点击次数：

论文类型：期刊论文

发表时间：2017-01-01

发表刊物：IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS

收录刊物：SCIE、EI、Scopus

卷号：28

期号：1

页面范围：177-190

ISSN号：2162-237X

关键字：Imbalanced learning; laser scanning; multiclass and multiview 3-D object detection; multitask learning; sharing features

摘要：This paper investigates the problem of multiclass and multiview 3-D object detection for service robots operating in a cluttered indoor environment. A novel 3-D object detection system using laser point clouds is proposed to deal with cluttered indoor scenes with a fewer and imbalanced training data. Raw 3-D point clouds are first transformed to 2-D bearing angle images to reduce the computational cost, and then jointly trained multiple object detectors are deployed to perform the multiclass and multiview 3-D object detection. The reclassification technique is utilized on each detected low confidence bounding box in the system to reduce false alarms in the detection. The RUS-SMOTEboost algorithm is used to train a group of independent binary classifiers with imbalanced training data. Dense histograms of oriented gradients and local binary pattern features are combined as a feature set for the reclassification task. Based on the dalian university of technology (DUT)-3-D data set taken from various office and household environments, experimental results show the validity and good performance of the proposed method.