To keep the balance of precision and speed of unmanned aerial vehicles (UAVs) in detecting insulator defects during power inspection, an improved insulator defect identification algorithm, Insu-YOLO, which is based on the latest YOLOv8 network, is proposed in this paper. Firstly, to lower the computational complexity of the network, the GSConv module is introduced in the backbone and neck network. In the neck network, a lightweight content-aware reassembly of features (CARAFE) structure is adopted to better utilize the feature information for upsampling, which enhances the feature fusion capability of Insu-YOLO. Additionally, Insu-YOLO enhances the fusion between shallow and deep feature maps by adding an extra object detection layer, thereby increasing the accuracy for detecting small targets. The experimental results indicate that the mean average precision of Insu-YOLO reaches 95.9%, which is 3.95% higher than the YOLOv8n baseline model, with a memory usage of 9.2 MB. Moreover, the detection speed of Insu-YOLO is 87 frames/s which achieves the purpose of real-time identification of insulator defects.

UAV localization in denial environments is a hot research topic in the field of cross-view geo-localization. The previous methods tried to find the corresponding position directly in the satellite image through the UAV image, but they lacked the consideration of spatial information and multi-scale information. Based on the method of finding points with an image, we propose a novel architecture—a Weight-Adaptive Multi-Feature fusion network for UAV localization (WAMF-FPI). We treat this positioning as a low-level task and achieve more accurate localization by restoring the feature map to the resolution of the original satellite image. Then, in order to enhance the ability of the model to solve multi-scale problems, we propose a Weight-Adaptive Multi-Feature fusion module (WAMF), which introduces a weighting mechanism to fuse different features. Finally, since all positive samples are treated in the same way in the existing methods, which is very disadvantageous for accurate localization tasks, we introduce Hanning loss to allow the model to pay more attention to the central area of the target. Our model achieves competitive results on the UL14 dataset. When using RDS as the evaluation metric, the performance of the model improves from 57.22 to 65.33 compared to Finding Point with Image (FPI). In addition, we calculate the actual distance errors (meters) to evaluate the model performance, and the localization accuracy at the 20 m level improves from 57.67% to 69.73%, showing the powerful performance of the model. Although the model shows better performance, much remains to be done before it can be applied.

The geo-localization and navigation technology of unmanned aerial vehicles (UAVs) in denied environments is currently a prominent research area. Prior approaches mainly employed a two-stream network with non-shared weights to extract features from UAV and satellite images separately, followed by related modeling to obtain the response map. However, the two-stream network extracts UAV and satellite features independently. This approach significantly affects the efficiency of feature extraction and increases the computational load. To address these issues, we propose a novel coarse-to-fine one-stream network (OS-FPI). Our approach allows information exchange between UAV and satellite features during early image feature extraction. To improve the model's performance, the framework retains feature maps generated at different stages of the feature extraction process for the feature fusion network, and establishes additional connections between UAV and satellite feature maps in the feature fusion network. Additionally, the framework introduces offset prediction to further refine and optimize the model's prediction results based on the classification tasks. Our proposed model, boasts a similar inference speed to FPI while significantly reducing the number of parameters. It can achieve better performance with fewer parameters under the same conditions. As a one-stream network, our proposed model not only improves inference speed, but also reduces the number of parameters. Moreover, it achieves state-of-the-art performance on the UL14 dataset. Compared to previous models, our model achieved a significant 10.92-point improvement on the RDS metric, reaching 76.25. Furthermore, its performance in meter-level localization accuracy is impressive, with 82.62% improvement in 3-meter accuracy, 64.17% improvement in 5-meter accuracy, and 37.43% improvement in 10-meter accuracy. Code and models are publicly available at https://github.com/cjhing/OS-FPI.

In recent years, with the rapid development of UAV technology, drones have been widely applied in various fields. Obtaining accurate location information is crucial for UAVs when performing tasks in challenging environments. In previous research, a pure vision-based self-positioning method was employed, which determined the UAV’s position by matching the vertical view image of the UAV with offline satellite remote sensing images. However, in certain urban areas where architectural features are similar, and due to variations in image viewing angles, shooting positions, and sensor parameters, non-rigid deformations exist between UAV images and remote sensing images, posing significant challenges for UAV visual positioning. To address these challenges, we propose a novel approach called Deformable Convolutional Transformer-based UAV Positioning (DCD-FPI). Our approach combines the Transformer-based model with deformable convolution, enhancing the model’s capability to handle non-rigid image deformations and capture detailed information. We also employ adaptive spatial feature fusion through multi-scale fusion to preserve critical distinguishing features. Experimental comparisons on the UL14 dataset demonstrate that our model achieves improved performance, with an increase from 76.25 to 77.15 in terms of the evaluation index RDS. Moreover, our model reduces computational complexity from 14.28 GFLOPS to 11.54 GFLOPS and parameter quantity from 14.76 M to 13.96 M.

This paper presents a novel algorithm about the industrial robot contouring control based on the NURBS (non-uniform rational B-spline) curve. First, aiming at the error between the industrial robot’s actual trajectory and the desired trajectory, the contour error is proposed as the trajectory evaluation index, and the estimation algorithm of contour error based on the tangent approximation is proposed. Based on the tangent approximation algorithm, the estimation algorithm of contour error in the local task coordinate frame is proposed to realize the transformation from the Cartesian coordinate frame to the local task coordinate frame. Second, according to the configuration of the industrial robot, a modified cross-coupling control scheme based on the local task coordinate frame is designed. Finally, the Bernoulli’s lemniscate curves are constructed by NURBS curve and five-order polynomial curve, respectively, and they are symmetrical. The contrast experiment is designed using the two types of constructed Bernoulli’s lemniscate curves as the incentive trajectory. Through the analysis and comparison between the obtained uniaxial tracking error and the contour error curve of the two incentive trajectories, it is concluded that the incentive trajectory constructed by the NURBS curve has better contour control performance than that constructed by the five-order polynomial curve. The results drawn from this paper lay a certain foundation for the future high-precision contouring control of industrial robots.