STLP-OD: Spatial and Temporal Label Propagation for Traffic Outlier Detection
KAUST DepartmentComputer Science
Computer Science Program
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Permanent link to this recordhttp://hdl.handle.net/10754/655896
MetadataShow full item record
AbstractThis paper focuses on the detection of non-recurrent traffic anomaly caused by unexpected or transient incidents, such as traffic accidents, celebrations, and disasters. Comparing to existing approaches, it considers the spatial and temporal propagation of traffic anomalies from one road to other neighbor roads by proposing an STLP-OD framework. The experimental results on a real data set show that the proposed approach can improve the accuracy of traffic outlier detection baselines significantly.
CitationPu, J., Wang, Y., Liu, X., & Zhang, X. (2019). STLP-OD: Spatial and Temporal Label Propagation for Traffic Outlier Detection. IEEE Access, 7, 63036–63044. doi:10.1109/access.2019.2916853
SponsorsThis work was supported in part by the National Key Research and Development Program of China under Grant 2017YFB1002000, Science Technology and Innovation Commission of Shenzhen Municipality JCYJ20180307123659504, and the State Key Laboratory of Software Development Environment.