Figure 2. (a) A multiple-person scenario with 3 people and 3 cameras. (b)The dependency graph obtained if all cameras are used for estimation of all people. An edge A → B represents the information flow from A to B in the inference process-hence estimation of B depends on estimation of A. In this scenario, estimation of B depends on A due to occlusion in camera 1 and estimation of A and C depends on B and A respectively due to occlusions in cameras 3 and 2 respectively. (c) The dependency graph obtained if cameras are selected using COST. The selected cameras for estimation of each person are shown in the respective node. Since, camera 1 is not used for estimation of B , the estimation of B becomes independent of A. Additionally, if the degree of occlusion of C due to A is small (that is one cannot generate significant information for the estimation of C using the estimate of the location or pose of A) then one can also eliminate the dependency edge A → C without strongly affecting the accuracy of the result. Such elimination can be critical for loop removal when there are not enough cameras in which a person is isolated and discriminable.
...read more