Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-2/W7, 1319-1325, 2017
https://doi.org/10.5194/isprs-archives-XLII-2-W7-1319-2017
© Author(s) 2017. This work is distributed under
the Creative Commons Attribution 4.0 License.
 
14 Sep 2017
HOTSPOTS DETECTION FROM TRAJECTORY DATA BASED ON SPATIOTEMPORAL DATA FIELD CLUSTERING
K. Qin1,2, Q. Zhou1, T. Wu3, and Y. Q. Xu1 1School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China
2Collaborative Innovation Center of Geospatial Technology, Wuhan University, Wuhan, China
3School of Information engineering, Lingnan Normal University, Zhanjiang, China
Keywords: Taxi Trajectory, Spatiotemporal Clustering, Data Field, Hotspots Detection Abstract. City hotspots refer to the areas where residents visit frequently, and large traffic flow exist, which reflect the people travel patterns and distribution of urban function area. Taxi trajectory data contain abundant information about urban functions and citizen activities, and extracting interesting city hotspots from them can be of importance in urban planning, traffic command, public travel services etc. To detect city hotspots and discover a variety of changing patterns among them, we introduce a data field-based cluster analysis technique to the pick-up and drop-off points of taxi trajectory data and improve the method by introducing the time weight, which has been normalized to estimate the potential value in data field. Thus, in the light of the new potential function in data field, short distance and short time difference play a powerful role. So the region full of trajectory points, which is regarded as hotspots area, has a higher potential value, while the region with thin trajectory points has a lower potential value. The taxi trajectory data of Wuhan city in China on May 1, 6 and 9, 2015, are taken as the experimental data. From the result, we find the sustaining hotspots area and inconstant hotspots area in Wuhan city based on the spatiotemporal data field method. Further study will focus on optimizing parameter and the interaction among hotspots area.
Conference paper (PDF, 2648 KB)


Citation: Qin, K., Zhou, Q., Wu, T., and Xu, Y. Q.: HOTSPOTS DETECTION FROM TRAJECTORY DATA BASED ON SPATIOTEMPORAL DATA FIELD CLUSTERING, Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-2/W7, 1319-1325, https://doi.org/10.5194/isprs-archives-XLII-2-W7-1319-2017, 2017.

BibTeX EndNote Reference Manager XML