Purpose

The purpose of this paper is to use the most popular deep learning algorithm to complete the vehicle detection in the urban area of MiniSAR image, and provide reliable means for ground monitoring.

Design/methodology/approach

An accurate detector called the rotation region-based convolution neural networks (CNN) with multilayer fusion and multidimensional attention (M2R-Net) is proposed in this paper. Specifically, M2R-Net adopts the multilayer feature fusion strategy to extract feature maps with more extensive information. Next, the authors implement the multidimensional attention network to highlight target areas. Furthermore, a novel balanced sampling strategy for hard and easy positive-negative samples and a global balanced loss function are applied to deal with spatial imbalance and objective imbalance. Finally, rotation anchors are used to predict and calibrate the minimum circumscribed rectangle of vehicles.

Findings

By analyzing many groups of experiments, the validity and universality of the proposed model are verified. More importantly, comparisons with SSD, LRTDet, RFCN, DFPN, CMF-RCNN, R3Det, SCRDet demonstrate that M2R-Net has state-of-the-art detection performance.

Research limitations/implications

The progress in the field of MiniSAR application has been slow due to strong speckle noise, phase error, complex environments and a low signal-to-noise ratio. In addition, four kinds of imbalances, i.e. spatial imbalance, scale imbalance, class imbalance and objective imbalance, in object detection based on the CNN greatly inhibit the optimization of detection performance.

Originality/value

This research can not only enrich the means of daily traffic monitoring but also be used for enemy intelligence reconnaissance in wartime.

中文翻译：

---

M2R-Net：用于 MiniSAR 图像中任意定向车辆检测的深度网络

目的

本文的目的是利用最流行的深度学习算法完成MiniSAR图像的市区车辆检测，为地面监测提供可靠的手段。

设计/方法/方法

本文提出了一种精确的检测器，称为基于旋转区域的卷积神经网络（CNN），具有多层融合和多维注意力（M2R-Net）。具体来说，M2R-Net 采用多层特征融合策略来提取具有更广泛信息的特征图。接下来，作者实现了多维注意力网络来突出目标区域。此外，一种针对难易正负样本的新颖平衡采样策略和全局平衡损失函数被应用于处理空间不平衡和客观不平衡。最后，使用旋转锚来预测和校准车辆的最小外接矩形。

发现

通过对多组实验的分析，验证了所提出模型的有效性和通用性。更重要的是，与 SSD、LRTDet、RFCN、DFPN、CMF-RCNN、R3Det、SCRDet 的比较表明 M2R-Net 具有最先进的检测性能。

研究限制/影响

由于散斑噪声强、相位误差大、环境复杂、信噪比低，MiniSAR应用领域进展缓慢。此外，基于CNN的目标检测存在四种不平衡，即空间不平衡、尺度不平衡、类别不平衡和目标不平衡，极大地抑制了检测性能的优化。

原创性/价值

该研究不仅可以丰富日常交通监控手段，还可以用于战时敌方情报侦察。