Target Aircraft Research Articles

Decision-Making Strategies for Close-Range Air Combat Based on Reinforcement Learning with Variable-Scale Actions

The current research into decision-making strategies for air combat focuses on the performance of algorithms, while the selection of actions is often ignored, and the actions are often fixed in amplitude and limited in number in order to improve the convergence efficiency, making the strategy unable to give full play to the maneuverability of the aircraft. In this paper, a decision-making strategy for close-range air combat based on reinforcement learning with variable-scale actions is proposed; the actions are the variable-scale virtual pursuit angles and speeds. Firstly, a trajectory prediction method consisting of a real-time prediction, correction, and judgment of errors is proposed. The back propagation (BP) neural network and the long and short term memory (LSTM) neural network are used as base prediction network and correction prediction network, respectively. Secondly, the past, current, and future positions of the target aircraft are used as virtual pursuit points, and they are converted into virtual pursuit angles as the track angle commands using angle guidance law. Then, the proximity policy optimization (PPO) algorithm is applied to train the agent. The simulation results show that the attacking aircraft that uses the strategy proposed in this paper has a higher win rate during air combat and the attacking aircraft’s maneuverability is fully utilized.

Aircraft Target Detection in Low Signal-to-Noise Ratio Visible Remote Sensing Images

With the increasing demand for the wide-area refined detection of aircraft targets, remote sensing cameras have adopted an ultra-large area-array detector as a new imaging mode to obtain broad width remote sensing images (RSIs) with higher resolution. However, this imaging technology introduces new special image degradation characteristics, especially the weak target energy and the low signal-to-noise ratio (SNR) of the image, which seriously affect the target detection capability. To address the aforementioned issues, we propose an aircraft detection method for RSIs with low SNR, termed L-SNR-YOLO. In particular, the backbone is built blending a swin-transformer and convolutional neural network (CNN), which obtains multiscale global and local RSI information to enhance the algorithm’s robustness. Moreover, we design an effective feature enhancement (EFE) block integrating the concept of nonlocal means filtering to make the aircraft features significant. In addition, we utilize a novel loss function to optimize the detection accuracy. The experimental results demonstrate that our L-SNR-YOLO achieves better detection performance in RSIs than several existing advanced methods.

Study of UAVs in attempted formation flight based on pure azimuth passive positioning

As a great crystallization of human technology in the past hundred years, many western countries have applied high technology to the research and development of UAVs since the 1990s. In this paper, the pure azimuth passive positioning problem in attempted formation flight of UAVs is explored through the intersection of different straight lines to determine the position of the target aircraft, and the location information of the predicted and accurate points is used to optimize the target analysis. And the conclusion is drawn in minimizing the emission signal scenario of electromagnetic waves. Then, according to the knowledge of graph theory, the UAV array is fitted to a graph, a coordinate system is established with the position of one of the UAVs, and a database with standard positions is created for comparison.

Unmanned aerial vehicle strike on a flat plate: Tests and numerical simulations

The incursion of Unmanned Aerial Vehicles (UAVs) into airports often occurs due to the popularity of drones, which may lead to a threat to aircraft flight safety. Therefore, estimating the dynamic impact load caused by drone strikes is essential. This paper proposes a test method with high precision and low cost involving launching of a UAV to impact a flat plate specimen by using an air gun. The test results of UAVs impacting flat plates at different impact velocities, such as the UAV damage deformation captured by a high-speed camera and strain vs time dynamic response curves of plates, were obtained and analysed. At the same time, a corresponding numerical simulation was carried out by using the explicit finite element software LS-DYNA. The predicted damage to the UAV and strain on the flat plate during the strike process were compared with the test results. The overall trend of the simulation results is in good agreement with the test results, at least for the first three milliseconds of the event. This shows that the numerical simulation model established in this paper is reasonable. The UAV numerical method established in the present paper can be used to carry out numerical simulations and evaluations of the collision safety of UAVs against large aircraft and high-value ground targets. The results show that the local deformation of the impacted target is uneven due to the distribution of concentrated mass components such as motors, battery, and camera. As the impact velocity of the UAV increases, all parts of the UAV are seriously damaged and basically in a fragmented state, and the battery is greatly deformed. The interaction between the UAV and the flat plate specimen is approximately 2.7 ms, and the UAV numerical simulation model established in this paper can well simulate the real UAV impact process.

Scattering Features Spatial-Structural Association Network for Aircraft Recognition in SAR Images

Due to the all-day, all-weather imaging characteristics of Synthetic Aperture Radar (SAR), aircraft recognition in SAR images is emerging as an vital issue. Electromagnetic scattering (ES) characteristics of target are the unique features of SAR systems. In particular, it is more pronounced for aircraft targets with discrete appearance. However, the existing deep learning methods effectively extract features in image domain, ignoring the potential ES features. To obtain more valuable features for SAR aircraft recognition, an innovative scattering features spatial-structural association network (SFSA) is proposed in this paper. In this work, the strong scattering points (SSPs) of aircraft are extracted and converted into graph structure data, which more directly represent the spatial-structural association among SSPs and clearly reflect the geometric structure of the aircraft target. Subsequently, the graph convolutional neural network (GCN) is employed to extract the structural and high-level semantic ES features. Then, a modified VGGNet is designed to effectively extract the image domain features of aircraft with extremely discrete appearances. In brief, the SFSA network is an end-to-end network that integrates structural ES features and more discriminative image domain features of the aircraft to achieve higher recognition performance. It is also demonstrated that structural ES features facilitate the recognition of aircraft. Experiments on the SAR aircraft dataset validate the effectiveness of SFSA network compared to traditional CNN-based SAR recognition networks and graph neural networks (GNN).

Classification Matters More: Global Instance Contrast for Fine-Grained SAR Aircraft Detection

Since significant intra-class differences and inconspicuous inter-class variations, fine-grained aircraft detection in synthetic aperture radar (SAR) images is challenging. And the inherent lack of detailed features and severe noise interference in SAR images make it difficult to learn class-specific feature representations. Current detection approaches focus more on localization accuracy and ignore classification performance, which is more critical in fine-grained detection. To address the above challenges, we present GICNet: Global Instance Contrast for fine-grained SAR aircraft detection. A Global Instance-level Contrast (GIC) module is proposed to improve inter-class divergences and intra-class compactness. With a specially constructed global instance set, GICNet can contrast a large number of different aircraft targets while keeping a small batch size. Furthermore, we design a novel quality-aware focal loss (QAFL) to facilitate the accurate classification of well-localized aircraft targets. Meanwhile, to maintain localization performance, we develop a new edge-aware bounding-box refinement (EABR) module to refine predicted coarse bounding boxes. Experimental results show that our GICNet outperforms current advanced detectors and achieves a new state-of-the-art performance on the GaoFen-3 SAR aircraft detection dataset. Especially, GICNet also has advantages in reducing misclassification and recognizing well-located targets.

Fast detection algorithm of aircraft targets based on optical remote sensing for embedded platform

Fast detection algorithm of aircraft targets based on optical remote sensing for embedded platform

Aircraft target detection method based on improved SSD

Aircraft target detection method based on improved SSD

Complex Optical Remote-Sensing Aircraft Detection Dataset and Benchmark

Aircraft detection in remote sensing images is significant in both military and civilian fields, such as air traffic control and battlefield dynamic monitoring. Deep learning methods can achieve promising detection performance with sufficient and labeled samples. However, current aircraft datasets are mainly from a single data source and lack diverse scenes and targets, making it difficult to train a robust and generalized detector. Therefore, we manually label and construct a complex optical remote sensing aircraft target detection dataset (CORS-ADD) from Google Earth and multiple satellites such as WorldView-2, WorldView-3, Pleiades, Jilin-1, and IKONOS. It contains 7,337 images covering typical airports and various rare scenes, including the aircraft carrier, ocean and land with flying aircraft. The dataset consists of 32,285 civil and military aircraft instances, including bombers, fighters, and early warning aircraft. These targets range from 4×4 pixels to 240×240 pixels and are all labeled with both horizontal bounding box (HBB) and oriented bounding box (OBB) annotations. The various scenes and sufficient instances can fully support the training and evaluation of data-driven algorithms. Meanwhile, based on the constructed dataset, we train and evaluate several detectors to provide a benchmark and help promote the development of aircraft detection techniques.

YOLO-Class: Detection and Classification of Aircraft Targets in Satellite Remote Sensing Images Based on YOLO-Extract

YOLO-Class: Detection and Classification of Aircraft Targets in Satellite Remote Sensing Images Based on YOLO-Extract

Adaptive fuze-warhead coordination method based on BP artificial neural network

The appropriate fuze-warhead coordination method is important to improve the damage efficiency of air defense missiles against aircraft targets. In this paper, an adaptive fuze-warhead coordination method based on the Back Propagation Artificial Neural Network (BP-ANN) is proposed, which uses the parameters of missile-target intersection to adaptively calculate the initiation delay. The damage probabilities at different radial locations along the same shot line of a given intersection situation are calculated, so as to determine the optimal detonation position. On this basis, the BP-ANN model is used to describe the complex and highly nonlinear relationship between different intersection parameters and the corresponding optimal detonating point position. In the actual terminal engagement process, the fuze initiation delay is quickly determined by the constructed BP-ANN model combined with the missile-target intersection parameters. The method is validated in the case of the single-shot damage probability evaluation. Comparing with other fuze-warhead coordination methods, the proposed method can produce higher single-shot damage probability under various intersection conditions, while the fuze-warhead coordination effect is less influenced by the location of the aim point.

Research on Aircraft image recognition based on transfer learning and improved YOLOv5 model

Effective differentiation of aircraft types using images is important for providing military combat information as well as civilian aircraft operations. Aircraft image recognition has many difficulties such as large variations of target scale, complex backgrounds, and difficult data set acquisition, which lead to the low recognition accuracy of existing models. To address the problem of low recognition accuracy caused by the above difficulties. This paper proposes the improved YOLOv5 model for the recognition of aircraft images. First, this paper designs the CSPResNet50dCA network as the backbone of the YOLOv5 model to enhance the feature extraction capability for small target aircraft in images. By introducing the coordinate attention mechanism and the CSP structure, the feature-focusing capability and the computing speed of the model are enhanced. Afterward, we use data enhancement to expand the data set and transfer learning to improve the generalization ability and convergence speed of the model, so as to improve its robustness. The experimental results show that the improved YOLOv5 model has significantly improved the recognition accuracy of aircraft targets， and significantly enhanced feature extraction ability for small target aircraft with good generalization ability.

Using Drone Swarms as a Countermeasure of Radar Detection

The deployment of a drone swarm from carrier aircraft can support critical operations in which target aircraft should be protected by ground-based radar detection. To be successful as a countermeasure, the drones that are involved in the swarm must be equipped with proper payload systems and the geometry among the swarm units must be well designed. This paper describes the development of a scaled drone swarm geometry that can electromagnetically obscure a target from radar detection. Different drone swarm configurations were analyzed to select a feasible solution to develop ground and in-flight tests. During the tests, a compact software radar was used to detect a target drone. Several ground tests were executed to characterize the radar echo response of the target drone installed on a wooden tripod. Different geometries of corner reflectors were tested on tripods to select the swarm geometry that better obscured the target drone. Flight tests were executed involving decoy drones equipped with a corner reflector and a target drone to validate the proposed drone swarm geometry. The presented design of a drone swarm geometry allowed us to characterize the scaled distances among the swarm units and between the swarm and the target that must be protected against a ground-based radar detection.

Synthetic aperture radar image aircraft detection based on target spatial imaging characteristics

With the development of artificial intelligence and synthetic aperture radar (SAR) imaging technology, methods based on deep learning have been gradually applied to SAR image aircraft detection. However, due to the special SAR imaging mechanism, the imaging results of aircraft targets in SAR images do not have clear features and appear as sparse scattering centers. In addition, airports contain strongly scattering buildings and objects, such as corridor bridges, which will bring huge interference to SAR aircraft target detection. To alleviate these problems, we propose an aircraft scattering information extraction and detection model (SIEDM) based on the spatial imaging characteristics of the targets. First, a scattering center feature extraction module is designed to extract the potential scattering centers of the aircraft targets in the SAR images and acquire the overall structural features of the aircraft targets. In addition, the adaptive noise suppression module is proposed to suppress background interference by learning global information. Finally, we conduct a series of experiments on an SAR image aircraft detection dataset. The experimental results show that the mean average precision of the aircraft SIEDM is 95.7%, which is better than other methods, and the proposed modules in this paper are effective.

The impact of the joint use of false aircraft targets in a group of combat unmanned aerial vehicles on the results of destruction

The subject of the paper is the process of joint use of false aircraft targets as part of a group of combat unmanned aerial vehicles to perform tasks to destroy enemy targets. The current paper determines the optimal number of false aircraft targets in a group of combat unmanned aerial vehicles to defeat targets with the desired degree of their defeat and acceptable losses of own combat unmanned aerial vehicles. The scientific task is to improve the methodology for determining the optimal number of false aircraft targets in a group of combat unmanned aerial vehicles to defeat targets with the desired degree of defeat and acceptable losses of own combat unmanned aerial vehicles. To achieve the purpose of the research paper, the following tasks were performed: the process of joint use of false aircraft targets as part of a group of combat unmanned aerial vehicles to defeat targets with the desired degree of their defeat has been formalized; a mathematical model for determining the optimal composition of false aircraft targets as part of a group of combat unmanned aerial vehicles to minimize the losses of real aircraft during their tasks has been developed; based on the conditions of a practical example, the functioning of the improved methodology has been tested and the relevant recommendations have been substantiated. Methods. The mathematical model uses combinatorics and binomial probability distribution. The following results were obtained. An improved methodology is presented, which is multifunctional since, on the one hand, its use makes it possible to determine the required number of false aircraft targets in a group of combat unmanned aerial vehicles to defeat targets with the desired degree of their defeat and acceptable losses of own combat unmanned aerial vehicles, and on the other hand, to determine the predicted level of losses of real aircraft targets from the group when using a certain number of false aircraft targets. Conclusions. The availability of an improved methodology with ready-made calculation formulas will allow the prediction of possible results of combat use of groups of unmanned aerial vehicles based on the initial parameters and substantiate recommendations on their possible composition.

Remote sensing aircraft object detection algorithm based on memory CenterNet

In order to solve the problem of poor detection accuracy of CenterNet in remote sensing aircraft with dense targets and complex backgrounds, an improved memory CenterNet object detection algorithm is proposed. First, the multiscale receptive field module and residual attention module are introduced to improve ResNet50, which is used as a new backbone feature extraction network. It has a strong feature extraction ability and detection speed at the same time. Different dilated ratios are used in the multiscale receptive field to expand the receptive field and extract multiscale features, and the multiscale target features are highlighted through the attention mechanism. Then the last set of residual networks in ResNet50 is deleted, and the residual attention network is introduced and stacked in the same way. The feature parameters of different channels in the residual attention network are calculated by two-dimensional cosine transform and weighted with the original feature map, and the target features are highlighted to enhance the ability to locate the target at the end of the network. Second, three times deconvolution is replaced by a memory feature fusion module. The shallow detail information and the deep semantic information are fully fused. The key information in the output feature map is further enriched, which is beneficial to the improvement of model detection performance. Finally, the experimental results show that the average accuracy of remote sensing aircraft dataset is 88.46%, which is 18.21% higher than that of the original algorithm and effectively improves the detection accuracy of remote sensing aircraft targets.

SEAN: A Simple and Efficient Attention Network for Aircraft Detection in SAR Images

Due to the unique imaging mechanism of synthetic aperture radar (SAR), which leads to a discrete state of aircraft targets in images, its detection performance is vulnerable to the influence of complex ground objects. Although existing deep learning detection algorithms show good performance, they generally use a feature pyramid neck design and large backbone network, which reduces the detection efficiency to some extent. To address these problems, we propose a simple and efficient attention network (SEAN) in this paper, which takes YOLOv5s as the baseline. First, we shallow the depth of the backbone network and introduce a structural re-parameterization technique to increase the feature extraction capability of the backbone. Second, the neck architecture is designed by using a residual dilated module (RDM), a low-level semantic enhancement module (LSEM), and a localization attention module (LAM), substantially reducing the number of parameters and computation of the network. The results on the Gaofen-3 aircraft target dataset show that this method achieves 97.7% AP at a speed of 83.3 FPS on a Tesla M60, exceeding YOLOv5s by 1.3% AP and 8.7 FPS with 40.51% of the parameters and 86.25% of the FLOPs.

Lightweight convolutional neural network for aircraft small target real-time detection in Airport videos in complex scenes

Airport aircraft identification has essential application value in conflict early warning, anti-runway foreign body intrusion, remote command, etc. The scene video images have problems such as small aircraft targets and mutual occlusion due to the extended shooting distance. However, the detection model is generally complex in structure, and it is challenging to meet real-time detection in air traffic control. This paper proposes a real-time detection network of scene video aircraft-RPD (Realtime Planes Detection) to solve this problem. We construct the lightweight convolution backbone network RPDNet4 for feature extraction. We design a new core component CBL module(Conv (Convolution), BN (Batch Normalization), RELU (Rectified Linear Units)) to expand the range of receptive fields in the neural network. We design a lightweight channel adjustment module block by adding separable depth convolution to reduce the model’s structural parameters. The loss function of GIou loss improves the convergence speed of network training. the paper designs the four-scale prediction module and the adjacent scale feature fusion technology to fuse the adjacent features of different abstract levels. Furthermore, a feature pyramid structure with low-level to high-level is constructed to improve the accuracy of airport aircraft’s small target detection. The experimental results show that compared with YOLOv3, Faster-RCNN, and SSD models, the detection accuracy of the RPD model improved by 5.4%, 7.1%, and 23.6%; in terms of model parameters, the RPD model was reduced by 40.5%, 33.7%, and 80.2%; In terms of detection speed, YOLOv3 is 8.4 fps while RPD model reaches 13.6 fps which is 61.9% faster than YOLOv3.

Intelligent Target Design Based on Complex Target Simulation

The emergence and popularization of various fifth-generation fighter jets with supersonic cruise, super maneuverability, and stealth functionalities have raised higher and more comprehensive challenges for the tactical performance and operational indicators of air defense weapon systems. The training of air defense systems requires simulated targets; however, the traditional targets cannot simulate the radar cross-section (RCS) distribution characteristics of fifth-generation fighter aircrafts. In addition, the existing target aircrafts are expensive and cannot be mass-produced. Therefore, in this paper, a corner reflector and a Luneburg ball reflector with RCS distribution characteristics of a fifth-generation fighter in a certain spatial area are designed for target simulation. Several corner reflectors and Luneburg balls are used to form an array to realize the simulations. The RCS value and distribution characteristics of the target can be combined with fuzzy clustering and a single-chip microcomputer to design an intelligent switching system, which improves the practicability of the intelligent target design proposed in this paper.

Micro-Doppler Feature Extraction of Rotating Structures of Aircraft Targets with Terahertz Radar

The micro-Doppler features formed by the micro-motion of rotating blades of rotors and turbines are of great significance for aircraft target detection and recognition. Mastering the micro-motion features is the premise of radar target identification. The blades’ length and rotation rate are vital parameters for classifying aircraft targets. One can instantly judge the type and state of the targets by extracting micro-Doppler features. To extract the micro-Doppler features of rotating blades of the turbine target, we utilized microwave-band and terahertz-band radar to simulate the target and extract the Doppler frequency-shift information. For a turbine model with an obvious blade tip structure, we propose an algorithm based on wavelet coefficient enhancement and inverse Radon transform, integrating the time–frequency analysis with image processing. Under low SNR, this method allows for a high-accuracy parameter estimate. For a two-bladed rotor model without an obvious blade tip structure, we conducted an actual measurement experiment on the model utilizing a 120 GHz radar, and we propose a parameter estimation algorithm based on the fitting of the time–frequency distribution. By fitting the data of the time–frequency diagram, the micro-motion characteristic parameters of the rotor target were obtained. The simulation and experimental results demonstrate the benefits of terahertz radar in target detection, and indicate that the proposed algorithms have the characteristics of high extraction precision and insensitivity to noise.