This paper introduces an effective approach for detecting road traffic congestion. This approach uses a hybrid observer (HO) that exploits both the flexibility and simplicity of the piecewise switched linear model to estimate the traffic density parameter and employs a generalized likelihood ratio (GLR) test to detect traffic congestion. We evaluated the HO-GLR with real data from a segment of the four-lane State Route 60 (SR-60) highway in southern California. Results show that the HO-GLR approach is suitable for traffic congestion monitoring.
|Original language||English (US)|
|Title of host publication||2018 Annual American Control Conference (ACC)|
|Publisher||Institute of Electrical and Electronics Engineers (IEEE)|
|Number of pages||6|
|State||Published - Aug 17 2018|