跳到主要內容

臺灣博碩士論文加值系統

(44.211.117.197) 您好!臺灣時間:2024/05/23 11:36
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:黃士豪
論文名稱:基於局部學習對車牌影像超解析化
論文名稱(外文):Local Learning-Based Image Super-Resolution on License Plates
指導教授:陳世旺陳世旺引用關係梁祐銘
學位類別:碩士
校院名稱:國立臺灣師範大學
系所名稱:資訊工程研究所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2011
畢業學年度:100
語文別:中文
論文頁數:55
中文關鍵詞:超解析化流形學習局部線性嵌入車牌偵測
外文關鍵詞:super-resolutionmanifold learninglocally linear embeddinglicense plate detection
相關次數:
  • 被引用被引用:0
  • 點閱點閱:213
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
由於監視攝影器材被廣泛地架設,視訊監控系統更顯得其重要性。這些攝影器材所儲存之視訊紀錄(Video Record)也常常變成警方辦案時重要之協助資源,藉由車牌辨識,可以找出違規車輛。為了節省成本,這些監視攝影機之解析度通常都不可能太高,加上監視器材通常被架設在路旁高處,監視器材與車子之間必然存在著相當大之距離;因此,超解析化可以讓原本太小而模糊不清之影像,將其放大而較不失真,可以看得更清楚,以利於後續之應用。

本論文先針對監視器之低解析度影像進行車牌擷取動作,接著再將取得之低解析度車牌進行超解析化之方法;本論文使用以學習為基礎之演算法,利用流形學習(Manifold Learning)之局部線性嵌入(Locally Linear Embedding, 簡稱LLE)概念,將輸入之低解析度車牌影像,經由事先取得一群高解析度及其對應低解析度之影像配對,藉由LLE之概念,從低解析度部分找出相似之局部幾何(Local Geometry),再利用其對應之高解析度部分,產生此輸入影像對應高解析度之模樣,組合成一張對應之高解析度車牌影像。

本論文提出之超解析化方法所產生的清楚車牌與使用一般放大方法在同樣放大倍率之下,細節上顯得更清楚及平滑。此外,此方法僅需使用單張影像即可,相較於傳統使用多張或連續影像,利用前後影像關係提升解析度之方法來得更快速及方便。

Surveillance camera equipment is mounted, video surveillance systems even more important. Video records are often turned into the police handling assistance resources through license plate recognition. License plate recognition (LPR) usually plays an important role in video surveillance systems. In order to save costs, the resolution of these surveillance cameras is usually not too high, the objective of super- resolution (SR) on license plate images is to enhance the resolution of those images. In this paper, we propose a learning-based SR approach on license plate images. First, several high-resolution (HR) license plate images and the generated corresponding LR ones are first collected as the training images. Next, the clustered HR and LR patch pairs are obtained from the training images. Then, license plates are extracted from a LR traffic surveillance image and cut into overlapped patches, and the clustered HR and LR patch pairs are used to generate the HR patch for each cut LR patch by using locally linear embedding (LLE) algorithm. Finally, the HR license plate images can be reconstruction. Preliminary experiments on realistic image data demonstrate the applicability of the proposed approach.
摘要 I
Abstract II
致謝 III
目錄 IV
附圖目錄 VI
附表目錄 IX
第一章 緒論 1
1.1、研究背景: 1
1.2、研究目的: 3
1.3、文獻探討: 5
1.4、論文架構: 10
第二章 系統流程 11
2.1、系統流程: 11
2.1.1、前處理: 12
2.1.2、車牌擷取: 13
2.1.3、超解析化處理: 14
第三章 車牌影像擷取 16
3.1、高斯混合背景模型(Gaussian Mixture Background Model): 16
3.1.1、高斯混合背景模型之建立: 17
3.1.2、高斯混合背景模型之更新: 19
3.2、前景擷取(Foreground Extraction): 24
3.3、車牌擷取(License Plate Extraction): 27
第四章 影像超解析化 29
4.1、高解析度車牌影像之訓練 30
4.1.1、重疊小片切割(Overlapped Patches Cutting): 32
4.1.2、特徵擷取(Feature Extraction): 33
4.1.3、分群(Clustering): 34
4.2、高解析度小片產生(High Resolution Patch Generation): 37
4.3、高解析度車牌影像之重建: 41
第五章 實驗結果 42
第六章 結論及未來方向 49
6.1、結論: 49
6.2、未來方向: 50
參考文獻 51

[Ana08] C. Anagnostopoulos, I. Anagnostopoulos, V. Loumos, and E. Kayafas, “License Plate Recognition from Still Images and Video Sequences: A Survey,” IEEE Transactions on Intelligent Transportation Systems, vol. 9, no. 3, pp. 377- 391, 2008.

[Bis03] C. M. Bishop, A. Blake, and Bhaskara Marthi, “Super-Resolution Enhancement of Video,” Proceedings of the 9th International Conference on Artificial Intelligence and Statistics, Key West, Florida, January 3-6, 2003.

[Cha04] H. Chang, D.-Y. Yeung, and Y. Xiong, “Super-resolution through neighbor embedding,” IEEE conference on Computer Vision and Pattern Recognition, vol. 1, pp. 275-282, 2004.

[Che11] J.T. Chen and H.K. Xiong “Super-Resolution Reconstruction with Prior Manifold on Primitive Patches for Video Compression,” IEEE 13th International Workshop on Multimedia Signal Processing, pp. 1-6, 17-19 Oct. 2011.

[Fan07] W. Fan and D. Y. Yeung “Image Hallucination Using Neighbor Embedding over Visual Primitive Manifolds,” IEEE conference on Computer Vision and Pattern Recognition, pp. 1-7, 17-22 June 2007.

[Far03] S. Farsiu, M.D Robinson, M. Elad, and P. Milanfar,, “Fast and robust multi-frame super-resolution,” IEEE Transactions on Image Processing, vol. 13, no. 10, pp. 1327-1344, 2003.

[Hao09] S. Hao, L. Lin, Z. Weiping, and L. Limin, “Location and Super-resolution Enhancement of License Plates Based on Video Sequences,” Proceedings of the 1st International Conference on Information Science and Engineering, Nanjing, China, pp. 1319-1322, 26-28 Dec. 2009.

[Lai10] Y. C. Lai, Y. M. Liang, S. W Shih, H. Y. Mark Liao, and C. C. Lin, “Linear Production Game Solution to a PTZ Camera Network,” Proceedings of IEEE International Conference on Image Processing, Hong Kong, pp. 4317-4320, 26-29 Sept. 2010.

[Lin04] Z. Lin and H. Y. Shum, “Fundamental Limits of Reconstruction Based Super-resolution Algorithms under Local Translation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 26, no. 1, pp83- 97, 2004.

[Lu11] X. Q. Lu1, H.L. Yuan, Y. Yuan, P.K. Yan, L.Q. Li and X.L. Li ” Local Learning-Based Image Super-Resolution,” IEEE International Workshop on Multimedia Signal Processing, pp. 1-5, 17-19 Oct. 2011.

[Ngu00] N. Nguyen, and P. Milanfar, “An Efficient Wavelet-Based Algorithm for Image Super-resolution,” Proceedings of the IEEE International Conference on Image Processing, vol.2, pp. 351- 354, 10-13 Sept. 2000.

[Ngu10] C. D. Nguyen, Mohsen Ardabilian, L. M. Chen “Unifying Approach for Fast License Plate Localization and Super-Resolution,” International Conference on Pattern Recognition, pp. 376-379, 23-26 Aug. 2010.

[Par03] S. C. Park, M. K. Park, and M. G. Kang, “Super-Resolution Image Reconstruction: A Technical Overview,” IEEE Signal Processing Magazine, vol. 20, no. 3, pp. 21- 36, May 2003.

[Rhe99] S. H. Rhee and M. G. Kang, “Discrete Cosine Transform based regularized high-resolution image reconstruction algorithm,” Optical Engineering, vol. 38, no. 8, pp. 1348-1356, 1999.

[Sur06] K. V. Suresh and A. N. Rajagopalan “A Discontinuity Adaptive Method for Super-Resolution of License Plates,” Computer Vision, Graphics and Image Processing, P. Kalra and S. Peleg Eds. Springer Berlin Heidelberg, vol. 4338, pp. 25- 34, 2006.

[Sur07] K. V. Suresh, G. M. Kumar, and A. N. Rajagopalan, “Super-resolution of License Plates in Real Traffic Videos,” IEEE Transactions on Intelligent Transportation Systems, vol. 8, no. 2, pp. 321- 331, Jun. 2007.

[Tan06] M. Tanaka and M. Okutomi, “A Fast MAP-based Super-resolution Algorithm for General Motion,” Proceedings of SPIE Electronic Imaging, San Jose, CA, vol. 6065, pp. 404-415, 2006.

[Tsa84] R. Y. Tsai and T. S. Huang, “Multi-frame Image Restoration and Registration,” in Advances in Computer Vision and Image Processing, vol. 1, chapter 7, JAI Press, Greenwich, Conn, USA, pp. 317- 339, 1984.

[Wu06] H. H. P. Wu, H. H. Chen, R. J. Wu, D. F. Shen “License Plate Extraction in Low Resolution Video,” International Conference on Pattern Recognition, vol. 1, pp. 824-827, 2006.

[Yan11] M. C. Yang, C. H. Wang, T. Y. Hu, and Y. C. Frank Wang “Learning Context-Aware Sparse Representation For Single Image Super-Resolution,” IEEE 18th International Conference on Image Processing, pp. 1349-1352, 11-14 Sept. 2011.

[Yua08] J. Yuan, S. D. Du, and X. Zhu, “Fast Super-resolution for License Plate Image Reconstruction,” Proceedings of the 19th International Conference on Pattern Recognition, Tampa, FL, pp. 1-4, 8-11 Dec. 2008.

[黃02] 黃一民 “超解析技術應用於影像放大之研究,” 國立成功大學資訊系, 碩士論文, 2003.

[李10]李建興 游凱倫 林應璞, “即時動態車牌辨識,” Journal of Technology, Vol. 25, No. 2, pp. 151-165, 2010.

[林02] 林榮朗 “動態及靜態影像放大之研究,” 國立成功大學資訊系, 碩士論文,2002

連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top