TY  - JOUR
PY  - 1983//
TI  - Point process models for freeway incident detection
JO  - Transportation and traffic theory
A1  - Hurdle, V.
A1  - Hauser, E.
A1  - Ahmed, S.
A1  - Cook, Angus
SP  - 20
EP  - 30
VL  - 8
IS  - 
N2  - A new approach to the problem of freeway incident detection is proposed, based on point process models of the form arima (0,1,3) that describe the dynamics of traffic occupancy observations. The approch utilizes real-time estimates of the variability in traffic occupancies as detection thresholds, thus eliminating the need for threshold calibration and lessening the problem of false-alarms. The performance of the proposed detection algorithms is evaluated in terms of detection rate, false-alarm rate, and average time-lag to detection, using a total of 1,692 minutes of occupancy observations recorded during 50 representative traffic incidents.<p /> 
LA  - en
SN  - 
UR  - http://dx.doi.org/
ID  - ref1
ER  -