cvpr cvpr2013 cvpr2013-81 cvpr2013-81-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Aparna Taneja, Luca Ballan, Marc Pollefeys
Abstract: In this paper, we propose a method to detect changes in the geometry of a city using panoramic images captured by a car driving around the city. We designed our approach to account for all the challenges involved in a large scale application of change detection, such as, inaccuracies in the input geometry, errors in the geo-location data of the images, as well as, the limited amount of information due to sparse imagery. We evaluated our approach on an area of 6 square kilometers inside a city, using 3420 images downloaded from Google StreetView. These images besides being publicly available, are also a good example of panoramic images captured with a driving vehicle, and hence demonstrating all the possible challenges resulting from such an acquisition. We also quantitatively compared the performance of our approach with respect to a ground truth, as well as to prior work. This evaluation shows that our approach outperforms the current state of the art.
[1] M. Clerc and J. Kennedy. The particle swarm explosion, stability, and convergence in a multidimensional complex space. IEEE Transactions on Evolutionary Computation, 2002.
[2] N. Cornelis, B. Leibe, K. Cornelis, and L. Gool. 3d urban scene modeling integrating recognition and reconstruction. IJCV, pages 121–141, 2008.
[3] I. Eden and D. B. Cooper. Using 3d line segments for robust and efficient change detection from multiple noisy images. In ECCV, 2008.
[4] P. F. Felzenszwalb, R. B. Girshick, D. McAllester, and D. Ramanan. Object detection with discriminatively trained part based models. PAMI, 2010.
[5] C. Fruh and A. Zakhor. Constructing 3-d city models by merging aerial and ground views. IEEE CGA, 2003.
[6] M. Golparvar-Fard, F. Pena-Mora, and S. Savarese. Monitoring changes of 3d building elements from unordered photo collections. In ICCV Workshops, 2011.
[7] L. Ladicky, C. Russell, P. Kohli, and P. H. Torr. Associative hierarchical crfs for object class image segmentation. In International Conference on Computer Vision, 2009.
[8] L. Liu and I. Stamos. Automatic 3d to 2d registration for the photorealistic rendering of urban scenes. In CVPR, 2005.
[9] P. Lothe, S. Bourgeois, F. Dekeyser, E. Royer, and M. Dhome. Towards geographical referencing of monocular slam reconstruction using 3d city models: Application to real-time accurate vision-based localization. PAMI, 2009.
[10] T. Pollard and J. L. Mundy. Change detection in a 3-d world. In CVPR, 2007.
[11] T. Pylvanainen, K. Roimela, R. Vedantham, J. Itaranta, and R. Grzeszczuk. Automatic alignment and multi-view segmentation of street view data using 3d shape prior. In 3DPVT, 2010.
[12] R. J. Radke, S. Andra, O. Al-Kofahi, and B. Roysam. Image change detection algorithms: A systematic survey. IEEE Transactions on Image Processing, 14:294–307, 2005.
[13] S. Ramalingam, S. Bouaziz, P. Sturm, and M. Brand. Skyline2gps: Localization in urban canyons using omniskylines. In IROS, 2010.
[14] T. Sattler, B. Leibe, and L. Kobbelt. Fast image-based localization using direct 2d-to-3d matching. In ICCV, 2011.
[15] A. Taneja, L. Ballan, and M. Pollefeys. Image based detection of geometric changes in urban environments. In ICCV, 2011.
[16] A. Taneja, L. Ballan, and M. Pollefeys. Registration of spherical panoramic images with cadastral 3d models. In 3DIMPVT, 2012.
[17] W. Zhao, D. Nister, and S. Hsu. Alignment of continuous video onto 3d point clouds. PAMI, 2005. 111 111999 ? ? ?? ? ? ?? ? ? ?? Figu? re5.(Top)Cadstral3Dmodeloverlaidwth evoxelgrid.Voxe?lsdetcedas changear markedinblue.Theinputimagesare shown as green dots, while the green markers indicate some of the changed locations recognized using our approach. (Bottom) Images corresponding to the green markers in the map overlaid with the cadastral model. For locations D, E, F and H please refer to Figure 1. 111222000