New Sensing Strategies for Monitoring Moving Polyhedral Objects by Machine Vision

A new set of sensing strategies for monitoring Three-dimensional (3-D) moving objects by computer vision is proposed. Here 3-D object surface points are selected as the features for monitoring 3-D moving objects because the point features are easy to detect, extract, store, and manipulate. It is proved that the minimum measurable feature point set for monitoring a 3-D moving convex polyhedral object is just the set containing all the junction points of the object. Based on the sampling theorem and several properties of photogrammetry, it is proved that the minimum data acquisition rate of a vision system monitoring 3-D moving objects can be determined with discretely sampled two-dimensional image sequence data only. Certain properties of orthographic projection useful for determining the minimum number Ns of sensors needed to monitor 3-D moving convex polyhedral objects are investigated, and the bounds on Ns are also derived. Finally, an algorithm for determining Ns and the corresponding directions of the sensors is proposed. The feasibility of the proposed algorithm is shown by three illustrative examples and an application example.