文献类型：期刊文献

英文题名：Element-Weighted Neutrosophic Correlation Coefficient and Its Application in Improving CAMShift Tracker in RGBD Video

作者：Hu, Keli[1];Fan, En[1];Ye, Jun[2];Pi, Jiatian[3];Zhao, Liping[1];Shen, Shigen[1]

机构：[1]Shaoxing Univ, Dept Comp Sci & Engn, Shaoxing 312000, Peoples R China;[2]Shaoxing Univ, Dept Elect & Informat Engn, Shaoxing 312000, Peoples R China;[3]Chongqing Normal Univ, Coll Comp & Informat Sci, Chongqing 400700, Peoples R China

年份：2018

卷号：9

期号：5

外文期刊名：INFORMATION

收录：ESCI(收录号：WOS:000436150100025)、EI(收录号：20182105227071)、Scopus(收录号：2-s2.0-85047124110)、WOS

基金：This work was supported by the National Natural Science Foundation of China under Grant Nos. 61603258, 61703280, 61601200, and the Plan Project of Science and Technology of Shaoxing City under Grant No. 2017B70056.

语种：英文

外文关键词：tracking; CAMShift; neutrosophic set; single-valued neutrosophic set; correlation coefficient; element-weighted neutrosophic correlation coefficient

外文摘要：Neutrosophic set (NS) is a new branch of philosophy to deal with the origin, nature, and scope of neutralities. Many kinds of correlation coefficients and similarity measures have been proposed in neutrosophic domain. In this work, by considering that there may exist different contributions for the neutrosophic elements of T (Truth), I (Indeterminacy), and F (Falsity), a method of element-weighted neutrosophic correlation coefficient is proposed, and it is applied for improving the CAMShift tracker in RGBD (RGB-Depth) video. The concept of object seeds is proposed, and it is employed for extracting object region and calculating the depth back-projection. Each candidate seed is represented in the single-valued neutrosophic set (SVNS) domain via three membership functions, T, I, and F. Then the element-weighted neutrosophic correlation coefficient is applied for selecting robust object seeds by fusing three kinds of criteria. Moreover, the proposed correlation coefficient is applied for estimating a robust back-projection by fusing the information in both color and depth domains. Finally, for the scale adaption problem, two alternatives in the neutrosophic domain are proposed, and the corresponding correlation coefficient between the proposed alternative and the ideal one is employed for the identification of the scale. When considering challenging factors like fast motion, blur, illumination variation, deformation, and camera jitter, the experimental results revealed that the improved CAMShift tracker performs well.