Affiliation:
1. School of Electrical and Information Engineering, Changsha University of Science and Technology, Changsha 410205, China
Abstract
In aircraft feature detection, the difficulty of acquiring Synthetic Aperture Radar (SAR) images leads to the scarcity of some types of aircraft samples, and the high privacy makes the personal sample set have the characteristics of data silos. Existing data enhancement methods can alleviate the problem of data scarcity through feature reuse, but they are still powerless for data that are not involved in local training. To solve this problem, a new federated learning framework was proposed to solve the problem of data scarcity and data silos through multi-client joint training and model aggregation. The commonly used federal average algorithm is not effective for aircraft detection with unbalanced samples, so a federal distribution average deviation (FedDAD) algorithm, which is more suitable for aircraft detection in SAR images, was designed. Based on label distribution and client model quality, the contribution ratio of each client parameter is adaptively adjusted to optimize the global model. Client models trained through federated cooperation have an advantage in detecting aircraft with unknown scenarios or attitudes while remaining sensitive to local datasets. Based on the YOLOv5s algorithm, the feasibility of federated learning was verified on SAR image aircraft detection datasets and the portability of the FedDAD algorithm on public datasets. In tests based on the YOLOv5s algorithm, FedDAD outperformed FedAvg’s mAP0.5–0.95 on the total test set of two SAR image aircraft detection and far outperformed the local centralized training model.
Funder
National Natural Science Foundation of China
Research Foundation of Education Bureau of Hunan Province, China
Postgraduate Scientific Research Innovation Project of Hunan Province, China
Subject
General Earth and Planetary Sciences
Reference52 articles.
1. A tutorial on synthetic aperture radar;Moreira;IEEE Geosci. Remote Sens. Mag.,2013
2. Employing deep learning for automatic river bridge detection from SAR images based on adaptively effective feature fusion;Chen;Int. J. Appl. Earth Obs. Geoinf.,2021
3. Zeng, K., and Wang, Y. (2020). A deep convolutional neural network for oil spill detection from spaceborne SAR images. Remote Sens., 12.
4. Luti, T., De Fioravante, P., Marinosci, I., Strollo, A., Riitano, N., Falanga, V., Mariani, L., Congedo, L., and Munafò, M. (2021). Land consumption monitoring with SAR data and multispectral indices. Remote Sens., 13.
5. Shu, Y., Li, W., Yang, M., Cheng, P., and Han, S. (2021). Patch-based change detection method for SAR images with label updating strategy. Remote Sens., 13.
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献