An Abnormal Crowd Behavior Detection Algorithm Based on Fluid Mechanics

2014 ◽  
Vol 9 (5) ◽  
Author(s):  
Xiaofei Wang ◽  
Mingliang Gao ◽  
Xiaohai He ◽  
Xiaohong Wu ◽  
Yun Li
Author(s):  
Wilbert G. Aguilar ◽  
Marco A. Luna ◽  
Hugo Ruiz ◽  
Julio F. Moya ◽  
Marco P. Luna ◽  
...  

2014 ◽  
Vol 619 ◽  
pp. 327-331 ◽  
Author(s):  
Nuksit Noomwongs ◽  
Raksit Thitipatanapong ◽  
Sunhapos Chantranuwathana ◽  
Sanya Klongnaivai

Driver behavior is the key to safe mobility. In general, vehicle maneuvers can be determined from acceleration of the vehicle. Physically, the acceleration and brake can be detected with longitudinal acceleration while turning and lane change can be detected with lateral acceleration. Nowadays, navigation system technologies have been much improved both on availability and accuracy with combination of multiple navigation satellite systems. Normally, it’s called Multi-GNSS (multiple global navigation satellite system). With decimeter precision and the update rate scale up to 10-Hz, the GNSS could be an alternative solution for driver behavior detection. In this paper, advance Multi-GNSS with precise point position (PPP) technique was presented with a simple maneuver detection algorithm. The advantage of PPP over conventional navigation is decimeter accuracy without direct connection to any reference base station. The experimental Multi-GNSS receiver was JAVAD Delta G3T that installed on a utility vehicle. This high performance multi-GNSS navigation system was investigated with the driving behavior detection algorithm. The precise point positioning (PPP) technique in combination with multiple satellite navigation system (GPS+GLONASS+GALOLEO+QZSS) were applied in this study. The PPP technique improved the output of detection algorithm in acceleration limit from 260% error in conventional navigation system (GPS) to 20% of incidents with PPP.


Sign in / Sign up

Export Citation Format

Share Document