Abstract：To solve the problems of complex modeling and low detection accuracy of lane under different environments, a lane detection algorithm was proposed based on row distance and particle filter under complex road conditions. The RGB images were converted to HSV color space, and the inverse perspective transformation image of lane was obtained by vehicles cameras after calibration to calculate the row distance of every pix. The simple lane road model and the particle filter were used to get the location of lane road. The results show that by calculating the row distance of the binary image, the dotted part of lane can be connected, which is beneficial to establish continuous lane context relation and provide running environment for particle filters. By the particle filter algorithm, without establishing strict lane road model, the problem of low robustness in single lane road model under complex urban road conditions can be solved. The proposed algorithm has good robustness under complex environment.
杨金鑫, 范英, 谢纯禄. 基于行距离及粒子滤波的车道线识别算法[J]. 江苏大学学报（自然科学版）, 2020, 41(2): 138-142.
YANG Jinxin, FAN Ying, XIE Chunlu. Lane detection algorithm based on row distance and particle filter[J]. Journal of Jiangsu University(Natural Science Eidtion)
, 2020, 41(2): 138-142.
SUDDAMALLA U, KUNDU S, FARKADE S, et al. A novel algorithm of lane detection addressing varied scenarios of curved and dashed landmarks［C］∥2015 International Conference on Image Processing Theory, Tools and Applications. Piscataway,USA:IEEE, 2015:87-92.
［2］
COLLADO J M,HILARIO C,DE LA ESEALERA A， et al. Adaptive road lanes detection and classification ［J］.Lecture Notes in Computer Scienc,2006,4179(1):1151-1162.
［3］
DENG J Y, HAN Y. A real-time system of lane detection and tracking based on optimized RANSAC B-spline fitting［C］∥Proceedings of the 2013 Research in Adaptive and Convergent Systems,2013:157-164.
［4］
REVILLOUD M, GRUYER D, RAHAL M C. A new multi-agent approach for lane detection and tracking ［C］∥2016 IEEE International Conference on Robotics ＆ Automation. Piscataway,USA:IEEE, 2016:3147-3153.
［5］
PAN X G, SHI J P, LUO P, et al. Spatial as deep: spatial CNN for traffic scene understanding［J］. ar-Xiv preprint arXiv， 2018:1712.06080.
［6］
RUYI J, REINHARD K, TOBI V, et al. Lane detection and tracking using a new lane model and distance transform［J］. Machine Vision and Applications, 2011, 22(4):721-737.
［7］
NIETO M, LABORDA J A, SALGADO L. Road environment modeling using robust perspective analysis and recursive Bayesian segmentation［J］. Machine Vision and Applications, 2011, 22(6):927-945.
［8］
ALY M. Real time detection of lane markers in urban streets［J］. Computer Science,doi:10.1109／IVS.2008.4621152.
［9］
FELZENSZWALB P F, HUTTENLOCHER D P. Distance transforms of sampled functions［J］. Theory of Computing, 2004, 8(19):415-428.
［10］
WANG Y, BAI L, FAIRHURST M. Robust road mo-deling and tracking using condensation［J］. IEEE Tran-sactions on Intelligent Transportation Systems, 2008, 9(4):570-579.
2020, Vol. 41 
