Unmanned farms employ a variety of sensors, automated systems, and data analysis techniques to enable fully automated and intelligent management. This not only heightens agricultural production efficiency but also reduces the costs associated with human resources. As integral components of unmanned farms’ automation systems, agricultural UAVs have been widely adopted across various operational stages due to their precision, high efficiency, environmental sustainability, and simplicity of operation. However, present-day technological advancement levels and relevant policy regulations pose significant restrictions on UAVs in terms of payload and endurance, leading to diminished task efficiency when a single UAV is deployed over large areas. Accordingly, this paper aggregates and analyzes research pertaining to UAV swarms from databases such as Google Scholar, ScienceDirect, Scopus, IEEE Xplorer, and Wiley over the past decade. An initial overview presents the current control methods for UAV swarms, incorporating a summary and analysis of the features, merits, and drawbacks of diverse control techniques. Subsequently, drawing from the four main stages of agricultural production (cultivation, planting, management, and harvesting), we evaluate the application of UAV swarms in each stage and provide an overview of the most advanced UAV swarm technologies utilized therein. Finally, we scrutinize and analyze the challenges and concerns associated with UAV swarm applications on unmanned farms and provide forward-looking insights into the future developmental trajectory of UAV swarm technology in unmanned farming, with the objective of bolstering swarm performance, scalability, and adoption rates in such settings.

Underwater images suffer from color casts, low illumination, and blurred details caused by light absorption and scattering in water. Existing data-driven methods often overlook the scene characteristics of underwater imaging, limiting their expressive power. To address the above issues, we propose a Multiscale Disentanglement Network (MD-Net) for Underwater Image Enhancement (UIE), which mainly consists of scene radiance disentanglement (SRD) and transmission map disentanglement (TMD) modules. Specifically, MD-Net first disentangles original images into three physical parameters which are scene radiance (clear image), transmission map, and global background light. The proposed network then reconstructs these physical parameters into underwater images. Furthermore, MD-Net introduces class adversarial learning between the original and reconstructed images to supervise the disentanglement accuracy of the network. Moreover, we design a multi-level fusion module (MFM) and dual-layer weight estimation unit (DWEU) for color cast adjustment and visibility enhancement. Finally, we conduct extensive qualitative and quantitative experiments on three benchmark datasets, which demonstrate that our approach outperforms other traditional and state-of-the-art methods. Our code and results are available at: https://github.com/WYJGR/MD-Net.

The safety of autonomous driving is closely linked to accurate depth perception. With the continuous development of autonomous driving, depth completion has become one of the crucial methods in this field. However, current depth completion methods have major shortcomings in small objects. To solve this problem, this paper proposes an end-to-end architecture with adaptive spatial feature fusion by encoder–decoder (ASFF-ED) module for depth completion. The architecture is built on the basis of the network architecture proposed in this paper, and is able to extract depth information adaptively with different weights on the specified feature map, which effectively solves the problem of insufficient depth accuracy of small objects. At the same time, this paper also proposes a depth map visualization method with a semi-quantitative visualization, which makes the depth information more intuitive to display. Compared with the currently available depth map visualization methods, this method has stronger quantitative analysis and horizontal comparison ability. Through experiments of ablation study and comparison, the results show that the method proposed in this paper exhibits a lower root-mean-squared error (RMSE) and better small object detection performance on the KITTI dataset.