Abstract: With the development of urbanized transportation, the perceptual computing plays an important role in smart cities. Aiming at the problem that the traditional density clustering algorithm cannot adapt to massive taxi GPS trajectory data and visualization, the BCS-DBSCAN (Big-Data Cluster Center Statistics Density-Based Spatial Clustering of Applications with Noise) clustering algorithm is proposed. The algorithm can segment and parallelize the trajectory data, extract the maximum density cluster, and adapt the result to the visualization model. The experimental results show that compared with other popular methods, this method has significant advantages in extracting clustering speed, accuracy and visualization of urban passenger hotspots from mass data, and provides important decision information for further improving urban planning and traffic efficiency.

Key words: big data segmentation, cluster heart extraction, rapid clustering, hotspot visualization