Aerial Target Detection Research Articles

MPE-YOLO: enhanced small target detection in aerial imaging

Aerial image target detection is essential for urban planning, traffic monitoring, and disaster assessment. However, existing detection algorithms struggle with small target recognition and accuracy in complex environments. To address this issue, this paper proposes an improved model based on YOLOv8, named MPE-YOLO. Initially, a multilevel feature integrator (MFI) module is employed to enhance the representation of small target features, which meticulously moderates information loss during the feature fusion process. For the backbone network of the model, a perception enhancement convolution (PEC) module is introduced to replace traditional convolutional layers, thereby expanding the network’s fine-grained feature processing capability. Furthermore, an enhanced scope-C2f (ES-C2f) module is designed, utilizing channel expansion and stacking of multiscale convolutional kernels to enhance the network’s ability to capture small target details. After a series of experiments on the VisDrone, RSOD, and AI-TOD datasets, the model has not only demonstrated superior performance in aerial image detection tasks compared to existing advanced algorithms but also achieved a lightweight model structure. The experimental results demonstrate the potential of MPE-YOLO in enhancing the accuracy and operational efficiency of aerial target detection. Code will be available online (https://github.com/zhanderen/MPE-YOLO).

A Efficient and Accurate UAV Detection Method Based on YOLOv5s

Due to the limited computational resources of portable devices, target detection models for drone detection face challenges in real-time deployment. To enhance the detection efficiency of low, slow, and small unmanned aerial vehicles (UAVs), this study introduces an efficient drone detection model based on YOLOv5s (EDU-YOLO), incorporating lightweight feature extraction and balanced feature fusion modules. The model employs the ShuffleNetV2 network and coordinate attention mechanisms to construct a lightweight backbone network, significantly reducing the number of model parameters. It also utilizes a bidirectional feature pyramid network and ghost convolutions to build a balanced neck network, enriching the model’s representational capacity. Additionally, a new loss function, EloU, replaces CIoU to improve the model’s positioning accuracy and accelerate network convergence. Experimental results indicate that, compared to the YOLOv5s algorithm, our model only experiences a minimal decrease in mAP by 1.1%, while reducing GFLOPs from 16.0 to 2.2 and increasing FPS from 153 to 188. This provides a substantial foundation for networked optoelectronic detection of UAVs and similar slow-moving aerial targets, expanding the defensive perimeter and enabling earlier warnings.

Improved YOLOv8 algorithms for small object detection in aerial imagery

In drone aerial target detection tasks, a high proportion of small targets and complex backgrounds often lead to false positives and missed detections, resulting in low detection accuracy. To improve the accuracy of the detection of small targets, this study proposes two improved models based on YOLOv8s, named IMCMD_YOLOv8_small and IMCMD_YOLOv8_large. Each model accommodates different application scenarios. First, the network structure was optimized by removing the backbone P5 layer used to detect large targets and merging the P4, P3, and P2 layers, which are better suited for detecting medium and small targets; P3 and P2 serve as detection heads to focus more on small targets. Subsequently, the coordinate attention mechanism is integrated into the backbone’s C2f, to create a C2f_CA module that enhances the model’ s focus on key information and secures a richer flow of gradient information. Subsequently, a multiscale attention feature fusion module was designed to merge the shallow and deep features. Finally, a Dynamic Head was introduced to unify the perception of scale, space, and tasks, further enhancing the detection capability for small targets. Experimental results on the VisDrone2019 dataset demonstrated that, compared with YOLOv8s, IMCMD_YOLOv8_small achieved improvements of 7.7% and 5.1% in mAP@0.5 and mAP@0.5:0.95, respectively, with a 73.0% reduction in the parameter count. The IMCMD_YOLOv8_large model showed even more significant improvements in these metrics, reaching 10.8% and 7.3%, respectively, with a 47.7% reduction in the parameter count, displaying superior performance in small target detection tasks. The improved models not only enhanced the detection accuracy but also achieved model lightweighting, thereby proving the effectiveness of the improvement strategies and showcasing superior performance compared with other classic models.

An Aerial Image Detection Algorithm Based on Improved YOLOv5.

To enhance aerial image detection in complex environments characterized by multiple small targets and mutual occlusion, we propose an aerial target detection algorithm based on an improved version of YOLOv5 in this paper. Firstly, we employ an improved Mosaic algorithm to address redundant boundaries arising from varying image scales and to augment the training sample size, thereby enhancing detection accuracy. Secondly, we integrate the constructed hybrid attention module into the backbone network to enhance the model's capability in extracting pertinent feature information. Subsequently, we incorporate feature fusion layer 7 and P2 fusion into the neck network, leading to a notable enhancement in the model's capability to detect small targets. Finally, we replace the original PAN + FPN network structure with the optimized BiFPN (Bidirectional Feature Pyramid Network) to enable the model to preserve deeper semantic information, thereby enhancing detection capabilities for dense objects. Experimental results indicate a substantial improvement in both the detection accuracy and speed of the enhanced algorithm compared to its original version. It is noteworthy that the enhanced algorithm exhibits a markedly improved detection performance for aerial images, particularly under real-time conditions.

Aero-YOLO: An Efficient Vehicle and Pedestrian Detection Algorithm Based on Unmanned Aerial Imagery

The cost-effectiveness, compact size, and inherent flexibility of UAV technology have garnered significant attention. Utilizing sensors, UAVs capture ground-based targets, offering a novel perspective for aerial target detection and data collection. However, traditional UAV aerial image recognition techniques suffer from various drawbacks, including limited payload capacity, resulting in insufficient computing power, low recognition accuracy due to small target sizes in images, and missed detections caused by dense target arrangements. To address these challenges, this study proposes a lightweight UAV image target detection method based on YOLOv8, named Aero-YOLO. The specific approach involves replacing the original Conv module with GSConv and substituting the C2f module with C3 to reduce model parameters, extend the receptive field, and enhance computational efficiency. Furthermore, the introduction of the CoordAtt and shuffle attention mechanisms enhances feature extraction, which is particularly beneficial for detecting small vehicles from a UAV perspective. Lastly, three new parameter specifications for YOLOv8 are proposed to meet the requirements of different application scenarios. Experimental evaluations were conducted on the UAV-ROD and VisDrone2019 datasets. The results demonstrate that the algorithm proposed in this study improves the accuracy and speed of vehicle and pedestrian detection, exhibiting robust performance across various angles, heights, and imaging conditions.

Availability evaluation model for space-based optical aerial target detection system

Availability evaluation model for space-based optical aerial target detection system

Minimum detection velocity performance analysis for air moving target detection in a spaceborne surveillance radar system

AbstractDue to the advantages of wide coverage, continuous remote monitoring, and high measurement accuracy, the spaceborne multi‐channel surveillance radar has been widely used for the air moving target detection and tracking. In this paper, the minimum detection velocity (MDV) definition for the aerial target detection performance evaluation in a spaceborne multi‐channel radar system is analysed, where three kinds of MDV definitions based on empirical formula, output signal‐to‐clutter‐plus‐noise ratio (SCNR) loss criterion, and output SCNR criterion are discussed in detail based on theoretical analysis and simulation verification. The analysis results will provide valuable reference for the practical spaceborne radar system designment with the air target detection mode.

Small Aerial Target Detection Using Trajectory Hypothesis and Verification

Due to cluttered backgrounds, long-range imaging, rapid relative motion, etc., the detection of small aerial targets remains a challenge. Existing works have illustrated the importance of temporal cues for robust small aerial target detection. However, the strong assumptions about the temporal cues give such methods high computational complexity and weak adaptability. To address this problem, we treat trajectory verification as a classification problem using convolutional neural networks. A novel small aerial target detection method that uses trajectory hypothesis and verification is proposed in this study. First, the IMU assisted inter-frame difference is used to extract target candidates from each single image. Then, based on the continuous and smoothness characteristics of the target trajectory, hypotheses of the required length are generated by linking target candidates in adjacent frames. Finally, the trajectory hypotheses are sent to a trained classification convolution neural network for verification. The detected targets are traced back from the verified trajectory. Furthermore, trajectory merge is conducted to link adjacent trajectory segments. The proposed method can achieve real-time processing. Experimental results on public datasets show that the proposed method performs better than existing methods.

INCREASING CHARACTERISTICS OF BSNR 9С32 DURING IMPLEMENTATION IN ITS ANTENNA SYSTEM OF THE ELEMENTS ON A MODERN ELEMENT BASE

The military conflicts of the last decade are characterized by the wide use of air assets including small - sized and (or) unmanned ones by the warring parties. In modern conditions one of the effective measures to combat them is to increase the accuracy of coordinate information provided to combat (or fire) means. Increasing the accuracy of coordinate information determines: the possibility of non-searching detection and (or) capture of aerial targets by fire means, increasing the survivability of air defense systems due to the reduction of working time (including the time for "radiation") and rapid change of their positions after completing the assigned task.
 The modern development of science and technology makes it possible to create effective means of air defense to combat existing and promising means of air attack but their development and commissioning requires large costs. In this regard, the issue of improving the characteristics of existing complexes without significant capital investments is gaining relevance.
 One of the important characteristics of the detection means and tracking of a multi-channel air assets anti- aircraft missile complex is the resolution and accuracy of measuring the angular coordinates of objects. This is due to the fact that modern air defence anti-aircraft missile complex uses information about the angular velocities of the missile-target line and the missile velocity vector when aiming anti-aircraft guided missiles using the proportional approximation method. Therefore, the accuracy of their measurement depends on the features of the missile’s flight trajectory when firing at the target and as a result the probability of its damage. The resolution and accuracy of angular coordinate measurement depends significantly on the characteristics of the antenna system.
 It is proposed to use their analogues on a modern element base instead of standard multi-channel missile guidance station 9C32 antenna elements in the work . Estimates of the characteristics of the phased antenna array when introducing promising pass-through ferrite phase shifters (in particular the increase in the accuracy of measuring angular coordinates and the range of aerial targets detection) were obtained using mathematical modeling and calculation methods. Obtained ratios allow for an appropriate assessment.
 The obtained results can be used in the development of proposals for the introduction of modern antenna elements (ferrite phase shifters) into the antenna systems of multi-channel radio equipment of anti-aircraft missile systems.The last decade is characterized by a number of military conflicts, in most episodes of which the achievement of the goal (reconnaissance and (or) defeat of certain targets) by the warring parties is mostly achieved through the use of aircraft, including small and (or) unmanned. The main difference is to obtain the desired results without a direct collision with the enemy ground component of troops (forces).
 Most of the recommended measures to combat aircraft in modern conditions can be reduced to: the rational construction of battle order (using the air defense separation), the widespread use of covert communications, radio reconnaissance and electronic warfare, the creation of erroneous and camouflage combat (reserve) air defence means positions, automation of transmission and processing of information about the air situation with the use of modern technologies and increase the accuracy of coordinate information provided to combat (or fire) means.
 Improving the accuracy of coordinate information causes: the possibility of searchless detection and (or) capture of air targets by fire, increasing the survivability of air defense systems by reducing working hours (including time for “radiation”) and rapid change of their positions after the task. Modern algorithms for processing coordinate information provided by air defense systems take into account the errors of primary coordinates measurement by radio engineering, the delay time of information in communication channels and its possible distortion. At the same time, they do not explicitly take into account the influence of topographic errors and orientation errors of radio equipment.
 In the work with the use of mathematical modelling methods, an assessment of the characteristics of the phased antenna array was carried out with the introduction of a promising pass-through ferrite phase shifter (in particular, an increase in the accuracy of measuring angular coordinates and the range of detection of aerial targets). The obtained ratios allow to make an appropriate assessment.
 The obtained results can be used when introducing modern ferrite phase shifters to the antenna system of the multi-channel missile guidance station 9С32.

Space-based infrared aerial target detection method via interframe registration and spatial local contrast

Infrared aerial target detection on a space-based platform is of great importance in the field of aerospace. However, the intensities of clutter may be much stronger than those of aerial targets in space-based infrared images, which causes issues in accurate aerial target detection. Existing detection methods cannot adapt well to such a situation, and often receive results with missed detections and false alarms since they are prone to enhance clutter rather than the target. To tackle such limitations, we propose a two-stage Interframe Registration and Spatial Local Contrast (IFR-SLC) based method for space-based infrared aerial target detection. In the first stage, the interframe registration model is constructed to suppress strong clutter and highlight the target. In the second stage, the spatial local contrast model is introduced to further suppress the residual background and enhance the target, which eventually generates the saliency map with only the aerial target remaining. Target extraction is conducted by setting an adaptive threshold. Five space-based sequences with different backgrounds were selected for evaluation, and experimental results indicated better performances of IFR-SLC compared with those of space-based or state-of-the-art detection methods.

UAV Aerial Photography Target Detection Algorithm Based On Improved YOLOv5

Aiming at the characteristics of complex background and less target pixels in UAV aerial images, a UAV aerial target detection algorithm based on improved yolov5 is proposed in this paper. First, the low-level feature map with richer small target information is introduced into the feature fusion network, so a new prediction head is added. Then, the structure of the feature fusion network is improved to realize cross layer connection and assign different weights to each feature map. Finally, the loss function is optimized to further improve the detection accuracy of the model. The model is trained with VisDrone data set. The results show that the average accuracy of the improved algorithm is improved by 4.6 percentage points compared with yolov5x, and it has better detection performance for scenes with complex background and dense small targets.

SPECTRAL ESTIMATION METHODS FOR A JOINT SYSTEM OF THE NON-NOISE-LIKE TARGETS DETECTION AND THE NOISE RADIATING SOURCES LOCALIZATION

Context. For many radars, the autonomous systems of the non-noise-like aerial targets (AT) detection and the noise radiating sources (NRS) localization (direction-of-arrival estimation) may be replaced with a single detection-localization system, which carries out the common operations of the AT-detection and the NRS-localization only once. For such a system, groups of noneigenvalue and eigenvalue decomposition based “super-resolving” spectral estimation (SE) methods are considered to substantiate efficient one for the NRS-localization.
 Objective. The comparative analysis efficiency of the SE-methods of different groups by a set of criteria and recommendations on their practical application.
 Method. The methods’ efficiency is analyzed analytically, under simulation results and their comparison with new results presented in the open literature. In the simulation, a well-grounded and practically examined software-algorithmic basis of adaptive lattice filters for nonparametric SE-methods implementation is used.
 The results. It is shown that the SE-methods of both groups have no restrictions on the antenna array configuration (flat, ring, etc.), including when used in non-equal spaced “sparse” antenna arrays with inter-element distances of more than half radar wavelength. A comparison is made on the resolution (determination of the NRS number) and the NRS-localization (direction-of-arrival estimation) efficiency by methods of different groups when using various antenna arrays. It is shown that the methods of the first group (non-eigenvalue based) in terms of the probability of correct resolution, are almost not inferior to the known and new methods of the second group (eigenvalue ones). Based on the set of criteria and practical application conditions for direction-of-arrival estimation of the noise radiating sources, it is recommended to use the Capon’s minimum variance method if there are limitations on the computational complexity of the method. In the absence of such restrictions, it is advisable to use the SE-bank of methods.
 Conclusions. For the practical implementation of a joint system of the non-noise-like aerial target detection and the noise radiating sources localization, a structural-algorithmic basis of adaptive lattice filters is preferred. Using latter, along with the weight vector forming for the target detection, it is possible to implement not only the Capon’s method, but also a SE-bank of methods by combining the squares of absolute values of its original vectors’ components.

Drone Detection Using Sparse Lidar Measurements

Unmanned aerial vehicles (UAV) have been serving people, fulfilling various roles in research, industry and military, not to exclude personal entertainment. They have also been in use more often for malicious purposes, such as annoying neighbors, disrupting air-travel, attacking people or infrastructure. Therefore, motivated particularly by malicious uses, the research community has been interested in proposing solutions for detection of UAVs. In this work, we present a ground based aerial target detection system using lidars, relying on sparse detections rather than dense point clouds, with the aim of not only detecting but also estimating their motion and active tracking. We lay a theoretical groundwork to analyse the performance of such a lidar based detection system and help understanding its limitations. The work is complemented with field experiments utilizing a state-of-the-art lidar and several drones of different sizes, showing effectiveness in both detection and tracking using sparse measurements.

On the Detection of Decoy Aerial Targets

On the Detection of Decoy Aerial Targets

Automated Aerial Docking System Using Onboard Vision-Based Deep Learning

This paper proposes an automated aerial docking system for unmanned aerial vehicles. The proposed automated aerial docking system consists of the following two subsystems: 1) docking mechanical system and 2) vision-based deep learning detection/tracking system. A fundamental challenge during the midair docking phase is integration between the leader and follower vehicles with a robust target detection/tracking strategy. This paper presents not only the design of a probe-and-drogue-type aerial docking system, but it also presents the development of an onboard machine learning system for aerial target detection and tracking, which is limited from 0.1 to 3.5 m. The aerial docking system is designed based on a bistable mechanism to increase the robustness of integration and separation between two vehicles. The prototype of the proposed docking mechanism is built by a 3D printer. To employ effective drogue detection in the air, a deep convolutional neural network-based single-stage detector algorithm, YOLOv4-tiny, is applied. Furthermore, to track the moving drogue in the air simultaneously, a point cloud-based tracking algorithm with an RGB-D camera system is developed. The developed deep learning-based detection/tracking system is implemented to be operated in the Arm architecture-based onboard machine learning computer. For performance validation of the proposed automated aerial docking system, a ground test using two robot arms and an indoor flight test using quadcopter drone and an unmanned ground vehicle were conducted.

Local Spatial-Temporal Matching Method for Space-Based Infrared Aerial Target Detection.

The feature of a space-based infrared signal is that the intensity of clutter is much stronger than that of an aerial target. Such a feature poses a great challenge to aerial target detection since the existing infrared target detection methods are prone to enhance clutter but ignore the real target, which results in missed detection and false alarms. To tackle the challenge, we propose a concise method based on local spatial–temporal matching (LSM). Specifically, LSM mainly consists of local normalization, local direction matching, spatial–temporal joint model, and inverse matching. Local normalization aims to enhance the target to the same strength as the clutter, so that the weak target will not be ignored. After normalization, a direction-matching step is applied to estimate the moving direction of the background between the basic frame and referenced frame. Then the spatial–temporal joint model is constructed to enhance the target and suppress strong clutter. Similarly, inverse matching is conducted to further enhance the target. Finally, a salience map is obtained, on which the aerial target is extracted by the adaptive threshold segmentation. Experiments conducted on four space-based infrared datasets indicate that LSM handles the above challenge and outperforms seven state-of-the-art methods in space-based infrared aerial target detection.

Analytical Formula to Investigate the Modulation of Sloped Targets Using LiDAR Waveform

The relationship between the properties of targets and the features of modulated waveforms is fundamental to remote sensing based on the full-waveform light detection and ranging (LiDAR). Developing a mathematical formula of modulated LiDAR waveforms is of great importance in establishing this relationship. In this study, we derive the mathematical formula of a laser echo waveform modulated by four typical targets: a rectangle, a square, a circle, and an equilateral triangle. By using these formulas, numerical calculations are performed to investigate the relationship between the properties of the targets and the features of the modulated waveform. The results show that, at a rotation angle of 80°, the modulated waveform changes from a Gaussian form to a non-Gaussian form and finally returns to a Gaussian form as the target size increases. When the target center deviates from the laser spot center and the rotation angle increases, the modulated waveform varies from Gaussian to non-Gaussian form, the value of the peak intensity decreases, and the position of the peak intensity shifts. The specific trends of these changes are successfully explained in terms of the geometric characteristics of the target and the spatial intensity distribution of the incident laser. The distinct dependencies of modulated waveforms on geometric shape, size, center position, and rotation angle indicate a convenient method for identity extraction and target recognition in remote sensing using full-waveform LiDAR. This offers exciting implications for applications, such as topological mapping, environment monitoring, and aerial target detection and recognition.

Vision-Based 3D Aerial Target Detection and Tracking for Maneuver Decision in Close-Range Air Combat

Automatic maneuver decision in close-range air combat depends on the situation awareness of the 3D aerial space. Optimal decision could only be made when the 3D state (e.g. 3D position, orientation and velocity) of the target aircraft is accurately provided. Together with the state of the aircraft in our side, optimal maneuver decision could be made by maximizing the situation advantage or utilizing deep reinforcement learning. On the other hand, vision-based 3D sensing methods are ideal for acquiring the 3D state of the target aircraft in close-range air combat, since radar and other sensors work badly in such short range. In this paper, we propose a novel pipeline for vision-based maneuver decision in close-range air combat. The proposed pipeline contains three main modules: 3D target detection based on Augmented Autoencoder, 3D target tracking based on segmentation and optimization, and maneuver decision based on advantage maximization and Deep Q Networks (DQN). The proposed method effectively handles the difficulties in air combat environment, such as fast movement, occlusion from cloud, etc. Experiments demonstrate that our method could robustly detect and track the target aircraft in complex environment, which provides strong priors for maneuver decision and helps to significantly improve the winning rate of short-range air combat.

Infrared small target detection method based on multi-scale feature fusion

Infrared small target detection is widely used in aerial target detection and tracking system because of its long detection distance and strong anti-jamming ability. Aiming at the shortcomings of the current infrared small target detection algorithm, such as low precision rate and high false alarm rate when dealing with complex background. In this paper, we propose an end-to-end infrared small target detection model (called MFSSD) based on multi-scale feature fusion. Considering the trait of the targets, we propose a feature fusion module by using a refinement and fusion feature map method, and improve the correlation of different channels through the SP Module. The experimental results of three different sequences of infrared image detection show that the average detection accuracy of the MFSSD algorithm in infrared small target detection is as high as 87.8%. Compared with the traditional multi-scale feature fusion detection algorithm, both the precision rate and the recall rate have been significantly improved.

Investigating the Effects of a Combined Spatial and Spectral Dimensionality Reduction Approach for Aerial Hyperspectral Target Detection Applications

Target detection and classification is an important application of hyperspectral imaging in remote sensing. A wide range of algorithms for target detection in hyperspectral images have been developed in the last few decades. Given the nature of hyperspectral images, they exhibit large quantities of redundant information and are therefore compressible. Dimensionality reduction is an effective means of both compressing and denoising data. Although spectral dimensionality reduction is prevalent in hyperspectral target detection applications, the spatial redundancy of a scene is rarely exploited. By applying simple spatial masking techniques as a preprocessing step to disregard pixels of definite disinterest, the subsequent spectral dimensionality reduction process is simpler, less costly and more informative. This paper proposes a processing pipeline to compress hyperspectral images both spatially and spectrally before applying target detection algorithms to the resultant scene. The combination of several different spectral dimensionality reduction methods and target detection algorithms, within the proposed pipeline, are evaluated. We find that the Adaptive Cosine Estimator produces an improved F1 score and Matthews Correlation Coefficient when compared to unprocessed data. We also show that by using the proposed pipeline the data can be compressed by over 90% and target detection performance is maintained.