTC.1996.507286.
[25] B. Zhao, Z. X. Zhu, E. R. Mao and Z. H. Song, “Vision System Calibration of Agricultural Wheeled-Mobile Robot Based on BP Neural Network,” IEEE Int. Conf. Machine Learning and Cybernetics, 2007, Vol. 1, pp. 340-344, doi:10.1109/ICMLC.2007.4370166.
[26] Y. Xing, J. Sun and Z. Chen, “Analyzing and Improving of Neural Networks used in Stereo Calibration,” IEEE Int. Conf. Natural Computation, 2007, Vol. 1, pp. 745-749, doi:10.1109/ICNC.2007.240.
[27] L. W. Yu and X. Kai, “A Camera Calibration Method based on Neural Network optimized by Genetic Algorithm,” IEEE Int. Conf. Systems, Man and Cybernetics, 2007, pp. 2748-2753, doi:10.1109/ICSMC.2007.4413930.
[28] T. H. Sun, “Improving Stereo Matching Quality with Scanline-Based Asynchronous Hopfield Neural Networks,” Journal of the Chinese Institute of Industrial Engineers, Vol. 24, no. 1, 2007, pp. 50-59.
[29] T. H. Sun, “Stereo Matching Using Synchronous Hopfield Neural Network,” Journal of the Chinese Institue of Industrial Engineers, Vol. 26, no. 4, 2009, pp. 276-288.
[30] C. H. Huang and J. H. Wang, “Stereo Correspondence Using Hopfield Network with Multiple Constraints,” IEEE Int. Conf. Systems, Man and Cybernetics, Vol. 2, 2000, pp. 1518-1523, doi:10.1109/ICSMC.2000.886071.
[31] H. F. Hu and P. Zhang, “Stereo Matching Using 2-D Hopfield Network with Multiple Constraints,” IEEE Int. Conf. Artificial Reality and Telexistence--Workshops, 2006, pp. 427-431, doi:10.1109/ICAT.2006.118.
[32] Y. V. Venkatesh, S. K. Raja and A. J. Kumar, “On the Application of a Modified Self-Organizing Neural Network to Estimate Stereo Disparity,” IEEE Trans. on Image Processing, Vol. 16, Nov. 2007, pp. 282-2829, doi:10.1109/TIP.2007.906772.


QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊