A video acquisition method and system for airport flight guarantee time nodes

Abstract

The invention discloses a video acquisition method and system for airport flight guarantee time nodes. According to the first image obtained by the first camera installed on the top of the corridor bridge, the first confidence degree is obtained by analyzing the first neural network model, and then according to The second image captured by the second camera installed inside the corridor bridge is analyzed by the second neural network model to obtain the second confidence degree, and the composite confidence degree is obtained by combining the first confidence degree and the second confidence degree, and the composite confidence degree is determined The reliability of the corresponding flight guarantee status, so as to update the corresponding flight guarantee status, and report the time node of flight guarantee if the status changes. Through the first camera and the second camera to jointly verify whether the aircraft is in the parking position and whether the aircraft is close to the corridor bridge, the accuracy of the four key nodes is ensured, thereby effectively improving video collection under various weather conditions and at various time periods the accuracy rate.

Description

technical field [0001] The invention relates to the technical field of flight ground service support, in particular to a video collection method and system for airport flight support time nodes. Background technique [0002] Airport flight ground service guarantee is an important intelligent work of airport management. The airport flight support process includes multiple support nodes, such as aircraft entry, wheel chocking, refueling start, refueling end, catering start, meal catering end, wheel chock removal, aircraft launch, etc. These support nodes are based on whether the aircraft is It is judged on the basis of the two states of the parking position and whether it is close to the corridor bridge. For the automatic collection of airport flight support nodes, cameras can be installed to shoot aircraft and support vehicles, and flight node collection can be realized through computer vision technologies such as video analysis and image deep learning. Usually, the two sta...

AI Technical Summary

Problems solved by technology

Usually, the two states of whether the aircraft is at the parking position and whether it is close to the corridor bridge are obtained through the camera on the top of the corridor bridge and obtained through computer vision technology. The camera may appear blurred, which may cause errors in the recognition of the above two states, which will further affect the smooth development of the entire flight support process.

Images