To address the problems of low network accuracy, slow speed, and a large number of model parameters in printed circuit board (PCB) defect detection, an improved detection algorithm of PCB surface defects based on YOLOv5 is proposed, named PCB-YOLO, in this paper. Based on the K-means++ algorithm, more suitable anchors for the dataset are obtained, and a small target detection layer is added to make the PCB-YOLO pay attention to more small target information. Swin transformer is embedded into the backbone network, and a united attention mechanism is constructed to reduce the interference between the background and defects in the image, and the analysis ability of the network is improved. Model volume compression is achieved by introducing depth-wise separable convolution. The EIoU loss function is used to optimize the regression process of the prediction frame and detection frame, which enhances the localization ability of small targets. The experimental results show that PCB-YOLO achieves a satisfactory balance between performance and consumption, reaching 95.97% mAP at 92.5 FPS, which is more accurate and faster than many other algorithms for real-time and high-precision detection of product surface defects.

At present, UAV aerial photography has a good prospect in agricultural production, disaster response, and other aspects. The application of UAVs can greatly improve work efficiency and decision-making accuracy. However, owing to inherent features such as a wide field of view and large differences in the target scale in UAV aerial photography images, this can lead to existing target detection algorithms missing small targets or causing incorrect detections. To solve these problems, this paper proposes a small target detection algorithm for UAV aerial photography based on improved YOLOv5s. Firstly, a small target detection layer is applied in the algorithm to improve the detection performance of small targets in aerial images. Secondly, the enhanced weighted bidirectional characteristic pyramid Mul-BiFPN is adopted to replace the PANet network to improve the speed and accuracy of target detection. Then, CIoU was replaced by Focal EIoU to accelerate network convergence and improve regression accuracy. Finally, a non-parametric attention mechanism called the M-SimAM module is added to enhance the feature extraction capability. The proposed algorithm was evaluated on the VisDrone-2019 dataset. Compared with the YOLOV5s, the algorithm improved by 7.30%, 4.60%, 5.60%, and 6.10%, respectively, in mAP@50, mAP@0.5:0.95, the accuracy rate (P), and the recall rate (R). The experiments show that the proposed algorithm has greatly improved performance on small targets compared to YOLOv5s.

Semantic segmentation plays an indispensable role in automatic analysis of remote sensing image data. However, the abundant semantic information and irregular shape patterns in remote sensing images are difficult to utilize, making it hard to segment remote sensing images only using convolution and single-scale feature maps. To achieve better segmentation performance, a multiscale feature pyramid decoder (MFPD) is proposed to fuse image features extracted by vision transformer (ViT). The decoder employs a novel 2-D-to-3-D transform method to obtain multiscale feature maps that contain rich context information and fuses the multiscale feature maps by channel concatenation. Furthermore, a dimension attention module (DAM) is designed to further aggregate the context information of the extracted remote sensing image features. This approach yields superior mean intersection over union (mIoU) on the Gaofen2-CZ dataset (60.42%) and GID-5 dataset (68.21%). Experimental results indicate that the comprehensive performance of our approach exceeds the compared segmentation methods based on convolutional neural network (CNN) and ViT.

Unmanned aerial vehicles (UAVs), due to their flexible deployment, are used as a 3-D space assistant tool for vehicular edge computing (VEC) to cover moving vehicles. However, existing work generally assumes relatively uniform vehicle distribution while the actual road conditions vary over time. The time-varying location of vehicles and road congestion in peak hours pose challenges to VEC. First, traffic congestion can lead to imbalanced UAVs load, that is UAVs covering congested areas are overloaded while others remain idle. Second, after the high-speed moving vehicle leaves the service range of the current UAV, it is unable to receive computing results of the original request task, which means task processing failure. In this work, we propose a framework of UAV clusters adaptive deployment (UCAD) to address these issues. By clustering vehicles, UCAD gives a density-based adaptive region determination (DBARD) algorithm to determine congested areas and dynamically update them to adapt to dynamic network environments. After that, UCAD presents a particle swarm optimization-based Cluster deployment algorithm (PSOC), deploying UAV clusters within determined areas to provide continuous services for vehicles. Simulation results demonstrate that UCAD can adaptively deploy UAV clusters to assist vehicles based on traffic congestion conditions. Simulation results show that compared to existing works, CONEC, TU2V, and IELTS, the proposed UCAD can increase the task success rate by 8.7%, 18.5%, and 23.5%, respectively. UCAD can achieve better performance on UAVs workload balance.

Smoking behavior in public places and fire bans seriously threatens the safety of people's lives and property. In order to ensure public safety, this paper proposes a smoking behavior detection method based on YOLOv5 algorithm and image processing. Aiming at the small target of cigarettes, this paper uses the K-means algorithm and the method of adding a small target detection layer to improve the YOLOv5 algorithm, and realizes the improvement of the detection accuracy. On the self-made data set, the false detection rate is 0%, and the AP is 92.3%, which is 6.7% higher than that of the YOLOv5s algorithm.