Manuscript received July 10, 2018; revised October 7, 2018; accepted November 26, 2018. Date of publication January 4, 2019; date of current version October 9, 2019. This work was supported in part by the National Science Foundation of China under Grant 61733004, Grant 61703155, Grant 61573134, and Grant 61503128, in part by the Hunan Key Project of Research and Development Plan under Grant 2017XK2102, Grant 2018GK2022, and Grant 2018JJ3079, and in part by the Innovation Project of Postgraduate Student in Hunan Province of China under Grant CX2017B108. The Associate Editor coordinating the review process was Emanuele Zappa. (Corresponding authors: Changyan Xiao; Qing Zhu.) X. Zhou, Y. Wang, C. Xiao, and Q. Zhu are with the National Engineering Laboratory for Robot Visual Perception and Control Technology, College of Electrical and Information Engineering, Hunan University, Changsha 410082, China (e-mail: c.xiao@hnu.edu.cn; zhuqing_hnu@163.com).
