臺灣博碩士論文加值系統

近幾年車輛安全月來越受到人們的重視，其中車輛智慧監控系統為近期發展的重點。隨著各式各樣的監控系統技術逐漸成熟，人們將研究方向延伸到了行車安全監控系統。在眾多車輛監控系統中，360度環場影像監控為目前首要發展目標。本研究提出了一個方法來建立360度環場鳥瞰監控系統；此方法包含了魚眼攝影機支校正、鳥瞰視角轉換及環場影像縫合，並將此環場影像監控系統移植至Android嵌入式系統因其具有低成本及攜帶性佳等特性。為了增進系統計算效能，將前述過程結合成一個步驟並建立一個座標參照表；並且利用多執行緒技術加速執行速度。經過硬體實作與實驗評估，我們所提出的環車監控系統能滿意地達到12fps的即時影片輸出效能，並且平均誤差率只有2.89像素。近年來，車輛安全監控技術正快速發展，本方法能夠幫助駕駛人更清晰地了解車輛周圍環境，如此一來，某些因盲點導致的車輛碰撞意外即可避免，舉例來說，一位駕駛在打開車門的同時並未發現有一輛機車正巧接近，而導致意外的發生。本文所提出的系統可以架設在車輛上以避免碰撞意外的發生以降低行車事故發生率並提升交通安全性。

Traffic safety has become a priority in recent years, and therefore, the field of intelligent transportation surveillance systems has become a major field of research. Among vehicle surveillance systems, the 360° around view monitor (AVM) system is regarded as the development direction recently. In this paper, an approach to constructing a 360° bird's-eye-view around view monitor system is proposed; the approach involves rectifying four fisheye cameras and stitching together the four calibrated images obtained from the cameras into one surrounding view image on a low-cost and high portability Android embedded system. To improve the computation performance, the aforementioned procedures are combined into a single step construction mapping using table lookup mechanism and multithreading technique. Through hardware implementation and experiments evaluation, the proposed AVM system performs satisfactorily with surrounding view video output frame rate 12 fps and the average matching error is as low as 2.89 pixel.

Abstract i
Contents ii
1 Introduction 1
1.1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.2 Related Literature . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
1.2.1 Rectication . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
1.2.2 Bird's-eye-view transformation . . . . . . . . . . . . . . . . . . . . . . 4
1.2.3 Image stitching . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
1.2.4 Around view monitoring . . . . . . . . . . . . . . . . . . . . . . . . . 7
1.3 Thesis Organization . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
2 Surrounding Image Construction 10
2.1 Rectication . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11
2.2 Bird's-Eye-View Transformation . . . . . . . . . . . . . . . . . . . . . . . . . 12
2.3 Image Stitching . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14
3 Embedded System Implementation 16
3.1 Hardware System Architecture . . . . . . . . . . . . . . . . . . . . . . . . . . 16
3.2 Performance Optimization . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
4 Experimental Results 21
4.1 Calibration Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21
4.2 Results of Bird's-Eye-View Transformation . . . . . . . . . . . . . . . . . . . 22
4.3 Obtaining 360◦ Surrounding View Image . . . . . . . . . . . . . . . . . . . . 23
4.4 Real-time Stitching Performance and Precision . . . . . . . . . . . . . . . . . 25
4.5 AVM System Performance Comparison . . . . . . . . . . . . . . . . . . . . . 27
5 Conclusions and Future Work 32
5.1 Conclusions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 32
5.2 Future Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33

[1] Keiji Ueminami, Kenji Hayase, and Eiji Sato. Multi-around monitor system. Mitsubishi Motors Technical Review, (19):55~58, 2007.
[2] Philip Koopman. Embedded system security. Computer, 37(7):95~97, 2004.
[3] Dean M Tullsen, Susan J Eggers, and Henry M Levy. Simultaneous multithreading: Maximizing on-chip parallelism. In ACM SIGARCH Computer Architecture News, volume 23, pages 392~403. ACM, 1995.
[4] Nissan Rogue AVM. Nissan Taiwan.
[5] Chunxiang Wang, Hengrun Zhang, Ming Yang, Xudong Wang, Lei Ye, and Chunzhao Guo. Automatic parking based on a bird's eye view vision system. Advances in Mechanical Engineering, 2014, 2014.
[6] Carlos Ricolfe-Viala, Antonio-Jose Sanchez-Salmeron, et al. Lens distortion models evaluation. Applied Optics, 49(30):5914~5928, 2010.
[7] Haijiang Zhu, Xuejing Wang, and Chong Yi. An elliptical function model for sheye camera correction. In Intelligent Control and Automation (WCICA), 2011 9th World Congress on, pages 248~253. IEEE, 2011.
[8] Frederic Devernay and Olivier Faugeras. Straight lines have to be straight. Machine vision and applications, 13(1):14~24, 2001.
[9] Frederic Devernay and Olivier D Faugeras. Automatic calibration and removal of distortion from scenes of structured environments. In SPIE's 1995 International Symposium on Optical Science, Engineering, and Instrumentation, pages 62~72. International Society for Optics and Photonics, 1995.
[10] Tarak Gandhi and Mohan M Trivedi. Motion based vehicle surround analysis using an omni-directional camera. In Intelligent Vehicles Symposium, 2004 IEEE, pages 560~565. IEEE, 2004.
[11] Tobias Ehlgen and Tomas Pajdla. Monitoring surrounding areas of truck-trailer combinations. In Proceedings of the 5th International Conference on Computer Vision Systems, 2007.
[12] Andrew W Fitzgibbon. Simultaneous linear estimation of multiple view geometry and lens distortion. In Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference on, volume 1, pages I~125. IEEE, 2001.
[13] David Claus and Andrew W Fitzgibbon. A rational function lens distortion model for general cameras. In Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, volume 1, pages 213~219. IEEE, 2005.
[14] David Claus and AndrewWFitzgibbon. A plumbline constraint for the rational function lens distortion model. In BMVC, 2005.
[15] Din-Chang Tseng, Ching-Chun Huang, and Tat-Wa Chao. Vision-based parking guidance with adaptive isometric transformation. 2013.
[16] Massimo Bertozzi and Alberto Broggi. Gold: A parallel real-time stereo vision system for generic obstacle and lane detection. Image Processing, IEEE Transactions on, 7(1):62~81, 1998.
[17] Ho Gi Jung, Dong Suk Kim, Pal Joo Yoon, and Jaihie Kim. Parking slot markings recognition for automatic parking assist system. In Intelligent Vehicles Symposium, 2006 IEEE, pages 106~113. IEEE, 2006.
[18] Ho Gi Jung, Yun Hee Lee, Dong Suk Kim, and Pal Joo Yoon. Stereo vision based advanced driver assistance system. In Workshop, pages 97~104, 2005.
[19] Massimo Bertozzi, Alberto Broggi, Paolo Medici, Pier Paolo Porta, and Agneta Sjogren. Stereo vision-based start-inhibit for heavy goods vehicles. In Intelligent Vehicles Symposium, 2006 IEEE, pages 350~355. IEEE, 2006.
[20] Massimo Bertozz, Alberto Broggi, and Alessandra Fascioli. Stereo inverse perspective mapping: theory and applications. Image and Vision Computing, 16(8):585~590, 1998.
[21] Aseem Agarwala, Mira Dontcheva, Maneesh Agrawala, Steven Drucker, Alex Colburn, Brian Curless, David Salesin, and Michael Cohen. Interactive digital photomontage. In ACM Transactions on Graphics (TOG), volume 23, pages 294~302. ACM, 2004.
[22] Dan B Goldman and Jiun-Hung Chen. Vignette and exposure calibration and compensation. In Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on, volume 1, pages 899~906. IEEE, 2005.
[23] J Javier Yebes, Pablo F Alcantarilla, Luis M Bergasa, A Gonzalez, and J Almazan. Surrounding view for enhancing safety on vehicles. In Proceedings of Workshop Perception in Robotics, as part of the IEEE Intelligent Vehicles Symposium, 2012.
[24] Richard Szeliski. Computer vision: algorithms and applications. Springer Science & Business Media, 2010.
[25] Richard Szeliski and Heung-Yeung Shum. Creating full view panoramic image mosaics and environment maps. In Proceedings of the 24th annual conference on Computer graphics and interactive techniques, pages 251~258. ACM Press/Addison-Wesley Publishing Co., 1997.
[26] Heung-Yeung Shum and Richard Szeliski. Panoramic image mosaics. Technical report, Citeseer, 1997.
[27] Peter J Burt and Edward H Adelson. A multiresolution spline with application to image mosaics. ACM Transactions on Graphics (TOG), 2(4):217~236, 1983.
[28] Yi-Yuan Chen, Yuan-Yao Tu, and Cheng-Hsiang Chiu. An embedded system for vehicle surrounding monitoring. In Power Electronics and Intelligent Transportation System (PEITS), 2009 2nd International Conference on, volume 2, pages 92~95. IEEE, 2009.
[29] Takaaki Sato, Alessandro Moro, Atsushi Sugahara, Tsuyoshi Tasaki, Atsushi Yamashita, and Hajime Asama. Spatio-temporal bird's-eye view images using multiple sh-eye cameras. In System Integration (SII), 2013 IEEE/SICE International Symposium on, pages 753~758. IEEE, 2013.
[30] Nissan Rogue AVM. Nissan.
[31] Utech AVM. Utech.
[32] Honda Multi-View Camera System.
[33] Luxgen 360 degree Surround View.
[34] Inniti AVM. Inniti Tw.
[35] Yi-Fu Chen et al. A bird-view surrounding monitor system for parking assistance. Institute of Computer Science and Information Engineering, National Central University, 2008.