点击次数：

论文类型：期刊论文

发表时间：2018-01-31

发表刊物：NEUROCOMPUTING

收录刊物：SCIE、EI、Scopus

卷号：275

页面范围：2752-2761

ISSN号：0925-2312

关键字：Road detection; Road modeling; Laser-vision data fusion; RANSAC spline fitting; UGV

摘要：Autonomous road detection and modeling play a key role for UGVs navigating in complex outdoor environments. This paper investigates road detection and description for UGVs in various outdoor scenes under different weather conditions. A novel environment perception system that includes two cameras and multiple laser range finders is introduced firstly. Taking classification accuracy and time-cost into account, 8-dimensional features are selected from a 91-dimensional candidate feature set using Adaboost algorithm. To adapt to the diversity of road scenes under different weather conditions in different seasons, an online classifier based on SVM is proposed to replace the fixed one. Moreover, a road region adjusting algorithm is present to eliminate misclassified regions especially when the roads have fuzzy boundaries or obstacles. Finally, a RANSAC spline fitting algorithm is adopted to provide an accurate road border model for UGVs' autonomous path planning and navigation. A series of experiments are conducted by using a self-built UGV platform and experimental results show the validity and practicality of the proposed approaches. (c) 2017 Elsevier B.V. All rights reserved.