Robust and Discriminative Feature Learning via Mutual Information Maximization for Object Detection in Aerial Images

Object detection in unmanned aerial vehicle(UAV)aerial images has become increasingly important in military and civil applications.General object detection models are not robust enough against interclass similarity and intraclass variability of small objects,and UAV-specific nuisances such as uncontrolledweather conditions.Unlike previous approaches focusing on high-level semantic information,we report the importance of underlying features to improve detection accuracy and robustness fromthe information-theoretic perspective.Specifically,we propose a robust and discriminative feature learning approach through mutual information maximization(RD-MIM),which can be integrated into numerous object detection methods for aerial images.Firstly,we present the rank sample mining method to reduce underlying feature differences between the natural image domain and the aerial image domain.Then,we design a momentum contrast learning strategy to make object features similar to the same category and dissimilar to different categories.Finally,we construct a transformer-based global attention mechanism to boost object location semantics by leveraging the high interrelation of different receptive fields.We conduct extensive experiments on the VisDrone and Unmanned Aerial Vehicle Benchmark Object Detection and Tracking(UAVDT)datasets to prove the effectiveness of the proposed method.The experimental results show that our approach brings considerable robustness gains to basic detectors and advanced detection methods,achieving relative growth rates of 51.0%and 39.4%in corruption robustness,respectively.Our code is available at https://github.com/cq100/RD-MIM(accessed on 2 August 2024).

A Vehicle Detection Method for Aerial Image Based on YOLO

With the application of UAVs in intelligent transportation systems, vehicle detection for aerial images has become a key engineering technology and has academic research significance. In this paper, a vehicle detection method for aerial image based on YOLO deep learning algorithm is presented. The method integrates an aerial image dataset suitable for YOLO training by pro-cessing three public aerial image datasets. Experiments show that the training model has a good performance on unknown aerial images, especially for small objects, rotating objects, as well as compact and dense objects, while meeting the real-time requirements.

CHANGE DETECTION FROM AERIAL IMAGES ACQUIRED IN DIFFERENT DURATIONS

Because of quick development of cities, the update of urban GIS data is very important. Change detection is the base of automatic or semi-automatic data update. One way of change detections in urban area is based on old and new aerial images acquired in different durations. The corresponding theory and experiments are introduced and analyzed in this paper. The main procedure includes four stages. The new and old images have to be registered firstly. Then image matching, based on the maximum correlation coefficient, is performed between registered images after the low contrast areas have been removed. The regions with low matching quality are extracted as candidate changed areas. Thirdly, the Gaussian-Laplacian operator is used to detect edges in candidate changed areas on both the registered images, and the straight lines are detected by Hough transformation. Finally, the changed houses and roads can be detected on the basis of straight line matching in candidate changed areas between registered images. Some experimental results show that the method introduced in this paper is effective.

Bidirectional parallel multi-branch convolution feature pyramid network for target detection in aerial images of swarm UAVs

In this paper,based on a bidirectional parallel multi-branch feature pyramid network(BPMFPN),a novel one-stage object detector called BPMFPN Det is proposed for real-time detection of ground multi-scale targets by swarm unmanned aerial vehicles(UAVs).First,the bidirectional parallel multi-branch convolution modules are used to construct the feature pyramid to enhance the feature expression abilities of different scale feature layers.Next,the feature pyramid is integrated into the single-stage object detection framework to ensure real-time performance.In order to validate the effectiveness of the proposed algorithm,experiments are conducted on four datasets.For the PASCAL VOC dataset,the proposed algorithm achieves the mean average precision(mAP)of 85.4 on the VOC 2007 test set.With regard to the detection in optical remote sensing(DIOR)dataset,the proposed algorithm achieves 73.9 mAP.For vehicle detection in aerial imagery(VEDAI)dataset,the detection accuracy of small land vehicle(slv)targets reaches 97.4 mAP.For unmanned aerial vehicle detection and tracking(UAVDT)dataset,the proposed BPMFPN Det achieves the mAP of 48.75.Compared with the previous state-of-the-art methods,the results obtained by the proposed algorithm are more competitive.The experimental results demonstrate that the proposed algorithm can effectively solve the problem of real-time detection of ground multi-scale targets in aerial images of swarm UAVs.

Enhancement Dataset for Low Altitude Unmanned Aerial Vehicle Detection

In recent years,the number of incidents involved with unmanned aerial vehicles(UAVs)has increased conspicuously,resulting in an increasingly urgent demand for developing anti-UAV systems. The vast requirements of high detection accuracy with respect to low altitude UAVs are put forward. In addition,the methods of UAV detection based on deep learning are of great potential in low altitude UAV detection. However,such methods need high-quality datasets to cope with the problem of high false alarm rate(FAR)and high missing alarm rate(MAR)in low altitude UAV detection,special high-quality low altitude UAV detection dataset is still lacking. A handful of known datasets for UAV detection have been rejected by their proposers for authorization and are of poor quality. In this paper,a comprehensive enhanced dataset containing UAVs and jamming objects is proposed. A large number of high-definition UAV images are obtained through real world shooting, web crawler, and data enhancement.Moreover,to cope with the challenge of low altitude UAV detection in complex backgrounds and long distance,as well as the puzzle caused by jamming objects,the noise with jamming characteristics is added to the dataset. Finally,the dataset is trained,validated,and tested by four mainstream deep learning models. The results indicate that by using data enhancement,adding noise contained jamming objects and images of UAV with complex backgrounds and long distance,the accuracy of UAV detection can be significantly improved. This work will promote the development of anti-UAV systems deeply,and more convincing evaluation criteria are provided for models optimization for UAV detection.

Safety Helmet Wearing Detection in Aerial Images Using Improved YOLOv4

In construction,it is important to check whether workers wear safety helmets in real time.We proposed using an unmanned aerial vehicle(UAV)to monitor construction workers in real time.As the small target of aerial photography poses challenges to safety-helmet-wearing detection,we proposed an improved YOLOv4 model to detect the helmet-wearing condition in aerial photography:(1)By increasing the dimension of the effective feature layer of the backbone network,the model’s receptive field is reduced,and the utilization rate of fine-grained features is improved.(2)By introducing the cross stage partial(CSP)structure into path aggregation network(PANet),the calculation amount of themodel is reduced,and the aggregation efficiency of effective features at different scales is improved.(3)The complexity of the YOLOv4 model is reduced by introducing group convolution and the pruning PANet multi-scale detection mode for de-redundancy.Experimental results show that the improved YOLOv4 model achieved the highest performance in the UAV helmet detection task,that the mean average precision(mAP)increased from83.67%of the original YOLOv4 model to 91.03%,and that the parameter amount of the model is reduced by 24.7%.The results prove that the improved YOLOv4 model can effectively respond to the requirements of real-time detection of helmet wearing by UAV aerial photography.

Improved Weighted Local Contrast Method for Infrared Small Target Detection

In order to address the problem of high false alarm rate and low probabilities of infrared small target detection in complex low-altitude background,an infrared small target detection method based on improved weighted local contrast is proposed in this paper.First,the ratio information between the target and local background is utilized as an enhancement factor.The local contrast is calculated by incorporating the heterogeneity between the target and local background.Then,a local product weighted method is designed based on the spatial dissimilarity between target and background to further enhance target while suppressing background.Finally,the location of target is obtained by adaptive threshold segmentation.As experimental results demonstrate,the method shows superior performance in several evaluation metrics compared with six existing algorithms on different datasets containing targets such as unmanned aerial vehicles(UAV).

A Novel Tensor Decomposition-Based Efficient Detector for Low-Altitude Aerial Objects With Knowledge Distillation Scheme

Unmanned aerial vehicles(UAVs) have gained significant attention in practical applications, especially the low-altitude aerial(LAA) object detection imposes stringent requirements on recognition accuracy and computational resources. In this paper, the LAA images-oriented tensor decomposition and knowledge distillation-based network(TDKD-Net) is proposed,where the TT-format TD(tensor decomposition) and equalweighted response-based KD(knowledge distillation) methods are designed to minimize redundant parameters while ensuring comparable performance. Moreover, some robust network structures are developed, including the small object detection head and the dual-domain attention mechanism, which enable the model to leverage the learned knowledge from small-scale targets and selectively focus on salient features. Considering the imbalance of bounding box regression samples and the inaccuracy of regression geometric factors, the focal and efficient IoU(intersection of union) loss with optimal transport assignment(F-EIoU-OTA)mechanism is proposed to improve the detection accuracy. The proposed TDKD-Net is comprehensively evaluated through extensive experiments, and the results have demonstrated the effectiveness and superiority of the developed methods in comparison to other advanced detection algorithms, which also present high generalization and strong robustness. As a resource-efficient precise network, the complex detection of small and occluded LAA objects is also well addressed by TDKD-Net, which provides useful insights on handling imbalanced issues and realizing domain adaptation.

Small objects detection in UAV aerial images based on improved Faster R-CNN

In order to solve the problem of small objects detection in unmanned aerial vehicle(UAV)aerial images with complex background,a general detection method for multi-scale small objects based on Faster region-based convolutional neural network(Faster R-CNN)is proposed.The bird’s nest on the high-voltage tower is taken as the research object.Firstly,we use the improved convolutional neural network ResNet101 to extract object features,and then use multi-scale sliding windows to obtain the object region proposals on the convolution feature maps with different resolutions.Finally,a deconvolution operation is added to further enhance the selected feature map with higher resolution,and then it taken as a feature mapping layer of the region proposals passing to the object detection sub-network.The detection results of the bird’s nest in UAV aerial images show that the proposed method can precisely detect small objects in aerial images.

Intelligent Passive Detection of Aerial Target in Space-Air-Ground Integrated Networks

Passive detection of moving target is an important part of intelligent surveillance. Satellite has the potential to play a key role in many applications of space-air-ground integrated networks(SAGIN). In this paper, we propose a novel intelligent passive detection method for aerial target based on reservoir computing networks. Specifically, delayed feedback networks are utilized to refine the direct signals from the satellite in the reference channels. In addition, the satellite direct wave interference in the monitoring channels adopts adaptive interference suppression using the minimum mean square error filter. Furthermore, we employ decoupling echo state networks to predict the clutter interference in the monitoring channels and construct the detection statistics accordingly. Finally, a multilayer perceptron is adopted to detect the echo signal after interference suppression. Extensive simulations is conducted to evaluate the performance of our proposed method. Results show that the detection probability is almost 100% when the signal-to-interference ratio of echo signal is-36 dB, which demonstrates that our proposed method achieves efficient passive detection for aerial targets in typical SAGIN scenarios.

Aerial multi-spectral AI-based detection system for unexploded ordnance

Unexploded ordnance(UXO)poses a threat to soldiers operating in mission areas,but current UXO detection systems do not necessarily provide the required safety and efficiency to protect soldiers from this hazard.Recent technological advancements in artificial intelligence(AI)and small unmanned aerial systems(sUAS)present an opportunity to explore a novel concept for UXO detection.The new UXO detection system proposed in this study takes advantage of employing an AI-trained multi-spectral(MS)sensor on sUAS.This paper explores feasibility of AI-based UXO detection using sUAS equipped with a single(visible)spectrum(SS)or MS digital electro-optical(EO)sensor.Specifically,it describes the design of the Deep Learning Convolutional Neural Network for UXO detection,the development of an AI-based algorithm for reliable UXO detection,and also provides a comparison of performance of the proposed system based on SS and MS sensor imagery.

Machine learning algorithm partially reconfigured on FPGA for an image edge detection system

Unmanned aerial vehicles(UAVs)have been widely used in military,medical,wireless communications,aerial surveillance,etc.One key topic involving UAVs is pose estimation in autonomous navigation.A standard procedure for this process is to combine inertial navigation system sensor information with the global navigation satellite system(GNSS)signal.However,some factors can interfere with the GNSS signal,such as ionospheric scintillation,jamming,or spoofing.One alternative method to avoid using the GNSS signal is to apply an image processing approach by matching UAV images with georeferenced images.But a high effort is required for image edge extraction.Here a support vector regression(SVR)model is proposed to reduce this computational load and processing time.The dynamic partial reconfiguration(DPR)of part of the SVR datapath is implemented to accelerate the process,reduce the area,and analyze its granularity by increasing the grain size of the reconfigurable region.Results show that the implementation in hardware is 68 times faster than that in software.This architecture with DPR also facilitates the low power consumption of 4 mW,leading to a reduction of 57%than that without DPR.This is also the lowest power consumption in current machine learning hardware implementations.Besides,the circuitry area is 41 times smaller.SVR with Gaussian kernel shows a success rate of 99.18%and minimum square error of 0.0146 for testing with the planning trajectory.This system is useful for adaptive applications where the user/designer can modify/reconfigure the hardware layout during its application,thus contributing to lower power consumption,smaller hardware area,and shorter execution time.

A multi-target stance detection based on Bi-LSTM network with position-weight

In the task of multi-target stance detection,there are problems the mutual influence of content describing different targets,resulting in reduction in accuracy.To solve this problem,a multi-target stance detection algorithm based on a bidirectional long short-term memory(Bi-LSTM)network with position-weight is proposed.First,the corresponding position of the target in the input text is calculated with the ultimate position-weight vector.Next,the position information and output from the Bi-LSTM layer are fused by the position-weight fusion layer.Finally,the stances of different targets are predicted using the LSTM network and softmax classification.The multi-target stance detection corpus of the American election in 2016 is used to validate the proposed method.The results demonstrate that the Bi-LSTM network with position-weight achieves an advantage of 1.4%in macro average F1 value in the comparison of recent algorithms.

Simulating unmanned aerial vehicle flight control and collision detection

An unmanned aerial vehicle(UAV)is a small,fast aircraft with many useful features.It is widely used in military reconnaissance,aerial photography,searches,and other fields;it also has very good practical-application and development prospects.Since the UAV’s flight orientation is easily changeable,its orientation and flight path are difficult to control,leading to its high damage rate.Therefore,UAV flight-control technology has become the focus of attention.This study focuses on simulating a UAV’s flight and orientation control,and detecting collisions between a UAV and objects in a complex virtual environment.The proportional-integral-derivative control algorithm is used to control the orientation and position of the UAV in a virtual environment.A version of the bounding-box method that combines a grid with a k-dimensional tree is adopted in this paper,to improve the system performance and accelerate the collision-detection process.This provides a practical method for future studies on UAV flight position and orientation control,collision detection,etc.

Shadow Detection and Compensation for Color Aerial Images

A method for shadow detection and compensation for color aerial images is presented. It is considered that the intensity value of each image pixel is the product of illumination function and ground object reflection, and the shadowed regions on the image are mainly caused by the short of illumination, so the information compensation for the shadowed regions should concentrate on the illumination adjustment of concerned area on the basis of the analysis of whole image. The shadow detection and compensation procedure proposed by this paper consists of four steps.

Rice Bacterial Infection Detection Using Ensemble Technique on Unmanned Aerial Vehicles Images

Establishing a system for measuring plant health and bacterial infection is critical in agriculture.Previously,the farmers themselves,who observed them with their eyes and relied on their experience in analysis,which could have been incorrect.Plant inspection can determine which plants reflect the quantity of green light and near-infrared using infrared light,both visible and eye using a drone.The goal of this study was to create algorithms for assessing bacterial infections in rice using images from unmanned aerial vehicles(UAVs)with an ensemble classification technique.Convolution neural networks in unmanned aerial vehi-cles image were used.To convey this interest,the rice’s health and bacterial infec-tion inside the photo were detected.The project entailed using pictures to identify bacterial illnesses in rice.The shape and distinct characteristics of each infection were observed.Rice symptoms were defined using machine learning and image processing techniques.Two steps of a convolution neural network based on an image from a UAV were used in this study to determine whether this area will be affected by bacteria.The proposed algorithms can be utilized to classify the types of rice deceases with an accuracy rate of 89.84 percent.

Desertification Detection in Makkah Region based on Aerial Images Classification

Desertification has become a global threat and caused a crisis,especially in Middle Eastern countries,such as Saudi Arabia.Makkah is one of the most important cities in Saudi Arabia that needs to be protected from desertification.The vegetation area in Makkah has been damaged because of desertification through wind,floods,overgrazing,and global climate change.The damage caused by desertification can be recovered provided urgent action is taken to prevent further degradation of the vegetation area.In this paper,we propose an automatic desertification detection system based on Deep Learning techniques.Aerial images are classified using Convolutional Neural Networks(CNN)to detect land state variation in real-time.CNNs have been widely used for computer vision applications,such as image classification,image segmentation,and quality enhancement.The proposed CNN model was trained and evaluated on the Arial Image Dataset(AID).Compared to state-of-the-art methods,the proposed model has better performance while being suitable for embedded implementation.It has achieved high efficiency with 96.47% accuracy.In light of the current research,we assert the appropriateness of the proposed CNN model in detecting desertification from aerial images.

Block Iterative STMV Algorithm and Its Application in Multi-Targets Detection

STMV beamforming algorithm needs inversion operation of matrix, and its engineering application is limited due to its huge computational cost. This paper proposed block iterative STMV algorithm based on one-phase regressive filter, matrix inversion lemma and inversion of block matrix. The computational cost is reduced approximately as 1/4 M times as original algorithm when array number is M. The simulation results show that this algorithm maintains high azimuth resolution and good performance of detecting multi-targets. Within 1 - 2 dB directional index and higher azimuth discrimination of block iterative STMV algorithm are achieved than STMV algorithm for sea trial data processing. And its good robustness lays the foundation of its engineering application.

Maximizing the probability an aerial anti-submarine torpedo detects its target

As a result of the high speed of anti-submarine patrol aircraft as well as their wide range, high efficiency and other characteristics, aerial torpedoes released by anti-submarine patrol aircraft have become the key anti submarine tool. In order to improve operational efficiency, a deep study was made of the target detection probabilities for aerial torpedoes released by anti-submarine patrol aircraft. The operational modes of aerial torpedoes were analyzed and mathematical-simulation models were then established. The detection probabilities of three attacking modes were then calculated. Measures were developed for improving low probabilities of detection when attacking a probable target position. This study provides an important frame of reference for the operation of aerial torpedo released by anti-submarine patrol aircraft.

Low-altitude small-sized object detection using lightweight feature-enhanced convolutional neural network

Unauthorized operations referred to as“black flights”of unmanned aerial vehicles(UAVs)pose a significant danger to public safety,and existing low-attitude object detection algorithms encounter difficulties in balancing detection precision and speed.Additionally,their accuracy is insufficient,particularly for small objects in complex environments.To solve these problems,we propose a lightweight feature-enhanced convolutional neural network able to perform detection with high precision detection for low-attitude flying objects in real time to provide guidance information to suppress black-flying UAVs.The proposed network consists of three modules.A lightweight and stable feature extraction module is used to reduce the computational load and stably extract more low-level feature,an enhanced feature processing module significantly improves the feature extraction ability of the model,and an accurate detection module integrates low-level and advanced features to improve the multiscale detection accuracy in complex environments,particularly for small objects.The proposed method achieves a detection speed of 147 frames per second(FPS)and a mean average precision(mAP)of 90.97%for a dataset composed of flying objects,indicating its potential for low-altitude object detection.Furthermore,evaluation results based on microsoft common objects in context(MS COCO)indicate that the proposed method is also applicable to object detection in general.