Google街景影像用於場景重現之研究｜國立臺灣科技大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	陳冠宇 Guan-Yu Chen
論文名稱：	Google街景影像用於場景重現之研究 Scene Reconstructing Using Google Street View Images
指導教授：	楊傳凱 Chuan-Kai Yang
口試委員:	花凱龍 Kai-Lung Hua 孫沛立 Pei-Li Sun
學位類別：	碩士 Master
系所名稱：	管理學院 - 資訊管理系 Department of Information Management
論文出版年：	2018
畢業學年度：	106
語文別：	中文
論文頁數：	46
中文關鍵詞：	虛擬實境、SIFT 、SURF 、全景影像
外文關鍵詞：	Virtual Reality, SIFT, SURF, Panorama images
相關次數：	點閱：235 下載：0
分享至:	分享至facebook 分享至twitter

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

照片是一種紀錄生活的方式，每當人們看到相片就能回憶起當時的時空與場景，但是相片無法提供當時的場景太多的資訊，本研究希望應用虛擬實境(Virtual Reality)的技術，讓使用者獲得舊地重遊的體驗。
本論文提出能夠重現相片360度場景並且找出照片在場景中對應角度的系統，根據使用者相片所提供的GPS資訊，透過Google Street View Image API取得該地點的街景圖，利用影像拼接製作全景圖，並將其貼在球體上呈現出360度場景的效果，但由於GPS的誤差問題，本論文會透過API抓取輸入相片GPS位置附近一個範圍內多個點的相片，並透過加速穩健特徵演算法(SURF)，對範圍內的每一張街景圖和使用者所輸入的影像進行特徵點的比對，改善GPS精確度的問題，並找相片相對應的角度。

Taking photos is a way to record a person’s life. The photographs can stir up people’s old memories, but it doesn’t provide too much information of scenes. To address this, we want to use the Virtual Reality technology to reconstruct 360 degree scenes to let a user virtually revisit the place again by using our system.
To achieve our goal, this paper proposed a system which can automatically reconstruct 360 degree panorama images corresponding to the place where the input photographs were taken. By using input photo’s GPS information, we can get the
street view images from Google Street View Image API. Then we got these stress view images to do the image stitching, and we can get the 360 degree panoramic image which serves as a texture to be applied on a sphere to let a user to have a feeling of going back to the place for taking photos. However, GPS information has a problem of accuracy. Therefore, we get the street view images from neighbor positions, and using the SURF algorithm to ﬁnd the local features from each street view image, by doing the features matching to ﬁnd the best similar position.

中文摘要.................................................................. III
英文摘要.................................................................. IV
誌謝 ...................................................................... V
目 錄 ..................................................................... VI
圖目錄 .................................................................... VIII
表目錄 .................................................................... X
第一章 緒論 .............................................................. 1
1 研究動機與目的 ............................................................ 1
2 論文架構 .................................................................... 2
第二章 文獻探討 ......................................................... 3
1 Google Street View Image API ............................................ 3
2 影像檢索 .................................................................... 3
3 SIFT特徵 ................................................................... 4
3.1 尺度空間極值偵測 . . . . . . . . . . . . . . . . . . . . . . . . 4
3.2 特徵點定位 . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6
3.3 方向定位 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
3.4 關鍵點描述子 . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
4 PCA-SIFT特徵 ............................................................. 7
5 SURF特徵 .................................................................. 8
6 特徵點演算法比較.......................................................... 11
7 RANSAC.................................................................... 11
8 影像拼接 .................................................................... 12
9 影像填補 .................................................................... 12
第三章 演算法設計與系統實作............................................ 15
1 系統流程 .................................................................... 15
2 特徵點比對.................................................................. 16
2.1 街景影像下載 . . . . . . . . . . . . . . . . . . . . . . . . . . . 16
2.2 特徵點比對 . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
3 全景圖合成.................................................................. 23
3.1 下載比對結果的圖 . . . . . . . . . . . . . . . . . . . . . . . . 23
3.2 影像拼接 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23
3.3 影像填補 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24
4 360呈現 ..................................................................... 27
第四章 實驗結果 ......................................................... 29
1 系統環境 .................................................................... 29
2 系統介面與功能 ............................................................ 30
3 實驗結果 .................................................................... 33
4 實驗評估 .................................................................... 43
第五章 結論與未來展望................................................... 44
參考文獻.................................................................. 45
                                

[1] https://blog.csdn.net/songzitea/article/details/16986423.
[2] A. Anandh, K. Mala, and S. Suganya. Content based image retrieval system based on semantic information using color, texture and shape features. 2016 International Conference on Computing Technologies and Intelligent Data Engineering ICCT IDE016, 2016.
[3] Herbert Bay, Tinne Tuytelaars, and Luc Van Gool. Surf: Speeded up robust features. In In ECCV, pages 404–417, 2006.
[4] Matthew Brown and David G. Lowe. Automatic panoramic image stitching using invariant features. 2007.
[5] Martin A. Fischler and Robert C. Bolles. Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM, 24(6):381–395, June 1981.
[6] Tao He, Yong Wei, Zhijun Liu, Guorong Qing, and Defen Zhang. Content based image retrieval method based on sift feature. 2018 International Conference on Intelligent Transportation, Big Data & Smart City (ICITBS), 2018.
[7] Chi-Chang Hsieh, Wen-Huang Cheng, Chia-Hu Chang, Yung-Yu Chuang, and Ja-Ling Wu. Photo navigator. In ACM Multimedia, pages 419–428. ACM, 2008.
[8] Shiuan Huang and Hsueh-Ming Hang. Multi-query image retrieval using cnn and sift features. 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference AP SIP AASC, 2017.
[9] Luo Juan, Oubong Gwun, Luo Juan, and Oubong Gwun. A comparison of sift, pca-sift and surf.
[10] Yan Ke and Rahul Sukthankar. Pca-sift: A more distinctive representation for local image descriptors. pages 506–513, 2004.
[11] Jan J. Koenderink. The structure of images. Biological Cybernetics, 50:363–370, 1984.
[12] Tony Lindeberg. Scale-space theory: A basic tool for analysing structures at different scales. Journal of Applied Statistics, 21:224–270, 1994.
[13] David G. Lowe. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60:91–110, 2004.
[14] Prinka and Vikas Wasson. An efficient content based image retrieval based on speeded up robust features (surf) with optimization technique. 2017 2nd
IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology RT EICT, 2017.
[15] Alexandru Telea. An image inpainting technique based on the fast marching method. J. Graphics, GPU, & Game Tools, 9(1), 2004.

全文公開日期 2023/07/12 (校內網路)
全文公開日期本全文未授權公開 (校外網路)
全文公開日期本全文未授權公開 (國家圖書館：臺灣博碩士論文系統)

簡易檢索 / 詳目顯示

相關論文