Aircraft tracking method in complex airport apron area based on double twin networks

Abstract

The invention discloses an aircraft tracking method in a complex airport apron area based on double twin networks. The method comprises the following steps: tracking a target aircraft based on a first camera: inputting a target airport apron area image obtained based on the first camera into a first twin network, obtaining a first positive and negative sample confidence coefficient based on an obtained first output result, and obtaining a first tracking frame based on an obtained second output result; tracking the target aircraft based on a second camera: inputting a target airport apron area image obtained based on the second camera into a second twin network, obtaining a second positive and negative sample confidence coefficient based on an obtained third output result, and obtaining a second tracking frame based on an obtained fourth output result, wherein, the first camera and the second camera are located at different positions; and executing a corresponding tracking processing strategy based on the first positive and negative sample confidence coefficient and the second positive and negative sample confidence coefficient. According to the invention, stable tracking of the target aircraft in the complex airport apron area can be realized.

Description

technical field [0001] The invention belongs to the field of target tracking, and more particularly, relates to a method for tracking an aircraft in a complex apron area based on a double twin network. Background technique [0002] In recent years, the target tracking technology in specific scenarios has achieved rapid development, from the traditional background difference algorithm, mixed Gaussian algorithm, TLD algorithm, KCF algorithm and CT algorithm to the emerging target tracking algorithm based on deep learning, which can be described as one after another. At present, for a certain usage scenario, selecting an appropriate target tracking algorithm can basically achieve stable target tracking. At the same time, the above target tracking algorithms all have open source versions, which can be directly used by users. [0003] However, it is difficult to achieve long-term stable tracking of aircraft in the apron area of ​​medium and large airports using the above target ...

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to solve the problem that the existing target tracking algorithm in a specific scene cannot stably track the target aircraft in the complex apron area

Images