Many sensor nodes have been widely deployed in the physical world to gather various environmental information, such as water quality, earthquake, and huge dam safety. Due to the limitation in the batter power, memory, and computational capacity, missing data can occur at arbitrary sensor nodes and time slots. In extreme situations, some sensors may lose readings at consecutive time slots. The successive missing data takes the side effects on the accuracy of real-time monitoring as well as the performance on the data analysis in the wireless sensor networks. Unfortunately, existing solutions to the missing data filling cannot well uncover the complex non-linear spatial and temporal relations. To address these problems, a DNN (Deep Neural Network) multi-view learning method (DNN-MVL) is proposed to fill the successive missing readings. DNN-MVL mainly considers five views: global spatial view, global temporal view, local spatial view, local temporal view, and semantic view. These five views are modeled with inverse distance of weight interpolation, bidirectional simple exponential smoothing, user-based collaborative filtering, mass diffusion-based collaborative filtering with the bipartite graph, and structural embedding, respectively. The results of the five views are aggregated to a final value in a multi-view learning algorithm with DNN model to obtain the final filling readings. Experiments on large-scale real dam deformation data demonstrate that DNN-MVL has a mean absolute error about 6.5%, and mean relative error 21.4%, and mean square error 8.17% for dam deformation data, outperforming all of the baseline methods.

To improve the detection accuracy for multiple small targets with Raster R-CNN model, we propose a Multitask Enhanced dam crack image detection method based on Faster R-CNN (ME-Faster R-CNN) to adapt the detection of dam cracks in different lighting environments and lengths. To solve the problem of insufficient samples of dam cracks, transfer learning methods are utilized to assist network training and data enhancement. In the ME-Faster R-CNN, ResNet-50 network is firstly adopted to extract features of original images and obtain the feature map. Then, the features map is input into multi-task enhanced RPN module to generate the candidate regions through adopting the appropriate size and dimension of anchor box. At last, the features map and candidate regions are processed to detect the dam cracks. Experimental results demonstrate that ME Faster R-CNN with transfer learning can obtain 82.52% average IoU and 80.08% average precision mAP, respectively. Compared with Faster R-CNN detection method with the same parameters, the average IoU and mAP can increase 1.06% and 1.56%, respectively.

As satellite imagery technology advances, remote sensing plays an increasingly prominent role in modern society. Nevertheless, the limitations of existing imaging sensors and complex atmospheric conditions constrain the quality of raw remote sensing data, posing challenges for interpretation and noise reduction. Super‐resolution technology focuses on enhancing low‐quality, low‐resolution remote sensing images. In this study, we introduce a method that utilizes a high‐order degradation model to generate low‐resolution remote sensing images. We employ a Generative Adversarial Network with a Convolutional Block Attention Module (CBAM‐GAN) to enhance these images, reducing noise interference and improving texture and feature display. Our approach outperforms other methods on the UCMerced‐LandUse, WHU‐RS19, and AID datasets. Specifically, it raises SSIM index scores to 0.9443, 0.8928, and 0.8633, respectively, exceeding baselines by 1.31%, 0.19%, and 1.30%. The MOS index also improves to 3.98, 3.96, and 3.83, respectively, representing a 2.31%, 8.20%, and 2.96% gain over the baseline. Our reconstruction produces superior results, demonstrating the effectiveness of our proposed method.

Accurately identifying and locating water-crossing objects is of utmost importance for environmental protection. However, traditional detection algorithms often exhibit poor anti-interference performance and low detection accuracy in complex environments. To address these issues, this paper proposes a YOLOW algorithm based on a one-stage object detection algorithm for the automatic identification of water objects. The proposed algorithm incorporates two new modules, namely the SPDCS module and the SPPAUG module, to improve the model’s performance. Specifically, the SPDCS module retains all information in the channel dimension, thereby enhancing the model’s detection accuracy and recognition ability for water-crossing objects. The SPPAUG module performs multiscale feature fusion, which further improves the model’s detection accuracy and recognition ability. Moreover, the C2f module is introduced from YOLOv8 to increase the detection speed. Experimental results on a water-floating object dataset demonstrate that the improved YOLOW model outperforms the standard YOLOv5s algorithm, especially in water-crossing object detection. This research has significant implications for environmental monitoring and protection.

Salient object detection (SOD), one of the most important applications in the field of computer vision, aims to extract the most visually appealing regions of scenes. However, the improvement of the accuracy of existing salient object detection in optical remote sensing images (ORSI‐SOD) is usually accompanied by an increase of network complexity, which affects the application of these models. Motivated by this, a novel lightweight edge‐supervised neural network for ORSI‐SOD is proposed, named CSFFNet. Specifically, the backbone (ResNet34) is first lightened by feature encoding module (FEM), building a lightweight subnet for feature extraction. Then, in the transformer‐based feature pyramid enhancement module (FPEM), the convolutional features obtained in the FEM are enhanced by long‐distance dependence to obtain multi‐scale features containing rich saliency cues. Based on this, the feature fusion module (FFM) is designed to capture cross‐scale long‐range dependencies and effectively fuse high‐level semantic information with low‐level detail information. Thus, the increase in network complexity due to multi‐level decoding is avoided. Finally, the segmentation results are optimized by using salient edges as auxiliary information, which effectively improves the contrast and completeness of the results. Experimental results on two public datasets demonstrate that the lightweight CSFFNet achieves competitive or even better performance compared with state‐of‐the‐art methods.

To solve the target search problems for unmanned aerial vehicle (UAV) swarm in uncertain environments without prior knowledge, this paper designed a communication-constrained coverage search model and a new optimization algorithm. We proposed a multi-objective optimization model based on grid environment modeling and UAVs modeling with communication constraints. Meanwhile, to optimize the proposed model, this paper designed a collaborative search scheme based on model predictive control and communication constraints (CSS-MPCCC) to solve the UAVs’ path planning and decision-making at each moment. CSS-MPCCC is a two-stage optimization method with joint optimization of search performance and optimal selection from Parato frontier, which relies on NSGA-II. Our model and algorithm enabled the UAV swarm to perform coverage search on both static and dynamic targets. In simulations, the proposed CSS-MPCCC algorithm is compared with classical random search and parallel search algorithms, and the performance of model and algorithm is analyzed on several groups of simulations. It is validated that the proposed algorithm effectively enables the UAV swarm to search for static and dynamic targets in uncertain scenarios.