21 e-learning Development of Real-time Learner Detection System for e-learning

Size: px

Start display at page:

Download "21 e-learning Development of Real-time Learner Detection System for e-learning"

えりかふしはら
4 years ago
Views:

1 21 e-learning Development of Real-time Learner Detection System for e-learning

2 e-learning WBT (Web Based training) e-learning LMS (Learning Management System) LMS WBT e-learning e-learning WBT LMS i

3 Abstract Development of Real-time Learner Detection System for e-learning Naoki MATSUMOTO In recent years, WBT (Web Based Training) and other e-learning are introducing at higher education institutions such as distance learning. Distance learning mainly apply the internet. Distance lecture is one of distance learning style. Higher education institutions is conducting distance lecture using the internet. accredit credit based on university establishment standards. Distance lecture can Each higher education institutions are addressing the distance lecture. It is necessary that distance lecture secure learning time based on university establishment standards to accredit credit. Currently, Learner s progress figure out from recorded information on LMS (Learning Management System) such as learning time and result of test. However, administrator of distance lecture can not figure out learner s situation from recorded information on LMS at directly and real-time. Therefore, administrator of distance lecture can not figure out the Learner s situation such as learn and not learn. In this paper, we developed real-time learner detection system for WBT and other e-learning. Moreover, we evaluated this system to confirm correctly detect the presence of learner. key words e-learning, WBT, LMS, Distance Lecture, Certification Unit, University Establishment Standard ii

4 e-learning WBT (Web Based Training) LMS (Learning Management System) ( ) ( ) ( ) iii

5 A B C iv

6 v

7 ( ) ( ) ( ) A A B B C C vi

8 Logicool 1.3-MP Webcam C Logicool 1.3-MP Webcam C Microsoft LifeCam VX vii

9 1 WBT e-learning Web 1999 [1] WBT e-learning LMS (Learning Management System) LMS [2] WBT e-learning Web Web 1

10 2 e-learning e-learning 2.1 e-learning (ICT : Information Communication Technology) e-learning e-learning 18 IT [3] 2 WBT (Web Based Training) e-learning (Distance Learning) SCS 2

11 2.1 e-learning (Space Collaboration System) WBT [1] WBT (Web Based Training) WBT Web e-learning e-learning CD-ROM DVD CBT (Comuputer Based Training) CBT WBT CBT Web Web LMS (Learning Management System) LMS (Learning Management System) CMS (Course Management System) WBT e-learning LMS LMS 3

12 2.1 e-learning ( ) 2 VOD (Video On Demand) VOD VOD Web [1] [1]

13 [4] [1] [5] [6] e-learning [7] e-learning 2.2 WBT WBT e-learning LMS (Learning Management System) LMS [2] LMS 5

14 2.3 e-learning 2.3 [1] LMS WBT e-learning Web Web Web USB (Universal Serial Bus) USB Web Web LMS Web Web 6

15 2.3 7

16 3 Web PC Web USB PC USB Web WBT e-learning 3.1 WBT Web 8

17 3.2 WBT e-learning Web Web WBT e-learning PC ( ) ( )

19 ( ) ( ) ( ) 11

21 WBT e-learning WBT 13

22 3.3 e-learning ( )

26 WBT e-learning Web ActionScript3.0 Web Apache Web Web 1 FPS (Frames Per Second)

27 ( )

28 , Haar-like Haar-like Haar-like Haar-like OpenCV ObjectDetection ( ) ActionScript3.0 Marilena OpenCV haarcascade frontalface alt.xml

29 RGB RGB R ( : Red) G ( : Green) B ( : Blue) RGB RGB RGB R G B HSV HSV H (Hue : ) S (Saturation : ) V (Value : ) 3 RGB HSV RGB H ( ), HSV RGB HSV HSV H ( ) 0 30 [8] HSV 21

30 haarcascade frontalface alt.xml ( ) ( ) 22

31 ( )

32 (A B C) Web Logicool 1.3-MP Webcam C300 Logicool 1.3-MP Webcam C (A B C) A B A B

33 ( ) ( ) ( ) ( ) 5.2 Logicool 1.3-MP Webcam C300 2cm - ( ) ( ) OS CPU / WindowsXP(SP2 ) WindowsVista Windows7 1GHz CPU(1.6GHz ) 512MB USB 2 C 3 C

34 A 5.2 A 26

35 B 5.4 B 27

36 C 5.6 C 28

37 A B C A B A B A B 2 A 456 A A A 29

38 C C

39 cm

40 cm 20 cm 32

41 pixel 6.2 Logicool 1.3-MP Webcam C300 Logicool 1.3-MP 33

42 Logicool 1.3-MP Webcam C300 ( ) ( ) ( ) ( ) Webcam C200 Microsoft LifeCam VX Logicool C300 Microsoft LifeCam VX px Logicool 1.3-MP Webcam C300 Microsoft LifeCam VX-300 Logicool 1.3-MP WebCam C px 90cm 34

43 Logicool 1.3-MP Webcam C200 ( ) OS CPU ( )mm 2cm - ( ) / WindowsXP(SP2 ) WindowsVista Windows7 1GHz CPU(1.6GHz ) 512MB USB ( ) 6.3 ( ) ( ) ( ) Logicool 1.3-MP Webcam C ( ) 1808px ( ) 2473px 35

44 Microsoft LifeCam VX-3000 ( ) OS CPU 2cm - ( ) / WindowsXP SP2 WindowsVista Windows7 Windows Vista : Pentium4 2.8GHz (Pentium Dual Core 1.8 GHz ) Windows XP SP2 : Pentium4 1.8GHz (Pentium4 3GHz ) WindowsVista : 1G RAM (2GB ) Windows XP SP2 : 256MB RAM (500MB ) USB ( )mm ( ) 535px

45 ( ) (Logicool C300) 1454px 1808px 354px 390px Logicool C px 2844px 803px 2088px Microsoft LifeCam VX px 2707px 317px 693px 6.5 ( ) ( ) 1454px 1808px 354px 390px ( ) 2129px 2473px 344px 289px ( ) 328px 535px 207px 296px cm 6.6 ( ) 1332px 1654px 322px 380px 0px 939px 939px 339px 37

3-MP WebCam C200 で撮影した画像図 6.1 Logicool 1.

46 6.5 比較検証の考察 6.5 比較検証の考察比較検証の結果に対して考察を行った本節ではなぜカメラの違いや照明環境の違い装飾品の違いから検出結果および顔検出肌色抽出結果に違いがでたのか理由を明らかにするそしてこれらの検出結果の違い抽出結果の違いから今後どのような対策が必要となるか考察を行うカメラの違いと照明環境の違い肌色情報の抽出結果について本検証から使用するカメラによって色の発色が違うということがわかった実際に使用したカメラで撮影した画像を図 6.1 に示す Logicool 1.3-MP WebCam C200 で撮影した画像図 6.1 Logicool 1.3-MP WebCam C300 で撮影した画像 Microsoft LifeCam VX-3000 で撮影した画像各カメラで撮影した画像これらの画像からわかるように使用するカメラによって明るさが異なり肌色にも違いが見られる本研究では HSV 表色系の H (色相) の値が 0 から 30 のときに肌色として抽出するようにしているがこのように使用するカメラによって発色が違うため H の値が変わってしまい肌色情報の抽出結果に差が現れたと考えられるまた照明環境の違いにより検証を行った照明環境の違いにより抽出できる肌色情報に差がでることを確認したとくに暗い (蛍光灯ひとつ点灯) 環境であれば安定して肌色情報を抽出することが難しいことが示唆されたこれは学習を行う環境が暗くなってしまったため設定しておいたしきい値では肌色情報を抽出できなかったことが原因だと考えられる 38

47 6.5 H ( ) 6.4 Logicool 1.3-MP WebCam C px H ( ) Web

48 6.5 40

49 7 e-learning LMS LMS 41

51 [1] [2] e 25 pp [3] IT [4] menu/shingi/12/daigaku/toushin/ htm [5] [6] [7] [8] Sherrah, J. & Gong, S (2001). Skin Color Analysis. CvOnline

Web Web Web Web Web, i

22 Web Research of a Web search support system based on individual sensitivity 1135117 2011 2 14 Web Web Web Web Web, i Abstract Research of a Web search support system based on individual sensitivity