摘要(英) |
The purpose of this paper is to develop a method of measuring human
height, using only one camera and some simple settings. First steps of the
algorithm is finding the subjects’ edge. Second, use the Hough transform
to mark the longest straight line of images. Lastly, use the algorithm to
calculate scale of each image, and let the longest straight line convert to
actual height.
This method can be used as a non-contact height measurement. It has
less restriction, but still can get accurate result, that can be used in medical
or catering. |
參考文獻 |
[1] Wikipedia:http://zh.wikipedia.org/zh-tw/Wikipedia
[2] 賴岱佑博士、郭忠義博士、黃福助博士,數位影像處理技術手冊
第二版,松崗資產管理股份有限公司,2016。
[3] 蔡蘇威和魏兆煌博士,使用嵌入式系統於影像動態偵測之設計與
實現,2006。
[4] 趙冠維、葉明宗和鍾翼能教授,應用影像處理技術於公路車輛偵
測及追蹤之研究,2013。
[5] Zhaleh Sadreddini, Tuğrul Çavdar and Hossein Barghi Jond, “A distance measurement method using single camera for indoor environments”, proceedings of the Telecommunications and Signal Processing (TSP), 2016 39th International Conference on, 27-29 June 2016.
[6] Jiqiang Song, Michael R. Lyu, “A Hough transform based line
recognition method utilizing both parameter space and image space”,
proceedings of the Department of Computer Science & Engineering,
Hong Kong, 20 September 2004.
[7] Somkiat Wangsiripitak, Wongsatorn Saelao, “Real-time monocular
human height estimation using bimodal background subtraction” ,
proceedings of the 2017 IEEE Region 10 Conference (TENCON),
Malaysia, November 5-8, 2017.
[8] Wen-Yuan Chen, Chiou-Kou Tung, Chuin-Mu Wang, Dang-Yi Kuo, “The noncontact human-height measurement scheme”, proceedings of the 2011 International Conference on Machine Learning and Cybernetics, Guilin, 10-13 July, 2011.
[9] Erno Jeges, Istvan Kispal, Zoltan Hornak, “Measuring Human Height Using Calibrated Cameras”, proceedings of the 2008 Conference on Human System Interactions, Poland, 25-27 May ,2008. |