汽車產業經過一百多年來的發展，最重要的引擎科技已大致驅近於完美階段，很難再有快速的進步。因此很多車廠皆將焦點放在，行駛的主動與被動安全之上。汽車環景補助系統是近年來頗受關注的行車安全輔助系統。汽車環景補助系統，是借由安裝環繞在汽車周圍四個到六個攝影機，將這些攝影機所取得的影像接合成一個能顯示汽車周圍環境的環景圖。希望提供駕駛人一個沒有視線死角的汽車周遭景物資訊，對於狹路會車，避免碰撞，以及停車的方便性，皆提供了適當的幫助。本研究的目標為探討，如何將裝在汽車周圍的攝影機所拍攝的廣角或魚眼影像，接合成一個汽車環景影像。並在環景影像上標記距離刻度，讓駕駛人可以參考車身與週遭之物件之間的距離。為實驗方便，本研究使用一個由角鋼組成的台車，其上裝四個魚眼攝影機，以模擬一台裝設四個攝影機的汽車，實作一個環景行車補助系統。駕駛者可借由本系統提供的環景影像，辦別汽車周圍的環境。

Under hundred year’s development, the engine technology of auto industry is very difficult to have substantial improvement. Today, most of the vehicle industries are concerned about the active and passive safety systems. Car surround view system is one of the passive safety systems recent years concerned to provide the driver with the information around the car. A car surround system usually uses 4 to 6 cameras installed around the vehicle, the images from these cameras are stitched to obtain a 360° surround view which can show the environment around the vehicle. The goal of this study is to develop a car surround view system based on homography transformation. The system is consisted of four fish-eye cameras each with 170 degrees of field of view, which are installed around the car. The four distorted images are corrected and then stitched to obtain a 360° surround view around the car to provide the driver with the environment information around the vehicle. A scale system is also marked to provide the distance information for the driver.

[1]林信宏 (102). "以專利分析探討車輛全周影像發展趨勢." 新新季刊 第四十三卷(第一期): 104.
[2]Shan, H. (2013). 單應性矩陣於多視角深度影像繪圖修補演算法之研究與實現. 成功大學電腦與通信工程研究所學位論文, 1-73.
[3]Bradski, G. and A. Kaehler (2008). Learning OpenCV: Computer vision with the OpenCV library, " O'Reilly Media, Inc.".
[4]Brown, M., & Lowe, D. G. (2007). Automatic panoramic image stitching using invariant features. International journal of computer vision, 74(1), 59-73.
[5]D. Chen and G. Zhang, “A new sub-pixel detector for x-corners in camera
calibration targets,” WSCG Short Papers (2005): 97–100
[6]D. C. Brown, “Close-range camera calibration,” Photogrammetric Engineering 37 (1971): 855–866
[7]Dubrofsky, E. (2009). Homography estimation, UNIVERSITY OF BRITISH COLUMBIA (Vancouver.
[8]H. Sawhney and R. Kumar. True multi-image alignment and its application to mosaicing and lens distortion correction. IEEE Transactions on Pattern Analysis and
[9]I. Zoghlami, O. Faugeras, and R. Deriche. Using geometric corners to build a 2D mosaic from a set of images. In Proceedings of the International Conference on Computer Vision and Pattern Recognition, Puerto Rico. IEEE, June 1997.
[10]L. Lucchese and S. K. Mitra, “Using saddle points for subpixel feature de-
tection in camera calibration targets,” Proceedings of the 2002 Asia Pacifi c Confer-ence on Circuits and Systems (pp. 191–195), December 2002.
[11]M. Irani and P. Anandan. About direct methods. In B. Triggs, A. Zisserman, and R. Szeliski, editors, Vision Algorithms: Theory and Practice, number 1883 in LNCS, pages 267–277. Springer-Verlag, Corfu, Greece, September 1999.
[12]Monitor provides a virtual 360-degree scene of the car in bird's-eye view (無日期) 2016年01月25日 取自Nissan 網站
http://www.nissan-global.com/EN/TECHNOLOGY/OVERVIEW/avm.html
[13]OCamCalib: Omnidirectional Camera Calibration Toolbox for Matlab (無日期)
https://sites.google.com/site/scarabotix/ocamcalib-toolbox
[14]P. McLauchlan and A. Jaenicke. Image mosaicing using sequential bundle adjustment. Image and Vision Computing, 20(9-10):751–759, August 2002.
[15]R. Szeliski and S. Kang. Direct methods for visual scene reconstruction. In IEEE Workshop on Representations of Visual Scenes, pages 26– 33, Cambridge, MA, 1995.
[16]Scaramuzza, D., Martinelli, A., & Siegwart, R. (2006, January). A flexible technique for accurate omnidirectional camera calibration and structure from motion. In Computer Vision Systems, 2006 ICVS'06. IEEE International Conference on (pp. 45-45). IEEE.
[17]Szeliski, R., & Shum, H. Y. (1997, August). Creating full view panoramic image mosaics and environment maps. In Proceedings of the 24th annual conference on Computer graphics and interactive techniques (pp. 251-258). ACM Press/Addison-Wesley Publishing Co..