In order to study secure federated learning for resource-constrained devices such as drones to protect user privacy and data security in drone networks, a blockchain-based secure federated learning scheme for drones is proposed. Currently, researchers focus on transferring models for federated learning after local training using drones, but in reality, drones will be limited in accomplishing local training due to their own resource and arithmetic issues. In this paper, the scheme offloads the training task of the UAV to the local server, and the UAV is only responsible for performing model aggregation and delivery. At the same time, a new consensus algorithm PoE (Proof-of-Energy) is proposed to model the energy and evaluate the arithmetic power of drones, which assigns roles to each drone node within the blockchain network and ensures that the drones effectively participate in the federated learning process. Due to the open and transparent nature of the blockchain, ring signatures are used to replace the traditional signatures in order to protect the private information such as the behavior and identity of each node and the content of block transactions. The experimental results show that the proposed model can ensure that UAVs effectively participate in federated learning. In addition, when there is a poisoning sample to disrupt the training process, the accuracy of the global model can be effectively ensured compared to the traditional scheme.
Image shadow removal is an essential image preprocessing task. In practical production environments, effective image shadow removal methods can significantly enhance the performance of subsequent image-based tasks. However, current methods for image shadow removal still encounter issues such as artifacts, color deviations, and blurriness due to factors including the capturing environment and algorithmic efficiency. This paper proposes an image shadow removal method using spatial attention, integrating physical and deep learning models. By incorporating multi-scale feature learning and preserving spatial details, the approach integrates shadow spatial attention modules, perceptual loss, and edge loss to improve the shadow removal effect. Experimental results demonstrate that the proposed method achieves a PSNR value of 36.14dB and an SSIM exceeding 98% in the ISTD dataset, with the RMSE reduced to 6.54. These outcomes affirm the efficiency and superiority of the proposed method in addressing the challenges of image shadow removal tasks.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.