Computer Vision-Based Multiple-Lane Detection on Straight road and in a Curve
===
###### Yan Jiang1, Feng Gao2, Guoyan Xu3 School of Transportation Science and Engineering, BeiHang University Beijing, China
## Keyword
multiple-lane detection; image processing; curve detection; perspective transformation; computer vision
## Content
設計了一種視覺系統,以“估計和檢測”方案檢測結構化高速公路上的多個車道,檢測車輛行駛的車道(中央車道)並估算兩個相鄰車道的可能位置。首先使用GPS位置和OpenStreetMap數字地圖識別車輛是否在直路或彎道行駛,兩種情況的處理方式有所不同:對於直路,使用霍夫變換在原始圖像中檢測到中心車道在彎道的情況下,進行了完整的透視變換,並通過掃描頂視圖圖像中的每一行來檢測中央車道,該系統能夠檢測到車道標記甚至被其他車輛阻擋。
### 實驗方法
#### 1. 直線與曲線判斷
使用GPS輔助判斷道路是直線還是曲線。
##### 直線的車道偵測
使用霍夫轉換找到鄰近的車道,藉由繪製單一方向的平行線,計算個平行線的角度差找到影像與實際車道的變化量(可將實際寬度轉換為像素差),最後藉由此變化量向外延伸尋找外側車道。

#### 2. 霍夫轉換
先使用Hough Transform做邊緣偵測,之後使用侵蝕與膨脹濾除過小的雜訊。
#### 3. IPM 提取車道線
使用IPM做圖像校正,使圖片中的距離不會依據遠近有大幅誤差,最後使用白色區域的寬度與長度塞選出車道線。

## Review
本篇重點在於多車道辨識,根據車輛GPS位置搭配地圖辨識車子目前位於直線或彎路搭配不同的車道線檢測。直線部分使用霍夫變換檢測中央車道,並設計透視變換恢復多個車道標記平行度。以預估相鄰車道;在彎道處先執行完整的透視變換,通過掃描每一行檢測中央。透過預估與檢測能讓系統能提高相鄰車輛遮擋的鄰道標記。使用圖像處理技術而不是手動測量收集透視轉換參數可以簡化系統安裝,使系統能在行駛過程更新。
## Reference
[1] M. Chen, T. Jochem and D. Pomerleau, “AURORA: a vision- based roadway departure warning system,” in Proc. 1995 IEEE/RSJ International Conference on, vol. 1, pp. 243-248 vol.1, 1995.
[2] B. Wu and C. Lin, “Robust lane detection and tracking for driving assistance systems,” Systems, Man and Cybernetics, 2007. ISIC. IEEE International Conference on, pp. 3848-3853, 2007.
[3] T.-Y. Sun, S.-J Tsai and V. Chan, “HSI color model based lane- marking detection,” Intelligent Transportation Systems Conference, 2006. ITSC '06. IEEE, pp. 1168-1172, 2006.
[4] D. Aubert and C. Thorpe, “Color image processing for navigation: Two road trackers,” Robotics Institute, Carnegie Mellon University, Tech. Rep. CMU-RI-TR-90-09, 1990.
[5] M. Bertozzi and A. Broggi, “GOLD: a parallel real-time stereo vision system for generic obstacle and lane detection,” Image Processing, IEEE Transactions on, vol. 7, pp. 62-81, 1998.
[6] R. Hartley and A. Zisserman, Multiple View Geometry in Computer Vision. Cambridge University Press, 2001.
[7] M. Nieto, L. Salgado, F. Jaureguizar and J. Arrospide, “Robust multiple lane road modeling based on perspective analysis,” Image Processing. ICIP 2008. 15th IEEE International Conference on, pp. 2396-2399, 2008.
[8] P. H. Batavia. “Driver-Adaptive Lane Departure Warning Systems,” Doctoral dissertation, tech. report CMU-RI-TR-99-25. Robotics Institute, Carnegie Mellon University. pp. 33, 1999.
[9] A. Broggi, “Robust real-time lane and road detection in critical shadow conditions,” Computer Vision, 1995. Proceedings. , International Symposium on, pp. 353-358, 1995
###### tags:`Finish` `論文`