Convolutional Neural Network for Ellipse Extended Target Tracking

Abstract

In the field of extended target tracking and information fusion, constrained by the sparse measurement set from radar, the target contour is commonly estimated as an elliptical shape. This paper uses convolutional neural networks to estimate the size and orientation information of extended targets. First, by establishing a systematic model for elliptical extended targets and modeling its measurement information, data normalization, and length equalization operations were conducted to provide reliable measurement data for subsequent neural network processing. Subsequently, through the construction of a convolutional neural network model, accurate estimation of the contour parameters of elliptical extended targets was achieved, and integration with Kalman filtering enabled precise tracking of the target positions. Finally, the effectiveness of the proposed method was verified through the construction of simulation scenarios, and the performance of the method was comprehensively evaluated using the Gaussian Wasserstein distance.