動態場景光束法平差

Dynamic Scene Bundle Adjustment

竇菲(Andreas Dopfer)

指導教授 ： 莊永裕

國立臺灣大學/電機資訊學院/資訊工程學研究所/博士(2015年)

https://doi.org/10.6342/NTU.2015.02300

摘要

本論文提出一項應用於動態環境下之光線束法平差演算法。根據一個或多個相機的影像，本演算法可重建相機的3D軌跡，以及環境中之靜態與動態物體的3D位置。我們提出一個高效率的低維度表示形式，藉此描述物體與攝影機的軌跡。每一物體的軌跡由一系列基軌跡的線性組合近似而成。我們提出的方法不須倚賴任何對於物體移動方式的事前了解，甚至不須知道物體為靜止與否。同時，與其他方法不同的是，我們可以處理不完全，並具有雜訊的資料。經由模擬與實際測試驗證，本文提出的方法可以有效重建物體與相機的3D軌跡。

關鍵字

光束法平差 ； 動態場景 ； 場景重構 ； 運動回復結構 ； 多台移動相機 ； 軌 跡基底 ； 交通場景重構

並列摘要

This work proposes an extension of Bundle Adjustment to dynamic scenes. In the setting of one or multiple cameras moving in a dynamic environment, the camera pose and the 3D positions of static and moving objects are reconstructed from the captured image sequences. An efficient, low- dimensional representation of the scene is introduced, which is based on approximating trajectories by linear combinations of trajectory bases. Our reconstruction approach requires no knowledge about the objects, not even which are moving or static and is, in difference to other approaches, able to deal with incomplete and noisy data. Experimental evaluation in simulation as well as with real data shows its effectiveness in reconstructing dynamic scenes from moving cameras.

並列關鍵字

Bundle Adjustment ； Dynamic Scene ； Reconstruction ； Structure from Motion ； multiple moving cameras ； Trajectory Bases ； Traffic Scene Reconstruction

參考文獻

[1] Sameer Agarwal, Noah Snavely, Steven M. Seitz, and Richard Szeliski. Bundle adjustment in the large. In Proceedings of the European Confer- ence on Computer Vision (ECCV), pages 29–42. Springer Verlag, Berlin, Heidelberg, 2010.

[3] Ijaz Akhter, Yaser Sheikh, Sohaib Khan, and Takeo Kanade. Trajectory space: A dual representation for nonrigid structure from motion. In IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), volume 33(7), pages 1442–1456, July 2011.

[6] AnatLevin and Richard Szeliski. Visual odometry and map correla- tion. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 611–618, 2004.

[9] Ake Bjo ̈rck. Numerical Methods for Least Squares Problems. Society for Industrial and Applied Mathematics, 1996.

[11] Christoph Bregler, Aaron Hertzmann, and Henning Biermann. Recov- ering non-rigid 3d shape from image streams. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), volume 2, pages 690–696, 2000.