Aircraft detection and tracking method based on multi-scale self-adaption and side domain attention

Abstract

The invention discloses an aircraft detection and tracking method based on multi-scale self-adaption and side domain attention, and the method comprises the steps: extracting an original feature map of a preprocessed original aircraft image through constructing a basic feature extraction network, and extracting a small-target feature map in the original feature map through combining with a small-size target branch network model; and obtaining a detection target feature map set and feature vectors corresponding to the detection target feature maps according to the small target feature maps by using a target prediction model, and performing aircraft detection and tracking by using a multi-aircraft tracking algorithm. Fusion transmission of shallow texture features and deeper semantic features of the feature map is optimized by using a coding and decoding structure and residual connection, the inference speed is improved, information fusion is more sufficient, and the feature extraction capability of a network model is effectively improved by combining a side domain attention mechanism network; and the small-size target branch network model is utilized to reduce the information loss degree, the small-size target detection accuracy is effectively optimized, and the management efficiency of airport scene aircrafts is improved.

Description

technical field [0001] The invention relates to the field of multi-target tracking, in particular to an aircraft detection and tracking method based on multi-scale self-adaptation and boundary attention. Background technique [0002] With the development of my country's economy, the volume of aviation business continues to grow, and the total amount of air transportation continues to increase. More and more people choose aviation tools as their preferred travel tools, which leads to the density of aircraft on the airport scene. significantly increased. At the same time, the rapid development of air passenger and cargo flow in the airport also puts forward higher requirements for the airport scene monitoring system. The airport scene monitoring system is a management system for aircraft, vehicles and staff in the airport scene. Its main functions include real-time detection and tracking of aircraft, and timely early warning; through real-time collection and analysis of aircra...

AI Technical Summary

Problems solved by technology

The multi-target tracking algorithm based on deep learning has the advantages of strong feature extraction ability, high tracking accuracy, and easy model training. However, due to the huge amount of model parameters and high requirements for equipment computing power, it is often difficult to achieve real-time results.

Images