現在位置首頁 > 博碩士論文 > 詳目
  • 同意授權
論文中文名稱:穿戴式視障者視覺輔助辨識系統 [以論文名稱查詢館藏系統]
論文英文名稱:Visual Recognition and Navigation for the Visual Impaired Wearable System [以論文名稱查詢館藏系統]
院校名稱:臺北科技大學
學院名稱:電資學院
系所名稱:資訊工程系研究所
畢業學年度:103
畢業學期:第二學期
出版年度:104
中文姓名:黃翊庭
英文姓名:Huang yi ting
研究生學號:102598017
學位類別:碩士
語文別:中文
口試日期:2015/07/12
指導教授中文名:張厥煒
口試委員中文名:楊士萱;奚正寧;謝禎冏;張厥煒
中文關鍵詞:穿戴式視障輔具障礙物偵測物件辨識特徵比對加速穩健特徵
英文關鍵詞:Visually Impaired AssistantObstacle DetectionObject RecognitionFeature MatchingSpeeded-Up Robust Features
論文中文摘要:本論文提出一套改善視覺障礙族群日常生活不便的穿戴式視覺輔助系統,提供視障者「陸標提醒」、「路況警示」與「日用品識別」的視覺輔具,以及建立圖像資訊共創平台。改善定向行動之方向定位不易、白手杖對於地面上方空間資訊提供不足、全球導盲犬數量不足與視障者對於形狀相似之物品無法辨認等問題進行設計。視障者穿戴此視覺輔具於身上,藉由語音方式提醒視障者陸標資訊、物品資訊以及障礙物出現警示,協助視障者「安全導引」、「掌握環境」的穿戴式視覺辨識輔助系統。
使用Xtion Pro進行實作,透過彩色影像(Color Image)與深度影像(Depth Image)資訊進行即時的RGB-D影像串流分析。障礙物警示採用深度分割(Depth Segmentation)、邊緣偵測(Edge Detection)、輪廓提取(Contour Extraction)標記出障礙物出現位置給於語音警示,使用尺度及旋轉不變特徵SURF(Speeded-Up Robust Features)演算法提取陸標與物品特徵,建立多重隨機Kd樹(Multiple Randomized Kd Trees)特徵索引資料,特徵匹配比對採用ANN(Approximate Nearest Neighbors)演算法,辨識陸標與物品資訊。在本實驗中陸標辨識率可達85.87%,在日用品識別的辨識率可達86.16%,障礙物警示中偵測率可達95.67%,在視障朋友受測後表示這項穿戴式視覺輔具有助於改善他們日常生活的不便,可以協助了解周圍資訊,建立起自己的心理地圖。
論文英文摘要:This paper presents the wearable visual aid system to improve the daily lives of the visually impaired inconvenience. Provide visually impaired persons "landmarks remind", "traffic alert" and "Item Identification" wearable visual aids and the establishment of image information platform. White cane for the space above the ground providing insufficient information, insufficient number of global guide dogs, for the visually impaired unrecognizable shape of articles similar issues such as improving the design. Use voice reminder visually impaired landmarks information, articles and obstacles appear warning information to assist visually impaired persons "safety guide ","control environment" wearable visual recognition system.
Use Xtion Pro implement, through color image and depth image information real time RGB-D video streaming analysis. Obstacle warning adopt Depth Segmentation, Edge Detection, Contour Extraction position appears to mark the obstacle to voice warning. Use Speeded-Up Robust Features algorithms to extract item and landmarks features, establishment Multiple Randomized Kd Trees characteristic index data matching feature matching algorithm using Approximate Nearest Neighbors. In this experiment, the landmark recognition rate of 85.87%, in item identification recognition rate of 86.16%, the obstacle warning detection rate of 95.67%.Visually impaired test indicates that the secondary has a wearable visual aid to improve their daily lives inconvenience, can help to understand the surrounding information, set up their own mind map.
論文目次:摘 要 i
ABSTRACT ii
誌 謝 iv
目 錄 v
表目錄 vii
圖目錄 viii
第一章 緒論 1
1.1 研究動機 1
1.2 研究目的 3
1.3 論文架構 5
第二章 相關研究與文獻探討 6
2.1 輔助科技輔具 6
2.1.1 導盲輔具現況 7
2.1.2 定向行動導盲儀 7
2.1.3 OrCam視覺輔具 8
2.1.4 穿戴式視障輔具研究 9
2.2 視障者定向行動訓練 9
2.2.1 定向訓練 10
2.2.2 行動訓練 10
2.2.3 陸標與線索 10
2.3 圖形匹配與陸標辨識 11
2.3.1 尺度不變特徵 12
2.3.2 特徵索引結構演算法 13
2.3.3 特徵匹配除錯演算法 14
第三章 系統架構與流程 15
3.1 系統概述 15
3.2 系統架構 16
3.2.1 穿戴式視覺輔具硬體架構 17
3.2.2 陸標圖資共創平台架構 17
3.3 系統運作流程 18
第四章 陸標圖資共創平台 19
4.1 圖像資訊建置 19
4.1.1 建置陸標資訊 20
4.1.2 建置物品資訊 24
4.2 SURF特徵學習 26
4.2.1 SURF特徵抽取 26
4.2.2 特徵篩選與合併 29
4.2.3 建立特徵索引資料庫 31
4.3 建立圖像資訊資料庫 32
第五章 穿戴式視覺辨識輔具 33
5.1 穿戴式輔具設計 33
5.2 即時陸標與物品辨識 34
5.2.1 特徵點比對 34
5.2.2 比對結果除錯 35
5.2.3 圖像資訊標記 37
5.3 障礙物偵測警示 39
5.3.1 深度影像分割 39
5.3.2 障礙物輪廓偵測 40
5.3.3 障礙物位置判別 42
第六章 實驗結果與場域驗證 45
6.1 實驗與系統環境 45
6.2 實驗結果與分析 46
6.2.1 陸標辨識 46
6.2.2 物品辨識 53
6.2.3 障礙物警示 58
6.3 場域驗證與討論 62
第七章 結論與未來展望 66
7.1 結論 66
7.2 未來展望 67
參考文獻 68
論文參考文獻:[1] 行政院主計總處,身心障礙人數統計,來源:http://www.stat.gov.tw/mp.asp?mp=4
[2] 毛連塭,盲童定向移動研究,南投縣:臺灣省視覺障礙兒童混合教育計畫,1995。
[3] 台灣導盲犬協會,導盲犬訓練費用,來源:http://www.guidedog.org.tw/
[4] 柯惠菁譯,身心障礙者的輔助科技,臺北:心理出版社股份有限公司,2009。
[5] 衛福部,認識CNS 15390,來源:http://repat.sfaa.gov.tw/cns/inside_01.asp
[6] 杞昭安,視障者定向行動輔具之研究,特殊教育學報,第十五期,2000,第107-127頁。
[7] Bay Advanced Technologies (BAT), Inc. K-Sonar - Ultrasonic sensing device for the blind & visually impaired. [Online]. Available: http://www.batforblind.co.nz/
[8] Orcam ,[Online].Available: http://www.orcam.com/
[9] A. Aladren, G. Lopez-Nicolas, Luis Puig, and Josechu J. Guerrero,“Navigation Assistance for the Visually Impaired Using RGB-D Sensor With Range Expansion, ”IEEE Systems Journal, vol. 99, 2014, pp. 1-11.
[10] S. Belongie, J. Malik, and J. Puzicha, “Shape Matching and Object Recognition Using Shape Contexts,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 4, 2002, pp. 509-522.
[11] D. G. Lowe, “Distinctive Image Features from Scale-Invariant Keypoints, Cascade Filtering Approach,” International Journal of Computer Vision, vol. 60, no.2, 2004, pp. 91-110.
[12] H. Bay, T. Tuytelaars, and L. Van Gool, “SURF: Speeded Up Robust Features,” Proceedings of European Conference on Computer Vision, 2006, pp. 404-417.
[13] T. Gevers and A. W. M. Smeulders, “Color-Based Object Recognition,” Pattern Recognition, vol. 32, 1999, pp. 453-464.
[14] C. Harris and M. Stephens, “A Combined Corner and Edge Detector,” Proceedings of Alvey Vision Conference, 1988, pp. 147-151.
[15] F. Aldershoff and Th. Gevers, “Visual Tracking and Localisation of Billboards in Streamed Soccer Matches,” SPIE Electronic Imaging, 2004, pp. 408-416.
[16] F. Pelisson, D. Hall, O. Riff, and J. L. Crowley, “Brand Identification Using Gaussian Derivative Histograms,” Machine Vision and Applications, vol. 16, 2003, pp. 41-46.
[17] D. G. Lowe, “Distinctive Image Features From Scale-Invariant Keypoints, Cascade Filtering Approach,” International Journal of Computer Vision, vol. 60, no.2, 2004, pp. 91-110.
[18] Y. Ke and R. Sukthankar, “PCA-SIFT: a more Distinctive Representation for Local Image Descriptors,” Proceedings Conference Computer Vision and Pattern Recognition, 2004, pp. 511-517.
[19] H. Bay, T. Tuytelaars, and L. Van Gool, “SURF: Speeded Up Robust Features,” Proceedings of European Conference on Computer Vision, 2006, pp. 404-417.
[20] L. Juan and O. Gwun, “A comparison of SIFT, PCA-SIFT and SURF,” International Journal of Image Processing, vol.3, 2009, pp. 143-152.
[21] J. S. Beis and D. G. Lowe, “Shape Indexing Using Approximate Nearest-Neighbour Search in High-Dimensional Spaces,” Computer Vision and Pattern Recognition, 1997.
[22] C. Silpa-Anan and R. Hartley, “Optimised KD-Trees for Fast Image Descriptor Matching,” Computer Vision and Pattern Recognition, 2008.
[23] M. Muja and D. G. Lowe, “Fast Approximate Nearest Neighbors with Automatic Algorithm Configuration,” International Conference on Computer Vision Theory and Applications, 2009, pp. 331-340.
[24] D. Dakopoulos and N. Bourbakis, “Wearable Obstacle Avoidance Electronic Travel Aids for Blind: A Survey,” IEEE Trans. Syst., Man, Cybern. C, vol. 40, no. 1, pp. 25–35, Jan. 2010.
[25] R. Öktem, E. Aydin, and N. Cagiltay, “An Indoor Navigation Aid Designed for Visually Impaired People,” in Proc. IEEE IECON, 2008, pp. 2982–2987.
[26] C. S. S. Guimaraes, R. V. Bayan Henriques, and C. E. Pereira, “Analysis and Design of An embedded System to Aid the Navigation of the Visually Impaired,” in Proc. ISSNIP BRC, 2013, pp. 1–6.
[27] J. Liu, C. Phillips, and K. Daniilidis, “Video-Based Localization Without3D Mapping for the Visually Impaired,” in Proc. IEEE CVPRW, Jun. 2010,pp. 23–30.
[28] D. Gutiérrez-Gómez, L. Puig, and J. J. Guerrero, “Full Scaled 3D Visual Odometry from a Single Wearable Omnidirectional Camera,” in Proc.IEEE/RSJ Int. Conf. Intell. Robots Syst., Oct. 2012, pp. 4276–4281.
[29] H. Takizawa, S. Yamaguchi,M. Aoyagi, N. Ezaki, and S.Mizuno, “Kinect Cane: Object Recognition Aids for the Visually Impaired,” in Proc. 6th Int. Conf. HSI, Jun. 2013, pp. 473–478.
[30] Lee , C. H. “An Intelligent Depth-Based Obstacle Detection System for Visually-Impaired Aid Applications,” Paper Presented at the 13th International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS) , Dublin , Ireland , May 23–25, 2012 .
[31] D. Bernabei, F. Ganovelli, M. Di Benedetto, M. Dellepiane, and R. Scopigno. “A low-cost time-critical obstacle avoidance system for the visually impaired,” In International conference on indoor positioning and indoor navigation, Guimaraes, Portugal, 2011
[32] J. A. Delmerico, D. Baran, P. David, J. Ryde, and J. J. Corso. “Ascending Stairway Modeling from Dense Depth Imagery for Travers Ability Analysis,” In Proceedings of IEEE Internation Conference on Robotics and Automation, 2013
[33] C. H. Lee, Y. C. Su, and L. G. Chen. “An intelligent Depth Based Obstacle Detection System for Visually-Impaired Aid Applications,” In WIAMIS, pages 1-4,2012
[34] F. Jabeen, “Intelligent Assistant to Help Blind People for Selecting Wearable Items,” Journal of American Science, Journal of American Science, vol. 7, no. 8, 2011
[35] 林家儒,運用顏色與SURF關鍵點特徵分類之快速多廣告看板計次系統,碩士論文,國立臺北科技大學,臺北,2010。
[36] 黃智澄,針對視障者定向輔助之視覺辨識系統,碩士論文,國立臺北科技大學,臺北,2014。
[37] 郭奕成,具有特定環境分析之視障輔助系統之設計,碩士論文,國立臺北科技大學,臺北,2014。
[38] 蘇仕瑋,以Kinect配合智慧型手機實做盲人輔具系統,碩士論文,國立成功大學,臺南,2013。
論文全文使用權限:同意授權於2015-07-13起公開