Vegetation Detection Approach Based on Gaussian Kernel Support Vector Machinein Unstructured Road Environment
ZHOU Zhiyu1, YANG Ming1, XUE Linji1, WANG Chunxiang2, WANG Bing1
1. Shanghai Key Lab of Navigation and Location Based Services, Department of Automation, Shanghai Jiao Tong University, Shanghai 200240, China;
2. Research Institute of Robotics, Shanghai Jiao Tong University, Shanghai 200240, China
Unstructured road environment is variable and unstable, but vegetation on both sides of road is more remarkable, which can be used to confine impassable area. In complex outdoor environment, vegetation area detection is vulnerable to multiple disturbance factors such as weather, shadow, road condition, and so on, resulting in detection error. Therefore a method of vegetation detection based on Gaussian kernel SVM(support vector machine) is proposed. Firstly, the sample feature of multidimensional color space is analyzed and learned through the sparse representation based on superpixel. Then, classification criteria are created for effectively absorbing vegetation information. Also, grid probability filtering are used to optimize testing results and improve the detection accuracy. Experiments show that the approach excellently solves the vegetation detection problem in unstructured road environment, which is of strong anti-interference ability facing the changing lighting and road condition, and has superior real-time performance and reliability. In practical applications, impassable regions on road are effectively restricted, ensuring the security area of the intelligent mobile robot in complicated road environment.
[1] Alvarez J M, Lopez A M. Combining priors, appearance, and context for road detection[J]. IEEE Transactions on Intelligent Transportation Systems, 2013, 15(3):1168-1178.[2] Nguyen D V, Kuhnert L, Thamke S, et al. A novel approach for a double-check of passable vegetation detection in autonomous ground vehicles[C]//15th IEEE International Conference on Intelligent Transportation Systems. Piscataway, USA:IEEE, 2012:230-236.[3] Nguyen D V, Kuhnert L, Jiang T, et al. Vegetation detection for outdoor automobile[C]//IEEE International Conference Guidance on Industrial Technology. Piscataway, USA:IEEE, 2011:358-364.[4] Bradley D M, Unnikrishnan R, Bagnell J. Vegetation detection for driving in complex environments[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2007:503-508.[5] Zhao Y P, Wang H, Yan R C. Unstructured road edge detection and initial positioning approach based on monocular vision[C]//AASRI Conference on Computational Intelligence and Bioinformatics. Amsterdam, Netherlands:Elsevier Science, 2012:486-491.[6] Salim N N A, Cheng X, Xiao D G. Improved shadow removal for unstructured road detection[C/OL]//Proceedings of the International Conference on Image Processing, Computer Vision, and Pattern Recognition. 2013:1-5.[2015-01-01]. http://worldcomp-proceedings.com/proc/p2013/IPC4037.pdf.[7] Gu Y J, Jin Z. Grass detection based on color features[C]// Proceedings of Chinese Conference on Pattern Recognition. Piscataway, USA:IEEE, 2010:1-5.[8] Ren X, Malik J. Learning a classification model for segmentation[C]//9th IEEE International Conference on Computer Vision. Piscataway, USA:IEEE, 2003:10-17.[9] Achanta R, Shaji A, Smith K. SLIC superpixels compared to state-of-the-art superpixel methods[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(11):2274-2282. [10] Yang W L, Wang Y, Vahdat A, et al. Kernel latent SVM for visual recognition[C/OL]//Advances in Neural Information Processing Systems. 2012:809-817.[2015-01-01]. http://www.researchgate.net/publication/268291907_Kernel_Latent_SVM_for_Visual_Recognition.[11] Jose C, Goyal P, Aggrwal P. Local deep kernel learning for efficient non-linear SVM prediction[C]//Proceedings of the 30th International Conference on Machine Learning. Berkeley, USA:Microtome Publishing, 2013:486-494.[12] Pal B. Support vector machine and random forest modeling for intrusion detection system[J]. Journal of Intelligent Learning Systems and Applications, 2014, 6(1):45-52. [13] Amer M, Goldstein M, Abdennadher S. Enhancing one-class support vector machines for unsupervised anomaly detection[C]//Proceedings of the ACM SIGKDD Workshop on Outlier Detection and Description. New York, USA:ACM, 2013:8-15.[14] Manikandan J, Venkataramani B. Diminishing learning based SVM classifier with non-linear kernels[C]//Electronic Design International Conference. Piscataway, USA:IEEE, 2008:1-6.[15] Davis J, Goadrich M. The relationship between precision-recall and ROC curves[C]//23rd International Conference on Machine Learning. New York, USA:ACM, 2006:233-240.
