Drones Latest open access articles published in Drones at https://www.mdpi.com/journal/drones
- Drones, Vol. 8, Pages 84: PVswin-YOLOv8s: UAV-Based Pedestrian and Vehicle Detection for Traffic Management in Smart Cities Using Improved YOLOv8por Noor Ul Ain Tahir el febrero 28, 2024 a las 12:00 am
In smart cities, effective traffic congestion management hinges on adept pedestrian and vehicle detection. Unmanned Aerial Vehicles (UAVs) offer a solution with mobility, cost-effectiveness, and a wide field of view, and yet, optimizing recognition models is crucial to surmounting challenges posed by small and occluded objects. To address these issues, we utilize the YOLOv8s model and a Swin Transformer block and introduce the PVswin-YOLOv8s model for pedestrian and vehicle detection based on UAVs. Firstly, the backbone network of YOLOv8s incorporates the Swin Transformer model for global feature extraction for small object detection. Secondly, to address the challenge of missed detections, we opt to integrate the CBAM into the neck of the YOLOv8. Both the channel and the spatial attention modules are used in this addition because of how well they extract feature information flow across the network. Finally, we employ Soft-NMS to improve the accuracy of pedestrian and vehicle detection in occlusion situations. Soft-NMS increases performance and manages overlapped boundary boxes well. The proposed network reduced the fraction of small objects overlooked and enhanced model detection performance. Performance comparisons with different YOLO versions ( for example YOLOv3 extremely small, YOLOv5, YOLOv6, and YOLOv7), YOLOv8 variants (YOLOv8n, YOLOv8s, YOLOv8m, and YOLOv8l), and classical object detectors (Faster-RCNN, Cascade R-CNN, RetinaNet, and CenterNet) were used to validate the superiority of the proposed PVswin-YOLOv8s model. The efficiency of the PVswin-YOLOv8s model was confirmed by the experimental findings, which showed a 4.8% increase in average detection accuracy (mAP) compared to YOLOv8s on the VisDrone2019 dataset.
- Drones, Vol. 8, Pages 83: Multiple-Target Matching Algorithm for SAR and Visible Light Image Data Captured by Multiple Unmanned Aerial Vehiclespor Hang Zhang el febrero 27, 2024 a las 12:00 am
Unmanned aerial vehicle (UAV) technology has witnessed widespread utilization in target surveillance activities. However, cooperative multiple UAVs for the identification of multiple targets poses a significant challenge due to the susceptibility of individual UAVs to false positive (FP) and false negative (FN) target detections. Specifically, the primary challenge addressed in this study stems from the weak discriminability of features in Synthetic Aperture Radar (SAR) imaging targets, leading to a high false alarm rate in SAR target detection. Additionally, the uncontrollable false alarm rate during electro-optical proximity detection results in an elevated false alarm rate as well. Consequently, a cumulative error propagation problem arises when SAR and electro-optical observations of the same target from different perspectives occur at different times. This paper delves into the target association problem within the realm of collaborative detection involving multiple unmanned aerial vehicles. We first propose an improved triplet loss function to effectively assess the similarity of targets detected by multiple UAVs, mitigating false positives and negatives. Then, a consistent discrimination algorithm is described for targets in multi-perspective scenarios using distributed computing. We established a multi-UAV multi-target detection database to alleviate training and validation issues for algorithms in this complex scenario. Our proposed method demonstrates a superior correlation performance compared to state-of-the-art networks.
- Drones, Vol. 8, Pages 81: Exploring the Potential of Remote Sensing to Facilitate Integrated Weed Management in Smallholder Farms: A Scoping Reviewpor Shaeden Gokool el febrero 26, 2024 a las 12:00 am
In light of a growing population and climate change compounding existing pressures on the agri-food system, there is a growing need to diversify agri-food systems and optimize the productivity and diversity of smallholder farming systems to enhance food and nutrition security under climate change. In this context, improving weed management takes on added significance, since weeds are among the primary factors contributing to crop yield losses for smallholder farmers. Adopting remote-sensing-based approaches to facilitate precision agricultural applications such as integrated weed management (IWM) has emerged as a potentially more effective alternative to conventional weed control approaches. However, given their unique socio-economic circumstances, there remains limited knowledge and understanding of how these technological advancements can be best utilized within smallholder farm settings. As such, this study used a systematic scoping review and attribute analysis to analyze 53 peer-reviewed articles from Scopus to gain further insight into remote-sensing-based IWM approaches and identify which are potentially best suited for smallholder farm applications. The findings of this review revealed that unmanned aerial vehicles (UAVs) are the most frequently utilized remote sensing platform for IWM applications and are also well suited for mapping and monitoring weeds within spatially heterogeneous areas such as smallholder farms. Despite the potential of these technologies for IWM, several obstacles to their operationalization within smallholder farm settings must be overcome, and careful consideration must be given on how best to maximize their potential before investing in these technologies.
- Drones, Vol. 8, Pages 80: State-of-Charge Trajectory Planning for Low-Altitude Solar-Powered Convertible UAV by Driven Modespor Xiao Cao el febrero 26, 2024 a las 12:00 am
The conversion efficiency of solar energy and the capacity of energy storage batteries limit the development of low-altitude solar-powered aircrafts in the face of challenging meteorological phenomena in the lower atmosphere. In this paper, the energy planning problem of solar-power convertible unmanned aerial vehicles (SCUAVs) is studied, and a degressive state-of-charge (SOC) trajectory planning method with energy management strategy (EMS) is proposed. The SOC trajectory planning strategy is divided into four stages driven by three modes, which achieves the energy cycle of SCUAV’s long-endurance cruise and multiple hovers without the need to fully charge the battery SOC. The EMS is applied to control the output of solar cell/battery and power distribution for each stage according to three modes. A prediction model based on wavelet transform (WT), long short-term memory (LSTM) networks and autoregressive integrated moving average (ARIMA) is proposed for the weather forecast in the low altitude, where solar irradiance is used for the prediction of solar input power, and the wind and its inflow direction take into account the multi-mode power prediction. Numerical and simulation results indicate that the effectiveness of the proposed SOC trajectory planning method has a positive impact on low-altitude solar-powered aircrafts.
- Drones, Vol. 8, Pages 82: Joint Incentive Mechanism Design and Energy-Efficient Resource Allocation for Federated Learning in UAV-Assisted Internet of Vehiclespor Shangjing Lin el febrero 26, 2024 a las 12:00 am
With the increasing demand for application development of task publishers (e.g., automobile enterprises) in the Internet of Vehicles (IoV), federated learning (FL) can be used to enable vehicle users (VUs) to conduct local application training without disclosing data. However, the challenges of VUs’ intermittent connectivity, low proactivity, and limited resources are inevitable issues in the process of FL. In this paper, we propose a UAV-assisted FL framework in the context of the IoV. An incentive stage and a training stage are involved in this framework. UAVs serve as central servers, which assist to incentivize VUs, manage VUs’ contributed resources, and provide model aggregation, making sure communication efficiency and mobility enhancement in FL. The numerical results show that, compared with the baseline algorithms, the proposed algorithm reduces energy consumption by 50.3% and improves model convergence speed by 30.6%.