In this paper, based on a bidirectional parallel multi-branch feature pyramid network (BPMFPN), a novel one-stage object detector called BPMFPN Det is proposed for real-time detection of ground multi-scale targets by swarm unmanned aerial vehicles (UAVs). First, the bidirectional parallel multi-branch convolution modules are used to construct the feature pyramid to enhance the feature expression abilities of different scale feature layers. Next, the feature pyramid is integrated into the single-stage object detection framework to ensure real-time performance. In order to validate the effectiveness of the proposed algorithm, experiments are conducted on four datasets. For the PASCAL VOC dataset, the proposed algorithm achieves the mean average precision (mAP) of 85.4 on the VOC 2007 test set. With regard to the detection in optical remote sensing (DIOR) dataset, the proposed algorithm achieves 73.9 mAP. For vehicle detection in aerial imagery (VEDAI) dataset, the detection accuracy of small land vehicle (slv) targets reaches 97.4 mAP. For unmanned aerial vehicle detection and tracking (UAVDT) dataset, the proposed BPMFPN Det achieves the mAP of 48.75. Compared with the previous state-of-the-art methods, the results obtained by the proposed algorithm are more competitive. The experimental results demonstrate that the proposed algorithm can effectively solve the problem of real-time detection of ground multi-scale targets in aerial images of swarm UAVs.

在本文中，基于双向并行多分支特征金字塔网络（BPMFPN），提出了一种名为 BPMFPN Det 的新型单级目标检测器，用于群无人机（UAV）对地面多尺度目标的实时检测。 . 首先，使用双向并行多分支卷积模块构建特征金字塔，以增强不同尺度特征层的特征表达能力。接下来，将特征金字塔集成到单阶段对象检测框架中以确保实时性能。为了验证所提出算法的有效性，在四个数据集上进行了实验。对于 PASCAL VOC 数据集，所提出的算法在 VOC 2007 测试集上实现了 85.4 的平均精度 (mAP)。对于光学遥感（DIOR）数据集中的检测，所提出的算法达到了 73.9 mAP。对于航拍图像 (VEDAI) 数据集中的车辆检测，小型陆地车辆 (slv) 目标的检测精度达到 97.4 mAP。对于无人机检测和跟踪 (UAVDT) 数据集，所提出的 BPMFPN Det 实现了 48.75 的 mAP。与之前最先进的方法相比，所提出的算法获得的结果更具竞争力。实验结果表明，该算法能够有效解决群无人机航拍图像中地面多尺度目标的实时检测问题。4 地图。对于无人机检测和跟踪 (UAVDT) 数据集，所提出的 BPMFPN Det 实现了 48.75 的 mAP。与之前最先进的方法相比，所提出的算法获得的结果更具竞争力。实验结果表明，该算法能够有效解决群无人机航拍图像中地面多尺度目标的实时检测问题。4 地图。对于无人机检测和跟踪 (UAVDT) 数据集，所提出的 BPMFPN Det 实现了 48.75 的 mAP。与以往最先进的方法相比，所提出的算法获得的结果更具竞争力。实验结果表明，该算法能够有效解决群无人机航拍图像中地面多尺度目标的实时检测问题。