| 研究生: |
廖振佑 Liao, Jhen-You |
|---|---|
| 論文名稱: |
利用熱影像與可見光影像進行人類偵測應用於海上搜索行動之可行性研究 A Study on People Detection with Thermal and Visible Images Methodology and Its Application on Marine Search Missions |
| 指導教授: |
楊澤民
Yang, Joe-Ming |
| 學位類別: |
碩士 Master |
| 系所名稱: |
工學院 - 系統及船舶機電工程學系 Department of Systems and Naval Mechatronic Engineering |
| 論文出版年: | 2017 |
| 畢業學年度: | 105 |
| 語文別: | 中文 |
| 論文頁數: | 71 |
| 中文關鍵詞: | 紅外線 、熱像儀 、人臉偵測 、人類偵測 |
| 外文關鍵詞: | infrared, thermal imager, face detection, people detection |
| 相關次數: | 點閱:105 下載:9 |
| 分享至: |
| 查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
近年來,自動化科技正快速的發展,無人載具越來越普及化,因為無人載具可以被用來執行各種複雜的任務,以此避免人員身處在危險的環境當中。在先前的研究中,四旋翼自主飛行以及利用所空拍的影像作為地圖進行路徑規劃給無人船導航都是可被實現的,而本研究即是要延伸先前的成果應用於實務方面,將影像系統增加搭載紅外線熱像儀,結合紅外線熱影像與可見光影像達到人類偵測之目的,以此未來在海上搜索的任務中能在黃金時間內提升效率,並減少人員的傷亡。
本文為了達到人類偵測之目的,將利用紅外線熱像儀與可見光相機同時拍攝影像,紅外線熱像儀能藉由感測不同物體所散發的熱輻射而依其溫度在熱影像上以不同顏色呈現,因此可以依人類體溫所呈現的顏色來設定二值化閥值,而可見光相機所拍攝之影像透過人臉偵測演算法,將可能為人臉的位置以紅色方框表示,再將兩影像疊合利用程式語言所設定的判斷式來偵測是否為人類,並輸出人類所在位置的像素座標值。此外,為了要將像素座標值轉換為GPS座標值,本研究也求得了FLIR ONE熱像儀的距離與影像解析度之間的關係曲線。如此可以將人類偵測程式語言所輸出的像素座標值轉換為GPS座標值以利後續的應用。
The current development of automatic control technology is rapidly improving. Unmanned vehicles are widely used due to their capability of completing complex missions while preventing people from being exposed to dangerous environments. In previous studies, utilizing an autonomous quadrotor and aerial images as the main map to plan the path for unmanned surface vehicles is found to be feasible. The results of previous research can be extended to current research in order to improve the practicality of the design. In this study, an infrared thermal imager is added to the previous camera system. By combining thermal and visible images, the goal of detecting people with the system can be accomplished. Thus, with the proposed camera system, greater efficiency and less casualties faced during marine searches can be achieved. In order to reach the goal of people detection in this study, an infrared thermal imager and a visible range camera are used to take images simultaneously. Firstly, the infrared thermal imager can detect heat emanated from different objects and show different colors according to their temperature on thermal images, where the binarization threshold can then be set in terms of the colors of body temperatures. Secondly, images taken by the visible range camera can spot human faces with a red frame via a face detection algorithm. A program is proposed and coded to combine the two types of images to determine the presence of people, and then it would calculate the center location of the red frame of the faces. In addition to this study, the distance-resolution correlation of FLIR ONE thermal imager in converting pixel coordinates into GPS coordinates has been achieved. Therefore, this program of detecting people can be applied in order to plan the paths for unmanned surface vehicles more effectively.
[1] L. Heng, L. Meier, P. Tanskanen and M. Pollefeys. “Autonomous Obstacle Avoidance and Maneuvering on a Vision-Guided MAV Using on-Board Processing,” Proceedings of International Conference on Robotics and Automation, 2011.
[2] L. Meier, P. Tanskanen, L. Heng, G. Lee, F. Fraundorfer and M. Pollefeys, “PIXHAWK: A Micro Aerial Vehicle Design for Autonomous Flight Using Onboard Computer Vision,” Autonomous Robots, pp. 1-19, 2012.
[3] 黃灝雄, 那至中, “面陣列熱影像特性之研究,” 國立政治大學, 2010.
[4] John R. Jensen, “Remote Sensing of the Environment: An Earth Resource Perspective (2nd Edition),” Pearson Education Limited, 2007.
[5] Mung-His Wang, Chao-Chih Wang, “A Study on Application of Thermogram to Human Face Recognition,” National Cheng Kung University, 2001.
[6] Dong-Ho Lee, “Thermal Analysis of Integrated-Circuit Chips Using Thermographic Imaging Techniques,” IEEE Transactions on Instrumentation and Measurement, Vol. 43, No. 6, pp. 824-829, 1994.
[7] Shi-Wei Chu, online course on Coursera about Quantum Mechanics, National Taiwan University. available online at https://zh-tw.coursera.org/learn/wuli/lecture/Esecm/7-2-pu-lang-ke-de-da-dan-cai-ce, 2015.
[8] The measurement formula, FLIR ResearchIR User Manual.
available online at http://www.thermokameras.com/ir-systeme/software/Handbuch_ResearchIR.pdf, 2010
[9] Thermal Imaging Camera, FLIR ONE, available online at http://www.flir.com/flirone/ios-android/.
[10] Alasdair McAndrew, “Introduction to Digital Image Processing with MATLAB,” Course Technology PTR, 2004.
[11] Rafael C. Gonzalez, Richard E. Woods, “Digital Image Processing (3rd Edition),” Prentice Hall, 2008.
[12] Yan-Fu Kuo, “Image Processing I,” National Taiwan University, available online at https://goo.gl/2pQ9qo, 2015.
[13] Yan-Fu Kuo, “Image Processing II,” National Taiwan University, available online at https://goo.gl/Xul0K1, 2015.
[14] Inn-Chyn Her, Wei-Cheng Tsai, “Edge Detection based on Grayscale Morphology on Hexagonal Images” National Sun Yat-sen University, 2012.
[15] A. Charnes, E. L. Frome and P. L. Yu, “The Equivalence of Generalized Least Squares and Maximum Likelihood Estimates in the Exponential Family,” Journal of the American Statistical Association, Vol. 71, No. 353, pp. 169-171, 1976.
[16] Otto Bretscher, “Linear Algebra with Applications (3rd Edition),” Prentice Hall, 1995.
[17] Stephen M. Stigler, “Gauss and the Invention of Least Squares,” The Annals of Statistics, Vol.9, No.3, pp. 465-474, 1981.
[18] Paul Viola, Michael J. Jones, “Robust Real-Time Face Detection,” International Journal of Computer Vision 57(2), 137-154, 2004.
[19] 蔡承宇, 柯建全, “植基於NCC膚色模型之人臉偵測系統,” 國立嘉義大學, 第十二屆離島資訊技術與應用研討會, pp. 893-899, 2013.
[20] Dong-Liang Lee, Jen-Sheng Liang, “Realization of a Real-time Face Detection and Recognition system using OpenCV,” Ming Chuan University, 2010.
[21] Wikipedia. “Adaboost,” available online at https://zh.wikipedia.org/wiki/AdaBoost.
[22] 李航, “統計學習方法,” 清華大學出版社, 2012.
[23] National Oceanic and Atmospheric Administration. Earth’s Magnetic Field Calculators. available online at http://www.ngdc.noaa.gov/geomag/magfield.shtml, 2012.
[24] Joe-Ming Yang, Chia-Chun Fan, “Real-time Path Planning for Unmanned Surface Vehicle by Using Finite Angle A* Algorithm,” National Cheng Kung University, 2013.
[25] Joe-Ming Yang, Po-Sheng Tseng, “Path Planning for Unmanned Surface Vehicle by Using Aerial Image from Quadrotor,” National Cheng Kung University, 2015.
[26] Joe-Ming Yang, Yu-Tang Yen, “A Study of Aerial Image on Autonomous Quadrotor by the Arduino and Xbee Methodology and It’s Application on the Path Planning of the USV,” National Cheng Kung University, 2016.
[27] Soo T. Tan, “Essential of Calculus,” Cengage Learning Asia Pte. Ltd., 2011.
[28] T. Vincenty, “Direct and Inverse Solutions of Geodesics on the Ellipsoid with Application of Nested Equations,” Survey Review, Vol.23, No.176, pp. 88-93, 1975.