高华, 赵春霞, 韩光. 基于one-class SVM与融合多可视化特征的可通行区域检测[J]. 机器人, 2011, 33(6): 731-735,741..
GAO Hua, ZHAO Chunxia, HAN Guang. Traversable Region Detection Based on One-class SVM and Multi-visual Features Fusion. ROBOT, 2011, 33(6): 731-735,741..
For the difficulty in obtaining the complete non-traversable region samples,a traversable region detection method based on one-class SVM(support vector machine) is proposed to improve the adaptability of algorithms in different scenes.This article formulates traversability detection as a one-class classification problem for the first time.An improved feature extraction method is proposed with the fusion of color and texture.Image data of every color channels are transformed by discrete cosine transform(DCT),then the DCT coefficients are decomposed using pyramid decomposition.Mean and variance in each decomposition are used to describe characteristic window.Traversable region pattern is generated by training the traversable samples using one-class SVM.Experiments show that the algorithm recognizes new data well,and performs with high detection accuracy and low abused detection rate.
[1] Casta(n)o R,Manduchi R,Fox J.Classification experiments on real-world textures[C]//3rd Workshop on Empirical Evaluation Methods in Computer Vision.Pasadena,CA,USA:Jet Propulsion Laboratory,National Aeronautics and Space Administration,2001:1-20.
[2] Shi X J,Manduchi R.On the Bayes fusion of visual features[J]. Image and Vision Computing,2007,25(11):1748-1758.
[3] Kim D S,Oh S M,Rehg J M.Traversability classification for UGV navigation:A comparison of patch and superpixel representations[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems.Piscataway,NJ,USA:IEEE,2007:3166-3173.
[4] Dima C,Hebert M,Stentz A.Enabling learning from large datasets:Applying active learning to mobile robotics[C]//IEEE International Conference on Robotics and Automation.Piscataway,NJ,USA:IEEE,2004:i08-114.
[5] Kim D S,Sun J,Oh S M,et al.Traversability classification using unsupervised on-line visual learning for outdoor robot navigation[C]//IEEE International Conference on Robotics and Automation.Piscataway,N J,USA:IEEE,2006:518-525.
[6] Sch(o)lkopf B,Platt J C,Shawe-Taylor J S,et al.Estimating the support of a high-dimensional distribution[J]. Neural Computation,2001,13(7):1443-1471.
[7] Permuter H,Francos J,Jermyn I.A study of Gaussian mixture models of colour and texture features for image classification and segmentation[J]. Pattern Recongnition,2006,39(4):695-706.
[8] Sung G Y,Kwak D M,Kim D J,et al.Terrain cover classification based on wavelet feature extraction[C]//Internationai Conference on Control,Automation and Systems.Piscataway,NJ,USA:IEEE,2008:203-207.
