Abstract
In a wide-area camera network, cameras are often placed such that their views do not overlap. Collaborative tasks such as tracking and activity analysis still require discovering the network topology including the extrinsic calibration of the cameras. This work addresses the problem of calibrating a fixed camera in a wide-area camera network in a global coordinate system so that the results can be shared across calibrations. We achieve this by using commonly available mobile devices such as smartphones. At least one mobile device takes images that overlap with a fixed camera's view and records the GPS position and 3D orientation of the device when an image is captured. These sensor measurements (including the image, GPS position, and device orientation) are fused in order to calibrate the fixed camera. This article derives a novel maximum likelihood estimation formulation for finding the most probable location and orientation of a fixed camera. This formulation is solved in a distributed manner using a consensus algorithm. We evaluate the efficacy of the proposed methodology with several simulated and real-world datasets.
- Hamid K. Aghajan and Andrea Cavallaro. 2009. Multi-Camera Networks: Principles and Applications 1st Ed. Academic Press, Waltham, MA. Google ScholarDigital Library
- A. J. Davison. 2003. Real-time simultaneous localisation and mapping with a single camera. In Proceedings of the 9th IEEE International Conference on Computer Vision. IEEE, 1403--1410. Google ScholarDigital Library
- John C. Gower and Garmt B. Dijksterhuis. 2004. Procrustes Problems. Oxford University Press, New York.Google Scholar
- Asaad Hakeem, R. Vezzani, Mubarak Shah, and R. Cucchiara. 2006. Estimating geospatial trajectory of a moving camera. In Proceedings of the 18th International Conference on Pattern Recognition. Vol. 2. IEEE, 82--87. Google ScholarDigital Library
- Richard Hartley and Andrew Zisserman. 2000. Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge, UK. Google ScholarDigital Library
- James Hays and Alexei A. Efros. 2008. IM2GPS: Estimating geographic information from a single image. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 1--8.Google Scholar
- Nathan Jacobs, Scott Satkin, Nathaniel Roman, Richard Speyer, and Robert Pless. 2007. Geolocating static cameras. In Proceedings of the International Conference on Computer Vision. IEEE.Google ScholarCross Ref
- Hideyuki Kume, Takafumi Taketomi, Tomokazu Sato, and Naokazu Yokoya. 2010. Extrinsic camera parameter estimation using video images and GPS considering GPS positioning accuracy. In Proceedings of the 20th International Conference on Pattern Recognition. IEEE, 3923--3926. Google ScholarDigital Library
- Maxime Lhuillier. 2011. Fusion of GPS and structure-from-motion using constrained bundle adjustments. In Proceedings of the Conference on Computer Vision and Pattern Recognition. IEEE, 3025--3032. Google ScholarDigital Library
- David G. Lowe. 2004. Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vision 60, 2, 91--110. Google ScholarDigital Library
- Yi Ma, Jana Kosecka, and Shankar Sastry. 2001. Optimization criteria and geometric algorithms for motion and structure estimation. Int. J. Comput. Vision 44, 3, 219--249. Google ScholarDigital Library
- Daniel Martinec and Tomas Pajdla. 2006. 3D Reconstruction by gluing pair-wise euclidean reconstructions, or “how to achieve a good reconstruction from bad images.” In Proceedings of the 3rd International Symposium on 3D Data Processing, Visualization, and Transmission (3DPVT'06). IEEE, 25--32. Google ScholarDigital Library
- Bogdan C. Matei, Harpreet S. Sawhney, and Supun Samarasekera. 2011. Vehicle tracking across nonoverlapping cameras using joint kinematic and appearance features. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 3465--3472. Google ScholarDigital Library
- M. Pollefeys, D. Nistér, et al. 2008. Detailed real-time urban 3d reconstruction from video. Int. J. Comput. Vision 78, 2, 143--167. Google ScholarDigital Library
- Srikumar Ramalingam, Sofien Bouaziz, Peter Sturm, and Matthew Brand. 2009. Geolocalization using skylines from omni-images. In Proceedings of the IEEE Workshop on Search in 3D and Video. IEEE.Google ScholarCross Ref
- Duncan Robertson and Roberto Cipolla. 2004. An image-based system for urban navigation. In Proceedings of the British Machine Vision Conference. BMVA, Malvern, Worcestershire, UK.Google ScholarCross Ref
- Aswin C. Sankaranarayanan, Ashok Veeraraghavan, and Rama Chellappa. 2008. Object detection, tracking and recognition for multiple smart cameras. Proc. IEEE 96, 10, 1606--1624.Google ScholarCross Ref
- David Schleicher, L. M. Bergasa, Manuel Ocaña, Rafael Barea, and Elena López. 2009. Real-time hierarchical GPS aided visual SLAM on urban environments. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA'09). IEEE, 4381--4386. Google ScholarDigital Library
- Noah Snavely, Steven M. Seitz, and Richard Szeliski. 2007. Modeling the world from internet photo collections. Int. J. Comput. Vision 80, 2, 189--210. Google ScholarDigital Library
- Richard Szeliski. 2005. Where am I?: ICCV 2005 Computer Vision Contest. http://research.microsoft.com/iccv2005/Contest/.Google Scholar
- Roberto Tron and René Vidal. 2009. Distributed image-based 3-D localization of camera sensor networks. In Proceedings of the IEEE Conference on Decision and Control. IEEE.Google ScholarCross Ref
- W. Wang and Hung Tat Tsui. 2000. A SVD decomposition of essential matrix with eight solutions for the relative positions of two perspective cameras. In Proceedings of the 15th International Conference on Pattern Recognition. IEEE, 362--365. Google ScholarDigital Library
- Yuji Yokochi, Sei Ikeda, Tomokazu Sato, and Naokazu Yokoya. 2006. Extrinsic camera parameter estimation based on feature tracking and GPS data. In Proceedings of the 7th Asian Conference on Computer Vision. Springer, 369--378. Google ScholarDigital Library
- Wei Zhang and Jana Kosecka. 2006. Image based localization in urban environments. In Proceedings of the 3rd International Symposium on 3D Data Processing, Visualization, and Transmission. IEEE. Google ScholarDigital Library
Index Terms
- Calibrating a wide-area camera network with non-overlapping views using mobile devices
Recommendations
Stereo Camera Tracking for Mobile Devices
CVPRW '13: Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition WorkshopsWe present our current work on a camera tracking algorithm designed for a mobile device equipped with a stereo camera. The tracker runs in real-time on a prototype mobile platform and it can be used as the core engine of augmented reality applications. ...
Continuous localization and mapping of a pan---tilt---zoom camera for wide area tracking
Pan---tilt---zoom (PTZ) cameras are well suited for object identification and recognition in far-field scenes. However, the effective use of PTZ cameras is complicated by the fact that a continuous online camera calibration is needed and the absolute ...
Object Inter-camera Tracking with Non-overlapping Views: A New Dynamic Approach
CRV '10: Proceedings of the 2010 Canadian Conference on Computer and Robot VisionDisjoint inter-camera object tracking is the task of tracking objects across video-surveillance cameras that have non-overlapping views. Unlike the closely related task of single-camera tracking, disjoint inter-camera tracking is difficult due to the ...
Comments