In distribution energy systems (DESs), the information security plays an essential role. Real-time encryption techniques can guarantee the transmission rate and confidentiality simultaneously. We propose a novel real-time encryption algorithm for DESs. First, we construct a 13D chaotic system based on quaternion, Chua’s circuit and complex variables, and discuss the existence of the attractors and other chaotic characteristics. Secondly, based on the proposed complex chaotic system, a simple encryption algorithm is proposed to ensure the confidentiality of DESs. Finally, our algorithm is verified by the standard test image and monitoring pictures in DESs. The execution time of the proposed algorithm is 0.0035s and 0.0021s respectively. It is only one percent of other algorithms. At the same time, our other security performances are competitive with other algorithms. And it has the ability to resist the malicious attack and avoid unnecessary equipment shutdown in DESs.

As visual simultaneous localization and mapping (vSLAM) is easy disturbed by the changes of camera viewpoint and scene appearance when building a globally consistent map, the robustness and real-time performance of key frame image selections cannot meet the requirements. To solve this problem, a real-time closed-loop detection method based on a dynamic Siamese networks is proposed in this paper. First, a dynamic Siamese network-based fast conversion learning model is constructed to handle the impact of external changes on key frame judgments, and an elementwise convergence strategy is adopted to ensure the accurate positioning of key frames in the closed-loop judgment process. Second, a joint training strategy is designed to ensure the model parameters can be learned offline in parallel from tagged video sequences, which can effectively improve the speed of closed-loop detection. Finally, the proposed method is applied experimentally to three typical closed-loop detection scenario datasets and the experimental results demonstrate the effectiveness and robustness of the proposed method under the interference of complex scenes.

In low-texture-scenes, point feature based simultaneous location and map (SLAM) building algorithms are difficult to extract enough valid feature points, so that the SLAM system cannot work properly. To solve such problems, this paper proposes a visual SLAM algorithm for fusion of point and line features. On the basis of ORB point feature extraction, the LSD line feature algorithm is introduced and the extracted line segments are represented by the Plücker coordinate method. In the online feature matching stage, the LBD line segment descriptor is introduced, and the quadtree algorithm is used to avoid the concentration problem of point feature extraction. The progressive sampling uniformity (PROSAC) algorithm and geometric constraints are used to filter out incorrect matching of point line features, thereby improving positioning accuracy. Then, in the process of feature fusion, the idea of point line feature weighting is introduced to construct a new error function for point line fusion, minimizing the error function to obtain more accurate positioning information. Finally, the publicly available dataset was used to conduct experiments.

Localization is one of the basic capabilities of a movable unmanned system. Among many localization techniques, geomagnetic field-based localization, which does not require external infrastructure, has unique advantages in indoor localization, but its accuracy and precision still need to be further improved. In this paper, we propose a landmark named LIDMF based on intensity differential of magnetic field with better discrimination, study the extraction and matching methods of LIDMF, and apply LIDMF to robot localization, and experimentally prove the effectiveness of our landmark.

Cybersecurity is the security cornerstone of digital transformation of the power grid and construction of new power systems. The traditional network security situation quantification method only analyzes from the perspective of network performance, ignoring the impact of various power application services on the security situation, so the quantification results cannot fully reflect the power information network risk state. This study proposes a method for quantifying security situation of the power information network based on the evolutionary neural network. First, the security posture system architecture is designed by analyzing the business characteristics of power information network applications. Second, combining the importance of power application business, the spatial element index system of coupled interconnection is established from three dimensions of network reliability, threat, and vulnerability. Then, the BP neural network optimized by the genetic evolutionary algorithm is incorporated into the element index calculation process, and the quantitative model of security posture of the power information network based on the evolutionary neural network is constructed. Finally, a simulation experiment environment is built according to a power sector network topology, and the effectiveness and robustness of the method proposed in the study are verified.

In traditional visual simultaneous localization and mapping (vSLAM) systems, feature points are critical for feature matching and pose estimation. However, visual odometry keyframes often contain many dynamic points, which can adversely affect the accuracy of the SLAM system. To address this issue, this paper proposes a dynamic feature point elimination algorithm based on the YOLOv5 target detection network and optical flow method using image processing techniques. Specifically, the YOLOv5 network is used to identify regions in the image that may contain dynamic objects, which are then divided into sub-regions. Depth information from the depth image and feature points from the dynamic regions are used to obtain feature points with depth information. These feature points are then clustered using the GMM clustering algorithm, and dynamic feature points are eliminated based on the clustering results. Experimental results show that the proposed algorithm effectively eliminates dynamic points in the image, thus improving the accuracy of the SLAM system.