現在位置首頁 > 博碩士論文 > 詳目
論文中文名稱:具有特定環境分析之視障輔助系統之設計 [以論文名稱查詢館藏系統]
論文英文名稱:The Design of an Assistant System by Specific Environment Analysis For Visually Impaired [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
中文姓名:郭奕成
英文姓名:Yi-Cheng, Kuo
研究生學號:101598010
學位類別:碩士
語文別:中文
口試日期:2014/07/14
指導教授中文名:張厥煒
指導教授英文名:Chueh-Wei, Chang
口試委員中文名:楊士萱;奚正寧
中文關鍵詞:穿戴式裝置、物件辨識、SURF、霍夫直線
英文關鍵詞:Wearable Devices、Object Recognition、SURF、Hough Line Transform, Assistive technology devices
論文中文摘要:科技來自於人性,至始至終是為了使其生活便利。隨著社會的演進,弱勢族群漸漸受到重視,因此使用科技來解決或協助弱勢族群,使其生活更加友善也成為主要議題。而視障族群雖然有許多可以協助生活的輔具,但是卻仍然有許多困難無法解決,如行走時使用導盲杖無法感測上身的障礙或無法了解周圍環境等問題存在,以致發生危險。
因此本論文之貢獻在於提出一套創新的科技輔具概念,透過穿戴式裝置的軟硬體結合,設計一套可以讓視障者穿戴在身上的輔具系統,透過影像辨識技術,來辨識周遭的環境。
本論文著重在視障者行走時,對於周遭環境的商家看板之辨識系統,與偵測路口斑馬線,避免誤闖車道造成危險等系統。在商家看板系統,透過顏色特徵的彩色直方圖進行畫面上的過濾,再搭配SURF特徵做物件辨識;在斑馬線偵測系統,透過霍夫曼直線的尋找、線段的修補與過濾,並分析斑馬線的紋路來判斷。
本系統可透過模組化之方式,擴充視障者對此輔具之需求及功能,開發出對視障者友善與可行之科技輔具。
論文英文摘要:Technology from humanity, from start to finish is that make our life more convenient. With the evolution of society, Social vulnerable groups getting attention gradually, so use technology to solve or help social vulnerable groups make life more friendly and also have became a major issue. And although there are many Assistive device can assist visually impaired people to live, but there are still many problems can not be solved, such as the use of guide cane can not sense obstacles upper body when walking or unable to understand the environment and other problems, resulting in danger.
Therefore, the contribution of this paper is to propose an innovative Assistive technology devices conception, through a combination of hardware and software wearable device, design a vest for visually impaired person can wear and combine with system which can do image recognition technology to identify around environment.
This paper focuses on the visually impaired people when walking issue. Design a environment recognition system and to detect intersection zebra, avoid straying into dangerous lane systems and billboards when they’re walking. For billboards system, through the color histogram filter object by color feature, and do object recognition by SURF feature; crossing detection system, looking straight through Hough Line, then repairing and filtering line, and analysis zebra crossing texture to judge finally.
The system can be modular for the expansion needs of the visually impaired and function. Developing an friendly and useful Assistive technology devices for visually impaired people.
論文目次:摘 要 i
ABSTRACT ii
誌 謝 iv
目 錄 vi
表目錄 ix
圖目錄 x
第一章 緒論 1
1.1 研究動機 1
1.2 研究目的與貢獻 4
1.3 論文架構 6
第二章 相關研究與文獻探討 7
2.1 視障輔具介紹 7
2.2 穿戴式科技的崛起 9
2.3 圖形匹配與物件辨識 10
2.4擷取物件特徵 12
2.4.1 色彩 12
2.4.2 邊緣 12
2.5 局部影像特徵 12
2.6 尺度不變特徵 13
2.7 SIFT特徵 14
2.8 SURF特徵 15
第三章 系統架構 20
3.1系統概述 20
3.2系統架構 22
第四章 看板辨識系統 26
4.1 特徵學習 26
4.1.1 顏色特徵擷取 26
4.1.2 彩色直方圖 27
4.1.3 SURF特徵點擷取 31
4.2 商家看板偵測 33
4.2.1反向投影(Back Projection) 33
4.2.2形態學處理 34
4.2.3二值化 34
4.2.4侵蝕與膨脹 35
4.2.5尋找輪廓 36
4.3 商家看板辨識 37
4.3.1特徵匹配方法 38
4.3.2特徵描述子間的距離 38
4.3.3合成向量的主要方向 40
4.3.4辨識結果 40
第五章 斑馬線偵測系統 42
5.1 影像前處理 42
5.2 直線偵測 43
5.3 直線修復 45
5.4 過濾非主流線段 46
5.5 尋找黑白紋路 47
第六章 實驗結果 48
6.1 實驗環境 48
6.2實驗結果與探討 48
第七章 結論與未來展望 54
7.1結論 54
7.2未來展望 54
參考文獻 55
論文參考文獻:[1]Wodsworth, R. H.(1983). Basics of audio and visual system design. Washington, D. C.: National Audio-visual Association.
[2]World Blind Union at:
http://www.worldblindunion.org/English/about-wbu/Pages/default.aspx
[3]衛生福利部統計處身心障礙者人數
http://www.mohw.gov.tw/cht/DOS/DisplayStatisticFile.aspx?d=31923&s=1
[4]Global data on visual impairment in the year 2002 at:
http://whqlibdoc.who.int/bulletin/2004/Vol82-No11/bulletin_2004_82(11)_844-851.pdf?ua=1.
[5]Global magnitude of visual impairment caused by uncorrected refractive errors in 2004 at: http://www.who.int/bulletin/volumes/86/1/07-041210.pdf?ua=1
[6]GLOBAL DATA ON VISUAL IMPAIRMENTS 2010 at:
http://www.who.int/blindness/GLOBALDATAFINALforweb.pdf?ua=1
[7]Global brief for World Health Day 2012 at:
http://whqlibdoc.who.int/hq/2012/WHO_DCO_WHD_2012.2_eng.pdf
[8]特殊教育課程發展共同原則及課程大綱總綱及配套措施,定向行動訓練課程 at: http://www.ntnu.edu.tw/spc/drlusp_1/data/s01208.pdf
[9]定向與生活招生網頁文案 - 內政部
at :http://www.moi.gov.tw/files/news_file/定向與生活招生網頁文案.doc
[10]輔具資源入口網-定向輔具
at:http://repat.sfaa.gov.tw/07product/pro_a_list.asp?MM_Query=MM_Query&mcate1=40&mcate2=119
[11]OrCam at : http://www.orcam.com/
[12]CNS15390是什麼?讓小博士來告訴你!!
at : http://repat.sfaa.gov.tw/book/inside_01b.asp?cate_id=40
[13]認識CNS 15390 at : http://repat.sfaa.gov.tw/cns/inside_01.asp
[14]輔具資源入口大類次類新視野 at : http://repat.sfaa.gov.tw/cns/inside_02.asp
[15]定向行動導盲儀(K-Sonar)
at: http://repat.sfaa.gov.tw/07product/pro_a_main.asp?t=2&id=2104
[16]視障輔具介紹與分類 at: 140.128.219.11/school/data/files/201109271713053.ppt
[17]Wearable technology Wiki at http://en.wikipedia.org/wiki/Wearable_technology
[18]C. Harris and M. Stephens, “A Combined Corner and Edge Detector,” Proceedings of Alvey Vision Conference, Manchester, 1988 , pp. 147-151,.
[19]H. P. Moravec, “Towards Automatic Visual Obstacle Avoidance,” Proceedings of the 5th International Joint Conference on Artificial Intelligence, 1977, p.584.
[20]C. Harris and M. Stephens, “A Combined Corner and Edge Detector,” Proceedings of Alvey Vision Conference, Manchester, 1988 , pp. 147-151,.
[21]K. Mikolajczyk and C. Schmid, “Indexing based on Scale Invariant Interest Points,” International Conference on Computer Vision, 2001, pp. 525-531.
[22]D. G. Lowe, “Distinctive image features from scaleinvariant keypoints,” International Journal of Computer Vision, vol. 60, no. 2, pp. 91–1, 2004.
[23]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.
[24]H. Bay, T. Tuytelaars, and L. Van Gool, “SURF: Speeded Up Robust Features,” Proceedings of European Conference on Computer Vision, 2006, pp. 404-417.
[25]L. Ballan, M. Bertini, A. D. Bimbo and A. Jain, “Automatic Trademark Detection and Recognition in Sports Videos,” Media Integration and Communication Center, University of Florence, Italy, 2010.
[26]P. Viola and M. Jones, “Rapid Object Detection Using a Boosted Cascade of Simple Features,” Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol.2, 2003, pp. 1403-1410.
[27]D.Lowe, “Distinctive Image Features from Scale-Invariant Keypoints, Cascade Filtering Approach,” International Journal of Computer Visio, Vol. 60, No.2, pp.91-110, 2004.
[28]Rainer Lienhart and Jochen Maydt, “An Extended Set of Haar-like Features for Rapid Object Detection,” IEEE ICIP, vol. 1, 2002, pp. I-900 – I-903.
[29]L. Juan and O. Gwun, “A Comparison of SIFT, PCA-SIFT and SURF,” International Journal of Image Processing, vol.3, 2009, pp. 143-152.
[30]http://zh.wikipedia.org/zh-tw/HSL%E5%92%8CHSV%E8%89%B2%E5%BD%A9%E7%A9%BA%E9%97%B4
論文全文使用權限:同意授權於2020-04-15起公開