在科技產品迅速發展的今日，人們已習慣且頻繁使用各種3C產品如智慧型手機、筆記型電腦等。這些科技產品被使用的目的，除了用於工作或者通訊外，有一部分是被消費族群視為娛樂目的而購買使用，而這些電子產品提供的娛樂項目，是建立在與由電腦圖學所建立的虛擬生物互動上。過去有各種生物，包括人類、貓、狗以及魚等等在內，已經被人工建立出來並應用於娛樂或者教育軟體上。然而建立這些虛擬生物與其生態環境所需要的技術與背景知識並非所有使用的消費者都具備，嚴重缺乏使用者根據自身需求調整理想飼育環境的延展性。因此我們嘗試從特定種類生物—魚類，找出其行為模式的共通特性，以建立出模仿現實世界魚類各種特徵行為的虛擬魚。此外，我們設計了一個使用者可自訂的水中環境，讓虛擬水族箱能更進一步符合使用者需求，節省設計過程所需成本。

本研究的目的為從魚類的生物資訊建立出可互動式虛擬水族箱。我們觀察了魚的活動特性，為虛擬魚製作骨架以控制魚的身體擺動，並設計了一套AI用以控制魚的游動、覓食或逃跑等行為，以讓虛擬魚能像現實魚類持續且自然的表現出游動動作。其次我們設計了一個可讓使用者自行調整擺設水草、假山等佈景的虛擬水族箱，讓虛擬飼養環境進一步個人化。最後，我們利用手部資訊感測器 Leap Motion其小型精簡易於安裝的特性，擷取出外部使用者手勢來與虛擬水族箱內魚隻進行驅趕、抓取、餵食等互動。

關鍵詞：人工虛擬魚、水族箱、人工智慧、手勢辨識、Leap Motion

Today, we have many kinds of the 3C device like smart phone or notebook. We use these for work, communication, and entertainment. In the past years, the device that detects real world information to interact with computer graphic becomes popular. Many of these devices, like Kinect, Leap Motion and HTC Vive, use multiple sensors to generate the 2D image with depth map. With the depth map, the software can combine two scenes into one, that allows the user to interact with the virtual objects.

In this thesis, we present a 3D interactive artificial aquarium system, which detects user’s gesture to interact with the artificial fishes. We design two kinds of artificial fish, start from modeling, texture, and bone collation. And we build the artificial fish’s AI to control the fish behavior. In addition, we use Leap Motion to detect user’s gesture. The user can catch, tow, feed fishes and decorate the aquarium with only their hands instead of other input devices. Our purpose is to build an aquarium system, for any user even never used mouse or keyboard before.

Keywords: Artificial fish, Aquarium, Artificial Intelligence, Hand tracking, Leap motion.

論文審定書 .................................................................................................... i
誌 謝 ....................................................................................................... ii
摘 要 ...................................................................................................... iii
Abstract ........................................................................................................ iv
目 錄 ....................................................................................................... v
圖 目 錄 ..................................................................................................... vii
第一章 導論 .............................................................................................. 1
第二章 文獻探討 ...................................................................................... 3
第三章 研究方法 ...................................................................................... 7
1. 魚外觀設計 ...................................................................................... 8
1.1 從影像建立魚模型 ......................................................................... 9
1.2 影像貼圖 ....................................................................................... 11
1.3 骨架與模型校對 ........................................................................... 12
2. 游動軌跡 ........................................................................................ 14
2.1 人工制定軌跡 ............................................................................... 15
3. 行為模式 ........................................................................................ 16
4. 互動系統 ........................................................................................ 17
4.1 手部辨識 ....................................................................................... 19
vi
4.2 互動反應 ....................................................................................... 21
第四章 系統建置 .................................................................................... 25
第五章 結論 ............................................................................................ 32
參考文獻 ..................................................................................................... 33

[1] A. Nealen, M. Müller, R. Keiser, E. Boxerman, and M. Carlson, “Physically based deformable models in computer graphics,” Computer Graphics Forum, vol. 25, no. 4, pp. 809-836, 2006.
[2] C. Kim, M. Shin, S. Jeong, I. Kang, E. Kim and B. Kim, “Real-time motion simulation of artificial fish for virtual marine world,” Sixth International Conference on Advanced Language Processing and Web Information Technology (ALPIT 2007), pp. 253-260, 2007.
[3] G. Allard, “Control of a free-swimming fish using fuzzy logic,” The International Journal of Virtual Reality, pp. 23-28, 2007.
[4] X. Tu, and D. Terzopoulos, “Artificial fishes:physics, locomotion, perception, behavior,” Annual Conference on Computer Graphics and Interactive Techniques (SIGGRAPH), pp. 43-50, 1994.
[5] K. Stephens, B. Pham, and A. Wardhani, “Modelling fish behaviour,” International Conference on Computer Graphics and Interactive Techniques (GRAPHITE), pp. 71-78, 2003.
[6] X. Jiang, H. Bunke, K. Abegglen, and A. Kandel, “Curve morphing by weighted mean of strings,” International Conference on Pattern Recognition, vol. 4, pp. 192-195, 2002.
[7] E. Kim, N. Ryu, K. Ban, J. Seo and M. Jang, “3D morphing techniques for fish growth process system implementation based on environmental factors,” 2008 Fourth International Conference on Networked Computing and Advanced Information Management, pp. 3-8, 2008.
[8] Y. Liu, “Research on the cognitive model artificial fish based on virtual marine environment,” 2016 8th International Conference on Information Technology in Medicine and Education (ITME), pp. 719-723, 2016.

[9] H. Yuan, S. Huang and Y. Chen, “Behavioral decision making of an artificial fish based on artificial emotion and the cerebellar model articulation controller,” 2013 Ninth International Conference on Natural Computation (ICNC), pp. 623-627, 2013.
[10] S. Podila and Y. Zhu, “Simulating a predator fish attacking a school of prey fish in 3D graphics,” Advances in Visual Computing Lecture Notes in Computer Science, pp. 586-594, 2016.
[11] G. Marin, F. Dominio and P. Zanuttigh, “Hand gesture recognition with leap motion and kinect devices,” 2014 IEEE International Conference on Image Processing (ICIP), pp. 1565-1569, 2014.
[12] L. E. Potter, J. Araullo, and L. Carter, “The Leap Motion controller,” Proceedings of the 25th Australian Computer-Human Interaction Conference on Augmentation, Application, Innovation, Collaboration - OzCHI 13, pp. 175-178, 2013.
[13] H. Cheng, L. Yang and Z. Liu, “Survey on 3D hand gesture recognition,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 26, no. 9, pp. 1659-1673, Sept. 2016.
[14] K. Sabir, C. Stolte, B. Tabor and S. I. O'Donoghue, “The molecular control toolkit: controlling 3D molecular graphics via gesture and voice,” 2013 IEEE Symposium on Biological Data Visualization (BioVis), pp. 49-56, 2013.
[15] A. Sucipto, A. Harsoyo and P. H. Rusmin, “Implementation of gesture recognition on aquarium application,” 2012 International Conference on System Engineering and Technology (ICSET), pp. 1-4, 2012.