Itai Katz
ABSTRACT
Monitoring the status of construction activity is a key factor in maximizing efficiency and reducing cost on capital construction sites. In contrast to human inspection, an automated technology would provide more frequent updates. However, real-time construction site monitoring remains an elusive goal because of many factors including the environment's large size and dynamic behavior. Calibrated camera networks have recently been developed to enable smart environments, where the location of people and objects in the scene are updated in real-time. Despite a growing interest in this technology, a detailed performance analysis has not been conducted. In this paper, empirical results on the calibration and static 3D localization error are presented for a calibrated camera network prototype using four cameras. Using a total station to provide ground truth, the cameras are calibrated and points in the workspace are reconstructed in 3D by combining observations from each image plane. Results show that performance is well suited for localizing objects typically found on a construction site (although scaling errors have not yet been characterized).
- Y. I. Abdel-Aziz and H. M. Karara. Direct linear transformation from comparator coordinates into object space coordinates in close-range photogrammetry. In Proceedings of the Symposium on Close-Range Photogrammetry, Falls Church, Virginia, 1971. American Society of Photogrammetry.Google Scholar
- P. Carr, P. J. Thomas, and R. Hornsey. Performance benefits and limitations of a camera network. In Proceedings of SPIE Digital Wireless Communications VII and Space Communication Technologies, volume 5819, pages 328--339, March 2005.Google Scholar
- R. I. Hartley and A. Zisserman. Multiple View Geometry in Computer Vision. Cambridge University Press, ISBN: 0521623049, 2000. Google ScholarDigital Library
- R. Rosenholtz, Y. Li, and L. Nakano. Measuring visual clutter. Journal of Vision, 7(2):1--22, 2007.Google ScholarCross Ref
- Z. Zhang. A flexible new technique for camera calibration. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000. Google ScholarDigital Library
Recommendations
Keeping a Pan-Tilt-Zoom Camera Calibrated
Pan-tilt-zoom (PTZ) cameras are pervasive in modern surveillance systems. However, we demonstrate that the (pan, tilt) coordinates reported by PTZ cameras become inaccurate after many hours of operation, endangering tracking and 3D localization ...
Performance Evaluation of Multi-camera Visual Tracking
AVSS '12: Proceedings of the 2012 IEEE Ninth International Conference on Advanced Video and Signal-Based SurveillanceMain drawbacks in single-camera multi-target visual tracking can be partially removed by increasing the amount ofinformation gathered on the scene, i.e. by adding cameras. By adopting such a multi-camera approach, multiple sensors cooperate for overall ...
3D Scene Reconstruction with an Un-calibrated Light Field Camera
AbstractThis paper is concerned with the problem of multi-view 3D reconstruction with an un-calibrated micro-lens array based light field camera. To acquire 3D Euclidean reconstruction, existing approaches commonly apply the calibration with a ...
Comments