Synthetic aircraft RS image modelling based on improved conditional GAN joint embedding network

Developing an efficient and quality remote sensing (RS) technology using volume and efficient modelling in different aircraft RS images is challenging. Generative models serve as a natural and convenient simulation method. Because aircraft types belong to the fine class under the rough class, the issue of feature entanglement may occur while modelling multiple aircraft classes. Our solution to this issue was a novel first-generation realistic aircraft type simulation system (ATSS-1) based on the RS images. It realised fine modelling of the seven aircraft types based on a real scene by establishing an adaptive weighted conditional attention generative adversarial network and joint geospatial embedding (GE) network. An adaptive weighted conditional batch normalisation attention block solved the subclass entanglement by reassigning the intra-class-wise characteristic responses. Subsequently, an asymmetric residual self-attention module was developed by establishing a remote region asymmetric relationship for mining the finer potential spatial representation. The mapping relationship between the input RS scene and the potential space of the generated samples was explored through the GE network construction that used the selected prior distribution z, as an intermediate representation. A public RS dataset (OPT-Aircraft_V1.0) and two public datasets (MNIST and Fashion-MNIST) were used for simulation model testing. The results demonstrated the effectiveness of ATSS-1, promoting further development of realistic automatic RS simulation.

Split delivery scheme for vehicle supported UAV

The traditional demand split logistics distribution schemes are mainly based on vehicle distribution. In recent years, with the rapid development of civil UAVs, the use of UAVs for distribution will be more efficient and economical in some specific conditions. In this paper, through the analysis of the advantages of UAV distribution, we simulate the demands and distribution schemes in real scene, especially in remote mountainous areas. And then, we propose to define a demand-splitting distribution scheme of vehicle-supported UAV, which ensures the customer point will be satisfy demand when the loading capacity of the UAV is exceeded. This scheme aims to provides a realizable distribution scheme for the customers point in mountainous areas with large demand.

Attention Optimized Deep Generative Adversarial Network for Removing Uneven Dense Haze

The existing dehazing algorithms are problematic because of dense haze being unevenly distributed on the images, and the deep convolutional dehazing network relying too greatly on large-scale datasets. To solve these problems, this paper proposes a generative adversarial network based on the deep symmetric Encoder-Decoder architecture for removing dense haze. To restore the clear image, a four-layer down-sampling encoder is constructed to extract the semantic information lost due to the dense haze. At the same time, in the symmetric decoder module, an attention mechanism is introduced to adaptively assign weights to different pixels and channels, so as to deal with the uneven distribution of haze. Finally, the framework of the generative adversarial network is generated so that the model achieves a better training effect on small-scale datasets. The experimental results showed that the proposed dehazing network can not only effectively remove the unevenly distributed dense haze in the real scene image, but also achieve great performance in real-scene datasets with less training samples, and the evaluation indexes are better than other widely used contrast algorithms.

A planning framework of environment detection for unmanned ground vehicle in unknown off-road environment

This paper describes a planning framework of environment detection for unmanned ground vehicle (UGV) in the completely unknown off-road environment, which is able to quickly guide the UGV with nonholonomic constraints to detect the environmental information as much as possible. The contributions of this paper contain four fold. First, due to the sensor characteristics of camera and lidar, we present a two-layer combined detection map which can accurately represent the detected and undetected area. Second a frontier extraction algorithm based on RRT considering information acquisition and nonholonomic constraints of UGV is used to extract the target pose. Third, we use a search path planning method based on motion primitive which is able to handle obstacle constraints of environment, nonholonomic constraints of UGV. Fourth the heuristic fusion is proposed to guide the extension of motion primitives to generate a kinodynamically feasible and collision-free trajectory in real-time. And it works well in both simulation and real scene.

Modeling and visualization of the forecast trajectory for the decision support system for controlling the movement of a river displacement vessel

An approach to dynamic modeling of the predicted trajectory of movement of a displacement vessel and its continuous visualization on an electronic panel is considered, superimposed on the actual digital twin of the real scene of the environment along the course of the vessel. The hardware and software implementation of the developed approach as a decision support system for the navigator in the form of a standard option of the integrated control panel located in the wheelhouse provides an opportunity to objectively assess the safe distance to potential navigation obstacles within the ship’s course at the free distance of the vessel by means of combined visualization. As part of the organizational and technical measures to ensure the safety of navigation, the proposed innovative approach to continuous joint visualization of the digital twin of the current scene of the surrounding sailing situation and the predicted trajectory of the vessel’s movement acquires significant importance in the operation of automatic vessels as an option for the supervisor to intervene in the operation of an integrated automatic control system in complex navigating conditions.

Three-Dimensional Outdoor Analysis of Single Synthetic Building Structures by an Unmanned Flying Agent Using Monocular Vision

An algorithm designed for analysis and understanding a 3D urban-type environment by an autonomous flying agent, equipped only with a monocular vision, is presented. The algorithm is hierarchical and is based on the structural representation of the analyzed scene. Firstly, the robot observes the scene from a high altitude to build a 2D representation of a single object and a graph representation of the 2D scene. The 3D representation of each object arises as a consequence of the robot’s actions, as a result of which it projects the object’s solid on different planes. The robot assigns the obtained representations to the corresponding vertex of the created graph. The algorithm was tested by using the embodied robot operating on the real scene. The tests showed that the robot equipped with the algorithm was able not only to localize the predefined object, but also to perform safe, collision-free maneuvers close to the structures in the scene.

Application of Augmented Reality (AR) Technology in Low-Voltage Line Interruption Training and Power Grid Emergency Training

Augmented reality technology uses computer performance to create a virtual scene and accurately integrate the virtual scene with the real world, and finally uses a video projector to present the virtual and real scene to the user, thereby significantly improving the user’s visual experience and Feeling knowledge. Therefore, augmented reality technology can be well applied to training companies. The use of virtual reality and augmented reality technology in the aerospace, construction and shipbuilding industries has achieved remarkable results, and the era of augmented reality applications in the power grid has also arrived. With the development of mobile terminals such as mobile phones, it has become an excellent platform for augmented reality applications. This article focuses on the application of augmented reality (AR) technology in low-voltage line interruption training and network emergency training. First, the basic technology of augmented reality (AR) and the application of augmented reality (AR) in power grid emergency training are introduced using bibliographic research methods. Then design a network emergency training system for low-voltage disconnection training, and finally test the algorithm used in this article. The detection result shows that the detection of feature points using AGAST takes less than 3ms, while the Shi-Tomasi operator is about 20ms. It can be seen that the use of AGAST operator to detect feature points has a great improvement in speed.

Application of Virtual Reality in the Teaching of Interior Design

With the rapid development of computer technology, a new technology – virtual reality has arisen at this historical moment. This technology mainly creates a real scene through simulation so as to reflect the changing form of objects. As a complex art form, the characteristics of interior design cannot be displayed only through pictures and words but with the effective application of virtual reality, the development of interior design can be promoted. This article mainly analyzes the current teaching situation of interior design and puts forward specific application strategies of virtual reality in the teaching of interior design, which have guiding significance in improving the teaching effect of interior design.

Parallel Swarm Intelligent Motion Planning with Energy-Balanced for Multirobot in Obstacle Environment

Multirobot motion planning is always one of the critical techniques in edge intelligent systems, which involve a variety of algorithms, such as map modeling, path search, and trajectory optimization and smoothing. To overcome the slow running speed and imbalance of energy consumption, a swarm intelligence solution based on parallel computing is proposed to plan motion paths for multirobot with many task nodes in a complex scene that have multiple irregularly-shaped obstacles, which objective is to find a smooth trajectory under the constraints of the shortest total distance and the energy-balanced consumption for all robots to travel between nodes. In a practical scenario, the imbalance of task allocation will inevitably lead to some robots stopping on the way. Thus, we firstly model a gridded scene as a weighted MTSP (multitraveling salesman problem) in which the weights are the energies of obstacle constraints and path length. Then, a hybridization of particle swarm and ant colony optimization (GPSO-AC) based on a platform of Compute Unified Device Architecture (CUDA) is presented to find the optimal path for the weighted MTSPs. Next, we improve the A ∗ algorithm to generate a weighted obstacle avoidance path on the gridded map, but there are still many sharp turns on it. Therefore, an improved smooth grid path algorithm is proposed by integrating the dynamic constraints in this paper to optimize the trajectory smoothly, to be more in line with the law of robot motion, which can more realistically simulate the multirobot in a real scene. Finally, experimental comparisons with other methods on the designed platform of GPUs demonstrate the applicability of the proposed algorithm in different scenarios, and our method strikes a good balance between energy consumption and optimality, with significantly faster and better performance than other considered approaches, and the effects of the adjustment coefficient q on the performance of the algorithm are also discussed in the experiments.