A Feature Extraction Method for Moving Targets on the Airport Surface

Abstract

Due to the increase in aircraft movement of the airport surface and other human reasons, runway incursion is a major hazard affecting air safety. An efficient feature extraction method for target detection is important to guarantee the safety of the airport scene in runway incursion prevention systems. Anisotropic magneto resistance used as target detection equipment of airport is proposed in this paper, and a combination of time and frequency domain feature extraction algorithm is also put forward. Firstly, the magnetic signals caused by surface moving target are sensed by sensors placed at the centerline of the runway, which are used to calculate the length of the target. After regularizing time domain signal, peak features can be extracted based on the target length. Secondly, the regularized signal is decomposed using DB wavelet. The obtained wavelet coefficients with the energies of normalizing approximate signal and every layer signal are realized as frequency domain feature of the signal. The similarities of different targets are restricted below 0.79, which is calculated by the method of target features differentiation measurement. It is demonstrated that signal features provided by the proposed method are more recognizable than the ones provided by time domain or frequency domain feature method individually.