School of Information and Automation Engineering, Qilu University of Technology (Shandong Academy of Sciences), Jinan, 250353, Shandong Province, China.
School of Surveying and Geo-Informatics, Shandong Jianzhu University, Jinan, 250101, Shandong Province, China.
Sci Rep. 2023 May 15;13(1):7817. doi: 10.1038/s41598-023-34892-4.
YOLOv5 is one of the most popular object detection algorithms, which is divided into multiple series according to the control of network depth and width. To realize the deployment of mobile devices or embedded devices, the paper proposes a lightweight aerial image object detection algorithm (LAI-YOLOv5s) based on the improvement of YOLOv5s with a relatively small amount of calculation and parameter and relatively fast reasoning speed. Firstly, to better detect small objects, the paper replaces the minimum detection head with the maximum detection head and proposes a new feature fusion method, DFM-CPFN(Deep Feature Map Cross Path Fusion Network), to enrich the semantic information of deep features. Secondly, the paper designs a new module based on VoVNet to improve the feature extraction ability of the backbone network. Finally, based on the idea of ShuffleNetV2, the paper makes the network more lightweight without affecting detection accuracy. Based on the VisDrone2019 dataset, the detection accuracy of LAI-YOLOv5s on the mAP@0.5 index is 8.3% higher than that of the original algorithm. Compared with other series of YOLOv5 and YOLOv3 algorithms, LAI-YOLOv5s has the advantages of low computational cost and high detection accuracy.
YOLOv5 是最受欢迎的目标检测算法之一，根据网络深度和宽度的控制分为多个系列。为了实现移动设备或嵌入式设备的部署，本文提出了一种基于 YOLOv5s 改进的轻量级航空图像目标检测算法（LAI-YOLOv5s），该算法计算量和参数相对较小，推理速度相对较快。首先，为了更好地检测小目标，本文用最大检测头替换最小检测头，并提出了一种新的特征融合方法 DFM-CPFN（Deep Feature Map Cross Path Fusion Network），以丰富深层特征的语义信息。其次，本文基于 VoVNet 设计了一个新的模块，以提高骨干网络的特征提取能力。最后，基于 ShuffleNetV2 的思想，本文使网络更加轻量化，而不影响检测精度。在 VisDrone2019 数据集上，LAI-YOLOv5s 在 mAP@0.5 指标上的检测精度比原始算法提高了 8.3%。与其他系列的 YOLOv5 和 YOLOv3 算法相比，LAI-YOLOv5s 具有计算成本低、检测精度高的优点。
