Abstract:
This paper proposes CrowdTracker, a novel object tracking system based on mobile crowd sensing (MCS). Different from other studies that are based on video surveillance, CrowdTracker recurits people to collaboratively take photos of the object to achieve object movement prediction and tracking. The optimization objective of CrowdTracker is to effectively track the moving object in real time and minimize the cost of user incentives. The incentive is determined by the number of workers assigned and the total distance that workers move to complete the task. In order to achieve the objective, CrowdTracker proposes an algorithm MPRE to predict the object moving pattern, and two task allocation algorithms, namely T-centric and P-centric, are proposed. T-centric selects workers in a task-centric way, while P-centric allocates tasks in a people-centric manner. By analyzing a large number of historical vehicle trajectories, MPRE builds a moving model of vehicle to predict the object’s next position. In the predicted regions, CrowdTracker selects an optimal set of workers for the tracking task by utilizing T-centric or P-centric. Experiments are conducted on a large-scale real-world dataset. The experimental results show that CrowdTracker can effectively track the object in real time and reduce the incentive cost at the same time.