Clustering Moving Objects Using Segments Slopes

Given a set of moving object trajectories, we show how to cluster them using k-means clustering approach. Our proposed clustering algorithm is competitive with the k-means clustering because it specifies the value of “k” based on the segment’s slope of the moving object trajectories. The advantage of this approach is that it overcomes the known drawbacks of the k-means algorithm, namely, the dependence on the number of clusters (k), and the dependence on the initial choice of the clusters’ centroids, and it uses segment’s slope as a heuristic to determine the different number of clusters for the k-means algorithm. In addition, we use the standard quality measure (silhouette coefficient) in order to measure the efficiency of our proposed approach. Finally, we present experimental results on both real and synthetic data that show the performance and accuracy of our proposed technique.