Mining Group Movement Patterns for Tracking Moving Objects Efficiently

Existing object tracking applications focus on finding the moving patterns of a single object or all objects. In contrast, we propose a distributed mining algorithm that identifies a group of objects with similar movement patterns. This information is important in some biological research domains, such as the study of animals’ social behavior and wildlife migration. The proposed algorithm comprises a local mining phase and a cluster ensembling phase. In the local mining phase, the algorithm finds movement patterns based on local trajectories. Then, based on the derived patterns, we propose a new similarity measure to compute the similarity of moving objects and identify the local group relationships. To address the energy conservation issue in resource-constrained environments, the algorithm only transmits the local grouping results to the sink node for further ensembling. In the cluster ensembling phase, our algorithm combines the local grouping results to derive the group relationships from a global view. We further leverage the mining results to track moving objects efficiently. The results of experiments show that the proposed mining algorithm achieves good grouping quality, and the mining technique helps reduce the energy consumption by reducing the amount of data to be transmitted.