Abstract | ||
---|---|---|
This paper proposes a novel traffic event classification approach using event severities at intersections. The proposed system basically learns normal and common traffic flow by clustering vehicle trajectories. Common vehicle routes are generated by implementing trajectory clustering with Continuous Hidden Markov Model. Vehicle abnormality is detected by observing maximum likelihoods of partial vehicle locations and velocities on underlying common route models. The second part of the work is based on extracting the severities of abnormality by deviation measurement using Coefficient of Variances method. By using abnormal event samples, two severity classes are built in order to recognize event severities by Support Vector Machines and k-Nearest Neighborhood algorithms. Experimental results show that the proposed model has high precision with satisfactory incident detection and event severity classification performance. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1007/s00138-011-0390-4 | machine vision applications |
Keywords | Field | DocType |
Traffic video scene analysis,Accident detection and classification,Event categorization,Markov models,Pattern recognition | Data mining,Traffic flow,Pattern recognition,Markov model,Computer science,Support vector machine,Abnormality,Trajectory clustering,Artificial intelligence,Hidden Markov model,Cluster analysis | Journal |
Volume | Issue | ISSN |
25 | 3 | 0932-8092 |
Citations | PageRank | References |
12 | 0.51 | 23 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ömer Aköz | 1 | 18 | 2.04 |
M. Elif Karsligil | 2 | 73 | 13.69 |