基於搜尋系統與快速空間關係驗證之多物件辨識及定位

Multiple Object Localization by Search-based Object Recognition and Fast Geometric Verification

林芳而(Fang-Erh Lin)

指導教授 ： 徐宏民

國立臺灣大學/電機資訊學院/資訊網路與多媒體研究所/碩士(2012年)

https://doi.org/10.6342/NTU.2012.02894

摘要

由於廣大的應用範圍及講求高效率的執行速度，近年來多物件的辨識與定位成為一個重要的問題。早期的研究只有在小型的資料庫中搜尋，因此能在短時間內搜尋與定位；我們希望除了能夠在龐大的物件圖片資料庫中準確辨識目標圖片中的物件與標出位置，也能夠在短時間內完成動作。這篇論文中，我們提出兩種演算法Adaptive Window Search和Hierarchical Cluster Search，利用物件辨識系統對目標圖片進行多物件的搜尋與定位，也提出一個加速演算法FastGV以減短物件定位的時間。實驗結果顯示我們提出的演算法在多物件的辨識與定位有很高的準確率，同時有效縮短在大型物件資料庫中的搜尋與定位時間。

關鍵字

多物件辨識 ； 多物件搜尋 ； 物件定位 ； 關係驗證

並列摘要

Multiple object localization and recognition has been an important problem in recent years not only because of its difficulty to be time efficient but also due to many different schemes of widespread applications. In many previous works, only a limited amount of object models contribute to less computational time. However, they tend to not work efficiently together with large-scale database. In this paper, we propose two search algorithm and search-based object recognition system to recognize and localize multiple objects in an image with a large-scale database. Since we tackle this problem with the idea that users can get brief information of an item immediately after taking only a snapshot, a low response time is also taken into account. Therefore, we propose a new spatial verification algorithm to improve the speed of localizing objects. We implement the algorithms within a large-scale book recognition system and present experimental results that demonstrate the efficiency of our algorithms in terms of detection recall, precision, and speed compared to the baseline and efficient subwindow search (ESS) approaches.

並列關鍵字

Multiple object recognition ； multiple object retrieval ； object localization ； geometric verification

參考文獻

[2] Sam S. Tsai, David Chen, Vijay Chandrasekhar, Gabriel Takacs, Ngai-Man Cheung, Ramakrishna Vedantham, Radek Grzeszczuk, and Bernd Girod, “Mobile product recognition,” in Proceedings of the international conference on Multimedia, New York, NY, USA, 2010, pp. 1587–1590, ACM.

[7] Martin A. Fischler and Robert C. Bolles, “Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography,” Communications of the ACM, 1981.

[10] Krystian Mikolajczyk and Cordelia Schmid, “Scale and affine invariant interest point detectors,” International Journal of Computer Vision, vol. 60, pp. 63–86, 2004.

[12] J. Matas, O. Chum, M. Urban, and T. Pajdla, “Robust wide-baseline stereo from maximally stable extremal regions,” Image and Vision Computing, vol. 22, no. 10, pp. 761–767, 2004.

[13] David G. Lowe, “Distinctive image features from scale-invariant keypoints,” International Journal of Computer Vision, vol. 60, no. 2, pp. 91–110, November 2004.