A Robust Vision-based Method for Real-time Flight Parking Bays Monitoring

The arrival and departure time sampling of the flight is one of the key information for parking bays monitoring to avoid conflict. Nowadays the time is reported and recorded by hand in many airports, which fault and delay reports may happen. Safety risks and lower efficiency cannot be neglected. This paper presents a robust vision-based method to automatically sample the arrival and departure time on the bays by flight move tracking and keep the flight under intelligent surveillance with the camera in the ramp. Based on the Gaussian Mixture Model algorithm, the improved method provided successfully solves the light changing disturbance and other moving object influence with Optical Flow Methods, which has been applied in the eighty seven bays of Shanghai Hongqiao International Airport that is one of the major airports in China. The practical result shows that the accuracy rate is above 90% and the missed alarm rate below 1%.