Calibration of Large Sensor Networks using Observed Motion Trajectories

We present a technique for the registration of a network of surveillance cameras through the automatic alignment of observed planar motion trajectories. The algorithm address the problem of recovering the relative pose of several stationary, networked cameras whose intrinsic parameters are known. Each camera tracks several objects to produce a set of trajectories in the image. Using temporal and geometric constraints derived from the trajectory and a network synronization signal, overlapping viewing frustrums are determined and corresponding cameras are calibrated. Full calibration is a two stage process. Initially, the relative orientation of each camera to the local ground plane, is computed in order to compute the projective mapping of image points to world trajectories embedded on a nominal plane of correct orientation. Projectively unwarped trajectory curves are then matched by solving for the a ne transformation that bring them into alignment. Registration aligns n-cameras with respect to each other in a single camera frame (that of the reference camera). The approach recovers both the epipolar geometry between all cameras and the camera-to-ground rotation for each camera. After calibration, points that are known to lay on a world ground plane can be directly backprojected into each of the camera frames. The algorithm is demonstrated for two, three, and ve camera scenarios by tracking pedestrians as they move through a surveillance area and matching the resulting trajectories. This work was supported in part by NSF grant number 9818332.