基於卷積神經網路架構並使用遮罩導引之部份遮蔽物體姿態估計

CNN-based Partially Occluded Object Pose Estimationwith Mask Guidance

洪毓君(Yu-Jun Hong)

指導教授 ： 林奕成

國立交通大學/資訊學院/多媒體工程研究所/碩士(2019年)

摘要

無資料

關鍵字

姿態預估 ； 深度學習

並列摘要

無資料

並列關鍵字

pose estimation ； deep learning

參考文獻

Austria, May 7-13, 2006, Proceedings, Part I, 2006, pp. 404–417. [Online]. Available:https://doi.org/10.1007/11744023_32[16]P. J. Besl and N. D. McKay, “A method for registration of 3-d shapes,”IEEE Trans.Pattern Anal. Mach. Intell., vol. 14, no. 2, pp. 239–256, 1992. [Online]. Available:https://doi.org/10.1109/34.121791[17]K. He, G. Gkioxari, P. Dollár, and R. B. Girshick, “Mask R-CNN,” inIEEEInternational Conference on Computer Vision, ICCV 2017, Venice, Italy, October22-29, 2017. IEEE Computer Society, 2017, pp. 2980–2988. [Online]. Available:https://doi.org/10.1109/ICCV.2017.322[18]J. Long, E. Shelhamer, and T. Darrell, “Fully convolutional networks for semanticsegmentation,” inIEEE Conference on Computer Vision and Pattern Recognition,CVPR 2015, Boston, MA, USA, June 7-12, 2015. IEEE Computer Society, 2015, pp.3431–3440. [Online]. Available:https://doi.org/10.1109/CVPR.2015.7298965[19]M. Everingham, S. M. A. Eslami, L. V. Gool, C. K. I. Williams, J. M. Winn, andA. Zisserman, “The pascal visual object classes challenge: A retrospective,”InternationalJournal of Computer Vision, vol. 111, no. 1, pp. 98–136, 2015. [Online]. Available:https://doi.org/10.1007/s11263-014-0733-530