School of Artificial Intelligence, Xidian University, Xi'an 710071, China.
School of Electronic Confrontation, National University of Defense, Hefei 230037, China.
Sensors (Basel). 2022 Nov 4;22(21):8482. doi: 10.3390/s22218482.
When tracking maneuvering targets, recurrent neural networks (RNNs), especially long short-term memory (LSTM) networks, are widely applied to sequentially capture the motion states of targets from observations. However, LSTMs can only extract features of trajectories stepwise; thus, their modeling of maneuvering motion lacks globality. Meanwhile, trajectory datasets are often generated within a large, but fixed distance range. Therefore, the uncertainty of the initial position of targets increases the complexity of network training, and the fixed distance range reduces the generalization of the network to trajectories outside the dataset. In this study, we propose a transformer-based network (TBN) that consists of an encoder part (transformer layers) and a decoder part (one-dimensional convolutional layers), to track maneuvering targets. Assisted by the attention mechanism of the transformer network, the TBN can capture the long short-term dependencies of target states from a global perspective. Moreover, we propose a center-max normalization to reduce the complexity of TBN training and improve its generalization. The experimental results show that our proposed methods outperform the LSTM-based tracking network.
在跟踪机动目标时，递归神经网络（RNN），特别是长短期记忆（LSTM）网络，被广泛应用于从观测中依次捕获目标的运动状态。然而，LSTM 只能逐步提取轨迹的特征；因此，它们对机动运动的建模缺乏全局性。同时，轨迹数据集通常是在一个较大但固定的距离范围内生成的。因此，目标初始位置的不确定性增加了网络训练的复杂性，而固定的距离范围降低了网络对数据集外轨迹的泛化能力。在这项研究中，我们提出了一种基于变压器的网络（TBN），它由编码器部分（变压器层）和解码器部分（一维卷积层）组成，用于跟踪机动目标。借助变压器网络的注意力机制，TBN 可以从全局角度捕获目标状态的长短期依赖关系。此外，我们提出了一种中心-最大归一化方法来降低 TBN 训练的复杂性并提高其泛化能力。实验结果表明，我们提出的方法优于基于 LSTM 的跟踪网络。
