文献类型：期刊文献

英文题名：Neutrosophic Hough Transform-Based Track Initiation Method for Multiple Target Tracking

作者：Fan, En[1,2];Xie, Weixin[1];Pei, Jihong[1];Hu, Keli[2];Li, Xiaobin[3]

机构：[1]Shenzhen Univ, ATR Natl Key Lab Def Technol, Shenzhen 518060, Peoples R China;[2]Shaoxing Univ, Dep Comp Sci & Engn, Shaoxing 312000, Peoples R China;[3]Jozef Stefan Int Postgrad Sch, Ljubljana 1000, Slovenia

年份：2018

卷号：6

起止页码：16068

外文期刊名：IEEE ACCESS

收录：SCI-EXPANDED(收录号：WOS:000430247500001)、、EI(收录号：20181104904705)、Scopus(收录号：2-s2.0-85043484017)、WOS

基金：This work was supported in part by the National Natural Science Foundation of China under Grant 61703280 and Grant 61603258, in part by the General Project of Educational Commission of Zhejiang Province under Grant 201635390, in part by the Plan Project of Science and Technology of Shaoxing City under Grant 2017B70056, in part by the Key Project of Science and Research of Shaoxing University under Grant 2015LG1006, and in part by the Public Welfare Technology Application Research-Industrial Project of Zhejiang Province under Grant 2016C31082.

语种：英文

外文关键词：Track initiation; Hough transform; neutrosophic set; data fusion; multiple target tracking

外文摘要：A neutrosophic Hough transform-based track initiation method (NHT-TI) is proposed to solve the uncertain track initiation problem in a complex surveillance environment. In the proposed method, a neutrosophic set is employed to describe the uncertain association of a measurement with different targets, which is divided into three categories, including the association with real targets, uncertain targets, and false targets, respectively. On this basis, the neutrosophic Hough transform (NHT) method is developed in the framework of the standard Hough transform (HT) method. Based on the sequential processing mode of the sensors, candidate temporary tracks are further de fined to directly calculate the parameter points in the parameter space, which are utilized to calculate the contribution for the corresponding vote cells in the accumulation matrix by using the Gaussian membership function. Based on the scheme, the NHT method can avoid large traversal operations and reduce computation complexity of the HT method. Moreover, considering the effects of noises and clutters on track initiation, two constraint conditions related to the velocity information of moving targets and the time information of measurement sequences are introduced to suppress false tracks and reduce vote times. Finally, the real tracks can be determined by detecting the peaks of the global accumulation matrix. The performance of the proposed NHT-TI method is evaluated by using two experiments with simulated data and real data in two complex surveillance environments. The results are found to be better than those of the standard HT-based track initiation (HT-TI) method, the modified HT-TI method based on candidate temporary tracks and the improved HT-TI method in detection reliability and computational complexity.