The navigation of small unmanned aerial vehicles (UAVs) mainly depends on global positioning systems (GPSs). However, GPSs are vulnerable to attack by spoofing, which causes the UAVs to lose their positioning ability. To address this issue, we propose a deep learning method to detect the spoofing of GPS signals received by small UAVs. Firstly, we describe the GPS signal dataset acquisition and preprocessing methods; these include the hardware system of the UAV and the jammer used in the experiment, the time and weather conditions of the data collection, the use of Spearman correlation coefficients for preprocessing, and the use of SVM-SMOTE to solve the spoofing data imbalance. Next, we introduce a PCA-CNN-LSTM model. We used principal component analysis (PCA) of the model to extract feature information related to spoofing from the GPS signal dataset. The convolutional neural network (CNN) in the model was used to extract local features in the GPS signal dataset, and long short-term memory (LSTM) was used as a posterior module of the CNN for further processing and modeling. To minimize randomness and chance in the simulation experiments, we used the 10-fold cross-validation method to train and evaluate the computational performance of our spoofing machine learning model. We conducted a series of experiments in a numerical simulation environment and evaluated the proposed model against the most advanced traditional machine learning and deep learning models. The results and analysis show that the PCA-CNN-LSTM neural network model achieved the highest accuracy (0.9949). This paper provides a theoretical basis and technical support for spoofing detection for small-UAV GPS signals.

An extended robot–world and hand–eye calibration method is proposed in this paper to evaluate the transformation relationship between the camera and robot device. This approach could be performed for mobile or medical robotics applications, where precise, expensive, or unsterile calibration objects, or enough movement space, cannot be made available at the work site. Firstly, a mathematical model is established to formulate the robot-gripper-to-camera rigid transformation and robot-base-to-world rigid transformation using the Kronecker product. Subsequently, a sparse bundle adjustment is introduced for the optimization of robot–world and hand–eye calibration, as well as reconstruction results. Finally, a validation experiment including two kinds of real data sets is designed to demonstrate the effectiveness and accuracy of the proposed approach. The translation relative error of rigid transformation is less than 8/10,000 by a Denso robot in a movement range of 1.3 m × 1.3 m × 1.2 m. The distance measurement mean error after three-dimensional reconstruction is 0.13 mm.

Infrared images can provide prominent targets based on the radiation difference, making them suitable for use in all day and night conditions. On the other hand, visible images can offer texture details with high spatial resolution. Infrared and visible image fusion is promising to achieve the best of both. Conventional frequency or spatial multi-scale transformation methods are good at preserving image details. Deep learning-based methods become more and more popular in image fusion because they can preserve high-level semantic features. To tackle the challenge in extracting and fusing cross-modality and cross-domain information, we propose a Spatial-Frequency Collaborative Fusion (SFCFusion) framework that effectively fuses spatial and frequency information in the feature space. In the frequency domain, source images are decomposed into base and detail layers with existing frequency decomposition methods. In the spatial domain, a kernel-based saliency generation module is designed to preserve spatial region-level structural information. A deep learning-based encoder is employed to extract features from the source images, decomposed images and saliency maps. In the shared feature space, we achieve cross-modality spatial-frequency collaborative fusion through our proposed adaptive fusion scheme. We have conducted experiments to compare our SFCFusion with both conventional and deep learning approaches on TNO, LLVIP and M ³ FD datasets. The qualitative and quantitative evaluation results demonstrate the effectiveness of our SFCFusion. We have further demonstrated the superiority of our SFCFusion in the downstream detection task. Our code will be available at https://github.com/ChenHanrui430/SFCFusion.

Soft actuators are the components responsible for organs and tissues adsorptive fixation in some surgical operations, but the lack of shape sensing and monitoring of a soft actuator greatly limits their application potential. Consequently, this paper proposes a real-time 3D shape reconstruction method of soft surgical actuator which has an embedded optical fiber with two Fiber Bragg Grating (FBG) sensors. First, the design principle and the sensing of the soft actuator based on FBG sensors are analyzed, and the fabrication process of soft actuator which has an embedded optical fiber with two FBG sensors is described. Next, the calibration of the FBG sensors is conducted. Based on curvatures and curve fitting functions, the strategy of 3D shapes reconstruction of the soft actuator is presented. Finally, some bending experiments of the soft actuator are carried out, and the 3D shapes of the soft actuator at different bending states are reconstructed. This well reconstructed 3D shape of a soft actuator demonstrates the effectiveness of the shape reconstruction method that is proposed in this paper, as well as the potential and increased applications of these structures for real soft surgical actuators.

Lens distortion parameters vary with the distance between the object point and the image plane. We propose an analytical model of depth-dependent distortion for large depth-of-field digital cameras used for high accuracy photogrammetry. Compared with the magnification-dependent model, the proposed one does not need focusing operation during calibration, thus eliminates focusing errors and guarantees the stability of camera interior parameters. Compared with the widely used constant distortion parameter model, the proposed model reduces the maximum distortion variation from 8.0 μm to 0.9 μm at 20 mm radial distance when the depth changes from 2.46 m to 4.51 m for the 35 mm lens, and from 23.0 μm to 3.6 μm when the depth changes from 2.07 m to 4.17 m for the 50 mm lens. Additionally, when applied to photogrammetry bundle adjustment, the proposed model reduces length measurement standard deviation from 0.055 mm to 0.028 mm in a measurement volume of 7.0 m × 3.5 m × 2.5m compared with the constant parameter model.