National Key Laboratory of Science and Technology on ATR, National University of Defense Technology, Changsha 410073, China.
Sensors (Basel). 2020 Mar 30;20(7):1922. doi: 10.3390/s20071922.
With an infrared circumferential scanning system (IRCSS), we can realize long-time surveillance over a large field of view. Recognizing targets in the field of view automatically is a crucial component of improving environmental awareness under the trend of informatization, especially in the defense system. Target recognition consists of two subtasks: detection and identification, corresponding to the position and category of the target, respectively. In this study, we propose a deep convolutional neural network (DCNN)-based method to realize the end-to-end target recognition in the IRCSS. Existing DCNN-based methods require a large annotated dataset for training, while public infrared datasets are mostly used for target tracking. Therefore, we build an infrared target recognition dataset to both overcome the shortage of data and enhance the adaptability of the algorithm in various scenes. We then use data augmentation and exploit the optimal cross-domain transfer learning strategy for network training. In this process, we design the smoother L1 as the loss function in bounding box regression for better localization performance. In the experiments, the proposed method achieved 82.7 mAP, accomplishing the end-to-end infrared target recognition with high effectiveness on accuracy.
利用红外周视扫描系统 (IRCSS)，我们可以实现对大视场的长时间监控。在信息化趋势下，自动识别视场中的目标是提高环境意识的关键组成部分，特别是在防御系统中。目标识别包括两个子任务：检测和识别，分别对应于目标的位置和类别。在这项研究中，我们提出了一种基于深度卷积神经网络 (DCNN) 的方法，以实现 IRCSS 中的端到端目标识别。现有的基于 DCNN 的方法需要大量的标注数据集进行训练，而公共红外数据集主要用于目标跟踪。因此，我们构建了一个红外目标识别数据集，以克服数据不足的问题，并增强算法在各种场景下的适应性。然后，我们使用数据增强和利用最优的跨域迁移学习策略进行网络训练。在这个过程中，我们设计了平滑 L1 作为边界框回归中的损失函数，以获得更好的定位性能。在实验中，所提出的方法在 mAP 方面达到了 82.7%，实现了高效的端到端红外目标识别，准确率高。
