Vegetation detection and terrain classification for autonomous navigation

Diese Arbeit beleuchtet sieben neuartige Ansatze aus zwei Bereichen der maschinellen Wahrnehmung: Erkennung von Vegetation und Klassifizierung von Gelande. Diese Elemente bilden den Kern eines jeden Steuerungssystems fur effiziente, autonome Navigation im Ausenbereich. Bezuglich der Vegetationserkennung, wird zuerst ein auf Indizierung basierender Ansatz beschrieben (1), der die reflektierenden und absorbierenden Eigenschaften von Pflanzen im Bezug auf sichtbares und nah-infrarotes Licht auswertet. Zweitens wird eine Fusionmethode von 2D/3D Merkmalen untersucht (2), die das menschliche System der Vegetationserkennung nachbildet. Zusatzlich wird ein integriertes System vorgeschlagen (3), welches die visuelle Wahrnehmung mit multi-spektralen Methoden ko mbiniert. Aufbauend auf detaillierten Studien zu Farb- und Textureigenschaften von Vegetation wird ein adaptiver selbstlernender Algorithmus eingefuhrt der robust und schnell Pflanzen(bewuchs) erkennt (4). Komplettiert wird die Vegetationserkennung durch einen Algorithmus zur Befahrbarkeitseinschatzung von Vegetation, der die Verformbarkeit von Pflanzen erkennt. Je leichter sich Pflanzen bewegen lassen, umso groser ist ihre Befahrbarkeit. Bezuglich der Gelandeklassifizierung wird eine struktur-basierte Methode vorgestellt (6), welche die 3D Strukturdaten einer Umgebung durch die statistische Analyse lokaler Punkte von LiDAR Daten unterstutzt. Zuletzt wird eine auf Klassifizierung basierende Methode (7) beschrieben, die LiDAR und Kamera-Daten kombiniert, um eine 3D Szene zu rekonstruieren. Basierend auf den Vorteilen der vorgestellten Algorithmen im Bezug auf die maschinelle Wahrnehmung, hoffen wir, dass diese Arbeit als Ausgangspunkt fur weitere Entwicklung en von zuverlassigen Erkennungsmethoden dient. This thesis introduces seven novel contributions for two perception tasks: vegetation detection and terrain classification, that are at the core of any control system for efficient autonomous navigation in outdoor environments. Regarding vegetation detection, we first describe a vegetation index-based method (1), which relies on the absorption and reflectance properties of vegetation to visual light and near-infrared light, respectively. Second, a 2D/3D feature fusion (2), which imitates the human visual system in vegetation interpretation, is investigated. Alternatively, an integrated vision system (3) is proposed to realise our greedy ambition in combining visual perception-based and multi-spectral methods by only using a unit device. A depth study on colour and texture features of vegetation has been carried out, which leads to a robust and fast vegetation detection through an adaptive learning algorithm (4). In addition, a double-check of passable vegetation detection (5) is realised, relying on the compressibility of vegetation. The lower degree of resistance vegetation has, the more traversable it is. Regarding terrain classification, we introduce a structure-based method (6) to capture the world scene by inferring its 3D structures through a local point statistic analysis on LiDAR data. Finally, a classification-based method (7), which combines the LiDAR data and visual information to reconstruct 3D scenes, is presented. Whereby, object representation is described more details, thus enabling an ability to classify more object types. Based on the success of the proposed perceptual inference methods in the environmental sensing tasks, we hope that this thesis will really serve as a key point for further development of highly reliable perceptual inference methods.

[1]  David M. Bradley,et al.  Vegetation Detection for Driving in Complex Environments , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[2]  Jun Ohta,et al.  Smart CMOS Image Sensors and Applications , 2007 .

[3]  L. Kuhnert,et al.  A novel approach of terrain classification for outdoor automobile navigation , 2011, 2011 IEEE International Conference on Computer Science and Automation Engineering.

[4]  John Weier and David Herring Measuring Vegetation (NDVI & EVI) : Feature Articles , 2000 .

[5]  C. A. Shull A Spectrophotometric Study of Reflection of Light from Leaf Surfaces , 1929, Botanical Gazette.

[6]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[7]  Roberto Manduchi,et al.  Bayesian fusion of color and texture segmentations , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[8]  Steven Dubowsky,et al.  Terrain estimation for high-speed rough-terrain autonomous vehicle navigation , 2002, SPIE Defense + Commercial Sensing.

[9]  Wolfram Burgard,et al.  Autonomous Terrain Mapping and Classification Using Hidden Markov Models , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.

[10]  R. Crippen Calculating the vegetation index faster , 1990 .

[11]  Markus Ax,et al.  Development of a High Speed 3D Laser Measurement System for Outdoor Robotics , 2011, Eurobot Conference.

[12]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[13]  Cristopher Moore,et al.  Online Terrain Estimation Using Internal Sensors , 2003 .

[14]  John Iselin Woodfill,et al.  Tyzx DeepSea High Speed Stereo Vision System , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[15]  K.-D. Kuhnert Software architecture of the Autonomous Mobile Outdoor Robot AMOR , 2008, 2008 IEEE Intelligent Vehicles Symposium.

[16]  L. Kuhnert,et al.  Cooperation in heterogeneous groups of autonomous robots , 2012, 2012 IEEE International Conference on Mechatronics and Automation.

[17]  Jean Ponce,et al.  General Road Detection From a Single Image , 2010, IEEE Transactions on Image Processing.

[18]  Alex Pentland,et al.  Pfinder: Real-Time Tracking of the Human Body , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[19]  John Townshend,et al.  Multitemporal Dimensionality of Images of Normalized Difference Vegetation Index at Continental Scales , 1985, IEEE Transactions on Geoscience and Remote Sensing.

[20]  Emmanuel G. Collins,et al.  Vibration-based terrain classification using surface profile input frequency responses , 2008, 2008 IEEE International Conference on Robotics and Automation.

[21]  C. Jordan Derivation of leaf-area index from quality of light on the forest floor , 1969 .

[22]  T. M. Lillesand,et al.  Remote Sensing and Image Interpretation , 1980 .

[23]  Markus Ax,et al.  Combining Distance and Modulation Information for Detecting Pedestrians in Outdoor Environment using a PMD Camera , 2010 .

[24]  S. Ullman,et al.  The interpretation of visual motion , 1977 .

[25]  James Lee Hafner,et al.  Efficient Color Histogram Indexing for Quadratic Form Distance Functions , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[26]  Jeff A. Bilmes,et al.  A gentle tutorial of the em algorithm and its application to parameter estimation for Gaussian mixture and hidden Markov models , 1998 .

[27]  V. V. Kumar,et al.  IHBM: Integrated Histogram Bin Matching For Similarity Measures of Color Image Retrieval , 2009 .

[28]  P.H.N. de With,et al.  Grass Field Detection for TV Picture Quality Enhancement , 2008, 2008 Digest of Technical Papers - International Conference on Consumer Electronics.

[29]  Ben Taskar,et al.  Discriminative learning of Markov random fields for segmentation of 3D scan data , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[30]  Stefan Thamke,et al.  A novel approach for a double-check of passable vegetation detection in autonomous ground vehicles , 2012, 2012 15th International IEEE Conference on Intelligent Transportation Systems.

[31]  Martial Hebert,et al.  Natural terrain classification using 3-d ladar data , 2004, IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004.

[32]  G. Baudat,et al.  Kernel-based methods and function approximation , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

[33]  Peter Eisert,et al.  Adaptive color classification for structured light systems , 2008, 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[34]  Larry S. Davis,et al.  W4S : A real-time system for detecting and tracking people in 2 D , 1998, eccv 1998.

[35]  Roberto Manduchi,et al.  Obstacle Detection and Terrain Classification for Autonomous Off-Road Navigation , 2005, Auton. Robots.

[36]  Liang Lu,et al.  Terrain surface classification for autonomous ground vehicles using a 2D laser stripe-based structured light sensor , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[37]  Duong Nguyen,et al.  An Integrated Vision System for Vegetation Detection in Autonomous Ground Vehicles , 2011 .

[38]  Seyed Eghbal Ghobadi,et al.  Real time object recognition and tracking using 2D/3D images , 2010 .

[39]  Lars Kuhnert,et al.  Structure overview of vegetation detection. A novel approach for efficient vegetation detection using an active lighting system , 2012, Robotics Auton. Syst..

[40]  A. Huete,et al.  A Modified Soil Adjusted Vegetation Index , 1994 .

[41]  T. M. Lillesand,et al.  Remote sensing and image interpretation. Second edition , 1987 .

[42]  Daniel P. Huttenlocher,et al.  Efficient Graph-Based Image Segmentation , 2004, International Journal of Computer Vision.

[43]  Zhong Jin,et al.  Grass Detection Based on Color Features , 2010, 2010 Chinese Conference on Pattern Recognition (CCPR).

[44]  李幼升,et al.  Ph , 1989 .

[45]  Joachim Hertzberg,et al.  A 3D laser range finder for autonomous mobile robots , 2001 .

[46]  Karin Sobottka Analysis of low-resolution range image sequences , 2000, DISKI.

[47]  Sebastian Thrun,et al.  Self-supervised Monocular Road Detection in Desert Terrain , 2006, Robotics: Science and Systems.

[48]  Majura F. Selekwa,et al.  Online Terrain Classification for Mobile Robots , 2005 .

[49]  Tao Jiang,et al.  Fitting plane algorithm-based depth correction for Tyzx DeepSea stereoscopic imaging , 2012, 2012 Fourth International Conference on Communications and Electronics (ICCE).

[50]  Xavier Brun,et al.  Modeling and Calibration of Coupled Fish-Eye CCD Camera and Laser Range Scanner for Outdoor Environment Reconstruction , 2007, Sixth International Conference on 3-D Digital Imaging and Modeling (3DIM 2007).

[51]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[52]  Ibrahim Halatci Vision-based terrain classification and classifier fusion for planetary exploration rovers , 2006 .

[53]  R.S.Sabeenian,et al.  Texture Based Weed Detection Using Multi Resolution Combined Statistical and Spatial Frequency (MRCSF) , 2009 .

[54]  A. Huete A soil-adjusted vegetation index (SAVI) , 1988 .

[55]  Jitendra Malik,et al.  Large displacement optical flow , 2009, CVPR.

[56]  Wolfram Burgard,et al.  Improving robot navigation in structured outdoor environments by identifying vegetation from laser data , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[57]  Klaus-Dieter Kuhnert,et al.  Terrain classification based on structure for autonomous navigation in complex environments , 2010, International Conference on Communications and Electronics 2010.

[58]  Gary Witus,et al.  Terrain characterization and classification with a mobile robot , 2006, J. Field Robotics.

[59]  Xiannong Meng,et al.  A Study of Color Histogram Based Image Retrieval , 2009, 2009 Sixth International Conference on Information Technology: New Generations.

[60]  Kim L. Boyer,et al.  Linearized vegetation indices based on a formal statistical framework , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[61]  W. Eric L. Grimson,et al.  Using adaptive tracking to classify and monitor activities in a site , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[62]  Christopher Rasmussen,et al.  Grouping dominant orientations for ill-structured road following , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[63]  Aaron C. Courville,et al.  A Generative Model of Terrain for Autonomous Navigation in Vegetation , 2006, Int. J. Robotics Res..

[64]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[65]  Lars Kuhnert,et al.  General vegetation Detection using an Integrated Vision System , 2013, Int. J. Robotics Autom..

[66]  Yi Zhang,et al.  Tree crown detection and delineation in high resolution RS image: a texture approach discussion , 2004, IGARSS 2004. 2004 IEEE International Geoscience and Remote Sensing Symposium.

[67]  C. J. Tucker,et al.  Relationship between atmospheric CO2 variations and a satellite-derived vegetation index , 1986, Nature.

[68]  J. A. Schell,et al.  Monitoring the Vernal Advancement and Retrogradation (Green Wave Effect) of Natural Vegetation. [Great Plains Corridor] , 1973 .

[69]  Kentaro Toyama,et al.  Wallflower: principles and practice of background maintenance , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[70]  David Mumford,et al.  Statistics of range images , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[71]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.

[72]  Jochen Frey,et al.  Robust 3 D Measurement with PMD Sensors , 2005 .

[73]  J. D. Tarpley,et al.  Global vegetation indices from the NOAA-7 meteorological satellite , 1984 .

[74]  Emmanuel G. Collins,et al.  Frequency response method for terrain classification in autonomous ground vehicles , 2008, Auton. Robots.

[75]  Bernd Radig,et al.  The HISCORE camera a real time three dimensional and color camera , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[76]  Johan J. Lukkien,et al.  A parallel algorithm for stereo vision based on correlation , 1996, Proceedings of 3rd International Conference on High Performance Computing (HiPC).

[77]  Alex Pentland,et al.  A Bayesian Computer Vision System for Modeling Human Interactions , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[78]  Michal Haindl Multimodal Range Image Segmentation , 2007 .

[79]  Christopher Rasmussen,et al.  Combining laser range, color, and texture cues for autonomous road following , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[80]  Guoqiang Peter Zhang,et al.  Neural networks for classification: a survey , 2000, IEEE Trans. Syst. Man Cybern. Part C.

[81]  Martial Hebert,et al.  Natural terrain classification using three‐dimensional ladar data for ground robot mobility , 2006, J. Field Robotics.

[82]  Roberto Manduchi,et al.  Ladar-Based Discrimination of Grass from Obstacles for Autonomous Navigation , 2000, ISER.

[83]  A L Rankin,et al.  Daytime Mud Detection for Unmanned Ground Vehicle Autonomous Navigation , 2008 .

[84]  Robert M. Gray,et al.  Image retrieval using color histograms generated by Gauss mixture vector quantization , 2004, Comput. Vis. Image Underst..

[85]  Lars Kuhnert,et al.  Spreading algorithm for efficient vegetation detection in cluttered outdoor environments , 2012, Robotics Auton. Syst..

[86]  Graham D. Finlayson,et al.  Log-opponent chromaticity coding of colour space , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[87]  Xuming Luan,et al.  Experimental investigation of photonic mixer device and development of TOF 3D ranging Ssystems based on PMD technology , 2006 .

[88]  Takeo Kanade,et al.  An Iterative Image Registration Technique with an Application to Stereo Vision , 1981, IJCAI.

[89]  Wolfgang Seemann,et al.  Design and realisation of the highly modular and robust autonomous mobile outdoor robot AMOR , 2007 .

[90]  Nahum Gat,et al.  Imaging spectroscopy using tunable filters: a review , 2000, SPIE Defense + Commercial Sensing.

[91]  S. J. Sutley,et al.  Imaging spectroscopy: Earth and planetary remote sensing with the USGS Tetracorder and expert systems , 2003 .

[92]  Cheng Lu,et al.  On the removal of shadows from images , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[93]  L. Kuhnert,et al.  Vegetation detection for outdoor automobile guidance , 2011, 2011 IEEE International Conference on Industrial Technology.

[94]  Carl A. Moore,et al.  TERRAIN ESTIMATION USING INTERNAL SENSORS , 2004 .

[95]  A. J. Richardsons,et al.  DISTINGUISHING VEGETATION FROM SOIL BACKGROUND INFORMATION , 1977 .

[96]  Siddharth Jain,et al.  A survey of Laser Range Finding , 2003 .

[97]  Gunnar Farnebäck,et al.  Two-Frame Motion Estimation Based on Polynomial Expansion , 2003, SCIA.

[98]  Qingsheng Zhu,et al.  Stereo effect of image converted from planar , 2008, Inf. Sci..

[99]  Christopher Rasmussen,et al.  Laser Range-, Color-, and Texture-based Classiers for Segmenting Marginal Roads , 2001, CVPR 2001.

[100]  M. Amann,et al.  Laser ranging: a critical review of usual techniques for distance measurement , 2001 .