A distributed smart camera network is a collective of vision-capable devices with enough processing power to execute algorithms for collaborative vision tasks. A true 3D sensing network applies to a broad range of applications, and local stereo vision capabilities at each node offer the potential for a particularly robust implementation. A novel spatial calibration method for such a network is presented, which obtains pose estimates suitable for collaborative 3D vision in a distributed fashion using two stages of registration on robust 3D features. The method is first described in a general, modular sense, assuming some ideal vision and registration algorithms. Then, existing algorithms are selected for a practical implementation. The method is designed independently of networking details, making only a few basic assumptions about the underlying network's capabilities. Experiments using both software simulations and physical devices are designed and executed to demonstrate performance. |