Tracking People with Probabilistic Occlusion Reasoning
Crowd in daily lives are increasing day by day and so in many cases we find a need to track them specially when safety is our primary concern and this is challenging because because people occlude each other when they walk around. The latest revision of person tracker uses adaptive appearance models that explicitly account for the probability that a person may be partially occluded. All potentially occluding targets are tracked jointly, and the most likely visibility order is estimated (so we know the probability that person A is occluding person B). Target size adaptation is performed using calibration information about the camera, and the reported target positions are in real-world coordinates.So here mentioning just a basic idea but actually we can work out in this field to improve our own intelligence and thus help the society.