{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T03:13:18Z","timestamp":1767237198635,"version":"build-2065373602"},"reference-count":37,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2012,9,12]],"date-time":"2012-09-12T00:00:00Z","timestamp":1347408000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/3.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Autonomous driving is a challenging problem, particularly when the domain is unstructured, as in an outdoor agricultural setting. Thus, advanced perception systems are primarily required to sense and understand the surrounding environment recognizing artificial and natural structures, topology, vegetation and paths. In this paper, a self-learning framework is proposed to automatically train a ground classifier for scene interpretation and autonomous navigation based on multi-baseline stereovision. The use of rich 3D data is emphasized where the sensor output includes range and color information of the surrounding environment. Two distinct classifiers are presented, one based on geometric data that can detect the broad class of ground and one based on color data that can further segment ground into subclasses. The geometry-based classifier features two main stages: an adaptive training stage and a classification stage. During the training stage, the system automatically learns to associate geometric appearance of 3D stereo-generated data with class labels. Then, it makes predictions based on past observations. It serves as well to provide training labels to the color-based classifier. Once trained, the color-based classifier is able to recognize similar terrain classes in stereo imagery. The system is continuously updated online using the latest stereo readings, thus making it feasible for long range and long duration navigation, over changing environments. Experimental results, obtained with a tractor test platform operating in a rural environment, are presented to validate this approach, showing an average classification precision and recall of 91.0% and 77.3%, respectively.<\/jats:p>","DOI":"10.3390\/s120912405","type":"journal-article","created":{"date-parts":[[2012,9,12]],"date-time":"2012-09-12T12:11:41Z","timestamp":1347451901000},"page":"12405-12423","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":54,"title":["Towards Autonomous Agriculture: Automatic Ground Detection Using Trinocular Stereovision"],"prefix":"10.3390","volume":"12","author":[{"given":"Giulio","family":"Reina","sequence":"first","affiliation":[{"name":"Department of Engineering for Innovation, University of Salento, via Arnesano, 73100 Lecce, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Annalisa","family":"Milella","sequence":"additional","affiliation":[{"name":"Institute of Intelligent Systems for Automation, National Research Council, via G. Amendola 122\/D, 70126 Bari, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2012,9,12]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/S0168-1699(99)00053-8","article-title":"Ground-based sensing systems for autonomous agricultural vehicles","volume":"25","author":"Hague","year":"2000","journal-title":"Comput. Electron. Agr."},{"key":"ref_2","unstructured":"Leger, C., Deen, R., and Bonitz, R. (, January October). Remote Image Analysis for Mars Exploration Rover Mobility and Manipulation Operations. Hawaii, HI, USA."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"661","DOI":"10.1002\/rob.20147","article-title":"Stanley: The robot that won the DARPA grand challenge","volume":"23","author":"Thrun","year":"2006","journal-title":"J. Field Robot"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1016\/j.compag.2006.06.001","article-title":"Development of machine vision and laser radar based autonomous vehicle guidance systems for citrus grove navigation","volume":"53","author":"Subramanian","year":"2006","journal-title":"Comput. Electron. Agr."},{"key":"ref_5","unstructured":"Hastie, T., Tibshirani, R., and Friedman, J. (2003). The Elements of Statistical Learning, Springer."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Broggi, A., Cappalunga, A., Caraffi, C., Cattani, S., Ghidoni, S., Porta, P., Posterli, M., and Zani, P. (September, January 19\u2013). TerraMax Vision at the Urban Challenge. Madeira Island, Portugal. Volume 11.","DOI":"10.1109\/TITS.2010.2041231"},{"key":"ref_7","unstructured":"Rouveure, R., Nielsen, M., Petersen, A., Reina, G., Foglia, M., Worst, R., Seyed-Sadri, S., Blas, M., Faure, P., Milella, A., and Lykkegrd, K. (2012, January 8\u201312). The QUAD-AV Project: Multi-Sensory Approach for Obstacle Detection in Agricultural Autonomous Robotics. Valencia, Spain."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Buehler, M., Iagnemma, K., and Singh, S. (2007). The 2005 DARPA Grand Challenge, Springer.","DOI":"10.1007\/978-3-540-73429-1"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1504\/IJVAS.2006.012206","article-title":"The FLEXnav precision dead-reckoning systems","volume":"4","author":"Ojeda","year":"2006","journal-title":"Int. J. Veh. Auton. Sys."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1163\/016918609X12619993300548","article-title":"Odometry correction using visual slip-angle estimation for planetary exploration rovers","volume":"24","author":"Reina","year":"2010","journal-title":"Adv. Robot"},{"key":"ref_11","unstructured":"Zhao, J., Katupitiya, J., and Ward, J. (April, January 10\u2013). Global Correlation Based Ground Plane Estimation Using V-Disparity Image. Roma, Italy."},{"key":"ref_12","unstructured":"Perrollaz, M., de. Yoder, J., and Laugier, C. (September, January 19\u2013). Using Obstacles and Road Pixels in the Disparity-Space Computation of Stereo-Vision Based Occupancy Grids. Madeira Island, Portugal."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1023\/A:1008831426966","article-title":"Traversability analysis and path planning for a planetary rover","volume":"6","author":"Gennery","year":"1999","journal-title":"Auton. Robot"},{"key":"ref_14","unstructured":"Singh, S., Simmons, R., Smith, T., Stentz, A., Verma, V., Yahja, A., and Schwehr, K. (, January April). Recent Progress in Local and Global Traversability for Planetary Rovers. San Francisco, CA, USA."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1002\/rob.20276","article-title":"Learning long-range vision for autonomous off-road driving","volume":"26","author":"Hadsell","year":"2009","journal-title":"J. Field Robot"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1023\/B:AURO.0000047286.62481.1d","article-title":"Obstacle detection and terrain classification for autonomous off-road navigation","volume":"18","author":"Manduchi","year":"2003","journal-title":"Auton. Robot"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1016\/j.compag.2007.07.007","article-title":"Stereo vision three-dimensional terrain maps for precision agriculture","volume":"60","author":"Zhang","year":"2008","journal-title":"Comput. Electron. Agr."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1016\/j.compag.2010.09.013","article-title":"Automatic segmentation of relevant textures in agricultural images","volume":"75","author":"Guijarro","year":"2011","journal-title":"Comput. Electron. Agr."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"290","DOI":"10.1108\/02602280610692006","article-title":"Computer vision technology for agricultural robotics","volume":"26","author":"Milella","year":"2006","journal-title":"Sens. Rev."},{"key":"ref_20","unstructured":"Huertas, A., Matthies, L., and Rankin, A. (January, January 5\u2013). Stereo-Based Tree Traversability Analysis for Autonomous Off-Road Navigation. Breckenridge, CO, USA."},{"key":"ref_21","unstructured":"Pagnot, R., and Grandjea, P. (May, January 21\u2013). Fast Cross Country Navigation on Fair Terrains. Aichi, Japan."},{"key":"ref_22","unstructured":"Pomerleau, D. (1989). Advances in Neural Information Processing Systems, Morgan Kaufmann Publishers Inc."},{"key":"ref_23","unstructured":"Jocherm, T., Pomerleau, T., and Thorpe, C. (, January August). Vision-Based Neural Network Road and Intersection Detection and Traversal. Pittsburgh, PA, USA."},{"key":"ref_24","unstructured":"LeCun, Y., Huang, F.J., and Bottou, L. (2, January 27). Learning Methods for Generic Object Recognition with Invariance to Pose and Lighting. Washington, DC, USA. Volume 2."},{"key":"ref_25","unstructured":"Hong, T., Chang, T., Rasmussen, C., and Shneier, M. (, January April). Road Detection and Tracking for Autonomous Mobile Robots. Orlando, FL, USA."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1016\/j.compag.2010.10.012","article-title":"Stereo vision with texture learning for fault-tolerant automatic baling","volume":"75","author":"Blas","year":"2011","journal-title":"Comput. Electron. Agr."},{"key":"ref_27","unstructured":"Milella, A., Reina, G., Underwood, J., and Douillard, B. Combining Radar and Vision for Self-Supervised Ground Segmentation in Outdoor Environments. San Francisco, CA, USA."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Reina, G., Milella, A., and Underwood, J. (2012). Self-learning classification of radar feautures for scene understanding. Robot. Auton. Sys.","DOI":"10.1016\/j.robot.2012.03.002"},{"key":"ref_29","unstructured":"Brooks, C., and Iagnemma, K. (, January June). Self-Supervised Terrain Classification for Planetary Rovers. Adelphi, MD, USA."},{"key":"ref_30","unstructured":"Stavens, D., and Thrun, S. (, January July). A Self-Supervised Terrain Roughness Estimator for Offroad Autonomous Driving. Cambridge, MA, USA."},{"key":"ref_31","unstructured":"Wellington, C., and Stentz, A. (, January April). Online Adaptive Rough-Terrain Navigation in Vegetation. New Orleans, LA, USA."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1002\/rob.20271","article-title":"Mapping, navigation, and learning for off-road traversal","volume":"26","author":"Konolige","year":"2009","journal-title":"J. Field Robot"},{"key":"ref_33","unstructured":"Santana, P., Guedes, M., Correia, L., and Barata, J. (, January May). A Saliency-Based Solution for Robust Off-Road Obstacle Detection. Anchorage, Alaska, USA."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1219","DOI":"10.1163\/016918610X501499","article-title":"Dynamic simulation-based action planner for a reconfigurable hybrid legWheel planetary exploration rover","volume":"24","author":"Rohmer","year":"2010","journal-title":"Adv. Robot"},{"key":"ref_35","unstructured":"Tax, D. (2001). One-Class Classification. Concept Learning in the Absence of Counter Examples. [Ph.D. Thesis, Delft University of Technology]."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1080\/03610929708831934","article-title":"Regression and time series model selection using variants of the Schwarz information criterion","volume":"26","author":"Neath","year":"1997","journal-title":"Commun. Stat."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1007\/s10514-007-9042-y","article-title":"Vision-based motion planning for an autonomous motorcycle on ill-structured roads","volume":"23","author":"Song","year":"2007","journal-title":"Auton. Robot"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/12\/9\/12405\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T21:52:19Z","timestamp":1760219539000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/12\/9\/12405"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,9,12]]},"references-count":37,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2012,9]]}},"alternative-id":["s120912405"],"URL":"https:\/\/doi.org\/10.3390\/s120912405","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2012,9,12]]}}}