Search

The advancements in drone technologies, digital imaging, computer vision techniques, and the liberalized laws related to drone flying have opened up drone-based applications such as the delivery of supplies, search and rescue, aerial surveillance, and so on. The drones, especially the nano/micro/small drones, may be mounted with only low-resolution camera(s) due to their maximum takeoff weight limitations. The low-resolution images generated by the cameras, if used for landing, can result in faulty detection unless the photos are taken from a very close distance to the point of interest. Detection and recognition of the point(s) of interest as early as possible is required to ensure sufficient response time for safe maneuvering. Hence, the images are to be captured at greater heights or distances from the point(s) of interest, and obtaining the high-resolution images from the captured low-resolution images is crucial. The High Resolution (HR) and the Low Resolution (LR) image pairs for training super-resolution models in the works presented in literature are generated using two different cameras or the HR images are captured by the camera and LR images are generated by degrading the HR images. As both methods are not appropriate for small/ micro/nano category drones, we propose a novel method based on Ground Sampling Distance (GSD) to capture the LR and HR images. In this paper, we have presented the designed methodology for the creation of a dataset using drone-mounted cameras covering a broad spectrum of views of the target(s) suitable for training and testing of the Single Image Super-Resolution (SISR) models. We also present a methodology for selecting an appropriate target for imaging that enables the visual quality assessment of the developed super-resolution model. [ABSTRACT FROM AUTHOR]

Visual object tracking, crucial in aerial applications such as surveillance, cinematography, and chasing, faces challenges despite AI advancements. Current solutions lack full reliability, leading to common tracking failures in the presence of fast motions or long‐term occlusions of the subject. To tackle this issue, a 3D motion model is proposed that employs camera/vehicle states to locate a subject in the inertial coordinates. Next, a probability distribution is generated over future trajectories and they are sampled using a Monte Carlo technique to provide search regions that are fed into an online appearance learning process. This 3D motion model incorporates machine‐learning approaches for direct range estimation from monocular images. The model adapts computationally by adjusting search areas based on tracking confidence. It is integrated into DiMP, an online and deep learning‐based appearance model. The resulting tracker is evaluated on the VIOT dataset with sequences of both images and camera states, achieving a 68.9% tracking precision compared to DiMP's 49.7%. This approach demonstrates increased tracking duration, improved recovery after occlusions, and faster motions. Additionally, this strategy outperforms random searches by about 3.0%. [ABSTRACT FROM AUTHOR]

Nowadays, with the rapid development of consumer Unmanned Aerial Vehicles (UAVs), utilizing UAV platforms for visual surveillance has become very attractive, and a key part of this is remote vision-based pedestrian attribute recognition. Pedestrian Attribute Recognition (PAR) is dedicated to predicting multiple attribute labels of a single pedestrian image extracted from surveillance videos and aerial imagery, which presents significant challenges in the computer vision community due to factors such as poor imaging quality and substantial pose variations. Despite recent studies demonstrating impressive advancements in utilizing complicated architectures and exploring relations, most of them may fail to fully and systematically consider the inter-region, inter-attribute, and region-attribute mapping relations simultaneously and be stuck in the dilemma of information redundancy, leading to the degradation of recognition accuracy. To address the issues, we construct a novel Mask-Relation-Guided Transformer (MRG-T) framework that consists of three relation modeling modules to fully exploit spatial and semantic relations in the model learning process. Specifically, we first propose a Masked Region Relation Module (MRRM) to focus on precise spatial attention regions to extract more robust features with masked random patch training. To explore the semantic association of attributes, we further present a Masked Attribute Relation Module (MARM) to extract intrinsic and semantic inter-attribute relations with an attribute label masking strategy. Based on the cross-attention mechanism, we finally design a Region and Attribute Mapping Module (RAMM) to learn the cross-modal alignment between spatial regions and semantic attributes. We conduct comprehensive experiments on three public benchmarks such as PETA, PA-100K, and RAPv1, and conduct inference on a large-scale airborne person dataset named PRAI-1581. The extensive experimental results demonstrate the superior performance of our method compared to state-of-the-art approaches and validate the effectiveness of mask-relation-guided modeling in the remote vision-based PAR task. [ABSTRACT FROM AUTHOR]

Ground target detection and positioning systems based on lightweight unmanned aerial vehicles (UAVs) are increasing in value for aerial reconnaissance and surveillance. However, the current method for estimating the target's position is limited by the field of view angle, rendering it challenging to fulfill the demands of a real-time omnidirectional reconnaissance operation. To address this issue, we propose an Omnidirectional Optimal Real-Time Ground Target Position Estimation System (Omni-OTPE) that utilizes a fisheye camera and LiDAR sensors. The object of interest is first identified in the fisheye image, and then, the image-based target position is obtained by solving using the fisheye projection model and the target center extraction algorithm based on the detected edge information. Next, the LiDAR's real-time point cloud data are filtered based on position–direction constraints using the image-based target position information. This step allows for the determination of point cloud clusters that are relevant to the characterization of the target's position information. Finally, the target positions obtained from the two methods are fused using an optimal Kalman fuser to obtain the optimal target position information. In order to evaluate the positioning accuracy, we designed a hardware and software setup, mounted on a lightweight UAV, and tested it in a real scenario. The experimental results validate that our method exhibits significant advantages over traditional methods and achieves a real-time high-performance ground target position estimation function. [ABSTRACT FROM AUTHOR]

The growth of gated communities and the omnipresence of video surveillance have changed urban life considerably in the last decades. Especially in cities governed by neoliberal public policies and widespread fear of crime, residents search for security, social status, and shared services in fortified enclaves where video cameras watch everybody who enters their premises. These developments are not restricted to private space, and affluent neighborhoods in megacities are eager to adopt a wide range of surveillance technology to protect their citizens. Eight years ago, the affluent municipality of Lo Barnechea in the metropolitan region of Santiago, Chile, installed a surveillance balloon in a residential area. The local security forces currently operate six balloons, and residents have become accustomed to the ever-present gaze of aerial video cameras. This article contrasts the presence of this technology in a megacity against different perspectives on surveillance and urbanism. A consideration of its panoptic features leaves an unsatisfactory explanation. Citizens actively participate in generating public policies and smart technology for public safety, as is characteristic of a maximum security society. The surveillance balloons have become a sustainable element in the urban landscape and an appreciated part of the social fabric of the residential neighborhoods. [ABSTRACT FROM AUTHOR]

Forest fires present a substantial environmental challenge, constituting a dual menace to human life and ecological well-being. The imperative for forest fire prevention and management underscores the indispensability of robust detection, prediction, and behavior analysis systems. This scholarly paper offers a thorough exploration of diverse methodologies and techniques employed in the realms of forest fire detection, prediction, and behavior analysis. Encompassing both ground-based and aerial surveillance systems, as well as remote sensing technologies, machine learning-based approaches, and social media-driven systems, the survey provides a comprehensive overview of the multifaceted landscape of forest fire monitoring. In addition to delineating the current state of the art, the paper critically examines the challenges and limitations inherent in existing systems. Furthermore, it imparts valuable insights into prospective avenues for research and development within this domain. In essence, this paper underscores the significance of amalgamating data from various sources and employing diverse analytical methods to enhance our comprehension of forest fire behavior. The overarching goal is to foster the formulation of efficacious strategies for mitigating the impact of this environmental menace. [ABSTRACT FROM AUTHOR]

This paper presents a method based on particle swarm optimization (PSO) for optimizing the power settings of unmanned aerial vehicle (UAVs) along a given trajectory in order to minimize fuel consumption and maximize autonomy during surveillance missions. UAVs are widely used in surveillance missions and their autonomy is a key characteristic that contributes to their success. Providing a way to reduce fuel consumption and increase autonomy provides a significant advantage during the mission. The method proposed in this paper included path smoothing techniques in 3D for fixed-wing UAVs based on circular arcs that overfly the waypoints, an essential feature in a surveillance mission. It used the equations of motions and the decomposition of Newton's equation to compute the fuel consumption based on a given power setting. The proposed method used PSO to compute optimized power settings while respecting the absolute physical constraints, such as the load factor, the lift coefficient, the maximum speed and the maximum amount of fuel onboard. Finally, the method was parallelized on a multicore processor to accelerate the computation and provide fast optimization of the power settings in case the trajectory was changed in flight by the operator. Our results showed that the proposed PSO was able to reduce fuel consumption by up to 25% in the trajectories tested and the parallel implementation provided a speedup of 21.67× compared to a sequential implementation on the CPU. [ABSTRACT FROM AUTHOR]

The authors propose a sequence of acquisition and interpretation of geospatial data obtained using different methods and means during mineral mining toward the accuracy increase in evaluation of industrially disturbed land. This approach uses the concept of stage-wise transition from the areas of industrial facilities to their individual points. The integration of data of satellite surveys, ground-based laser scanning and unmanned aerial surveillance in the digital models of land areas is described. It is highlighted that the rational combination of different methods of geospatial data acquisition and interpretation produces a high-accurate geoinformation system of digital twins of various subsoil use facilities. [ABSTRACT FROM AUTHOR]

Fire is considered as an essential climate variable, emitting greenhouse gases in the combustion process. Current global assessments of fire emissions traditionally rely on coarse remotely-sensed burned area data, along with biome-specific combustion completeness and emission factors, to provide near real-time information. However, large uncertainties persist regarding burned areas, biomass affected, and emission factors. Recent increases in resolution have improved previous estimates of burned areas and aboveground biomass, while increasing the information content used to derive emission factors, complemented by airborne sensors deployed in the Tropics. To date, temperate forests, characterized by a lower fire incidence and stricter aerial surveillance restrictions near wildfires, have received less attention. In this study, we leveraged the distinctive fire season of 2022, which impacted Western European temperate forests, to investigate fire emissions monitored by the atmospheric tower network. We examined the role of soil smoldering combustion responsible for higher carbon emissions, locally reported by firefighters but not accounted for in global fire emission budgets. We assessed the CO/CO2 ratio released by major fires in the Mediterranean, Atlantic pine, and Atlantic temperate forests of France. Our findings revealed low Modified Combustion Efficiency (MCE) for the two Atlantic temperate regions, supporting the assumption of heavy smoldering combustion. This type of combustion was associated with specific fire characteristics, such as long-lasting thermal fire signals, and affected ecosystems encompassing needle leaf species, peatlands, and superficial lignite deposits in the soils. Thanks to high-resolution data (approximately 10 meters) on burned areas, tree biomass, peatlands, and soil organic matter, we proposed a revised combustion emission framework consistent with the observed MCEs. Our estimates revealed that 6.15 MtCO2 (± 2.65) were emitted, with belowground stock accounting for 51.75% (± 16.05). Additionally, we calculated a total emission of 1.14 MtCO (± 0.61), with 84.85% (± 3.75) originating from belowground combustion. As a result, the carbon emissions from the 2022 fires in France amounted to 7.95 MteqCO2 (± 3.62). These values exceed by 2-fold the generic GFAS global estimates of 4.18 MteqCO2 (CO and CO2). Fires represent 1.97% (± 0.89) of the country's annual carbon footprint, corresponding to a reduction of 30 % of the forest carbon sink this year. Consequently, we conclude that current European fire emissions estimates should be revised to account for soil combustion in temperate forests. We also recommend the use of atmospheric mixing ratios as an effective monitoring system of prolonged soil fires that have the potential to reignite in the following weeks. [ABSTRACT FROM AUTHOR]

The last US drone strike during its occupation of Afghanistan took place in Kabul on 29 August 2021. The target was identified as an Islamic State-Khorosan (ISIS-K) cell preparing to attack Hamid Karzai International Airport while the United States and its allies conducted a large-scale non-combatant evacuation and the Taliban advanced into the capital. Although the strike was the culmination of intensive aerial surveillance, it killed only innocent civilians. In comparing the official account of events provided by the Pentagon to explain the catastrophic mistake with an alternative narrative established by investigative reporters, it becomes clear that the strike was prompted by a performative series of assumptions and inferences that fastened on every observed action as suspicious and ultimately hostile. A further comparison with a US airstrike in Uruzgan on 21 February 2010 shows that this chain of misinterpretation and miscalculation has been a constant in civilian casualty incidents for many years. This prompts a series of reflections on the architecture of aerial violence and its implications for civilians caught up in the battlespaces of later modern war. [ABSTRACT FROM AUTHOR]

Multiple unmanned aerial vehicle (multi-UAV) systems have gained significant attention in applications, such as aerial surveillance and search and rescue missions. With the recent development of state-of-the-art multiagent reinforcement learning (MARL) algorithms, it is possible to train multi-UAV systems in collaborative and competitive environments. However, the inherent vulnerabilities of multiagent systems pose significant privacy and security risks when deploying general and conventional MARL algorithms. The presence of even a single Byzantine adversary within the system can severely degrade the learning performance of UAV agents. This work proposes a Byzantine-resilient MARL algorithm that leverages a combination of geometric median consensus and a robust state update model to mitigate, or even eliminate, the influence of Byzantine attacks. To validate its effectiveness and feasibility, the authors include a multi-UAV threat model, provide a guarantee of robustness, and investigate key attack parameters for multiple UAV navigation scenarios. Results from the experiments show that the average rewards during a Byzantine attack increased by up to 60% for the cooperative navigation scenario compared with conventional MARL techniques. The learning rewards generated by the baseline algorithms could not converge during training under these attacks, while the proposed method effectively converged to an optimal solution, proving its viability and correctness. [ABSTRACT FROM AUTHOR]

Remote sensing technologies have been increasingly crucial to support policy-makers in achieving their ecological strategies. The data provided by such technology can estimate the bioenergy source production rate and monitor deforestation. This work participates in the cause by contributing an aerial dataset and developing an intelligent tree-detection system usable for counting trees with the bioenergy potential. Low-altitude flying units have been vastly used for such a purpose due to their ability to capture highquality data from distant locations. Despite these potentials, collected images that compose a dataset are often characterized by imbalanced distribution among classes. The class disproportion can affect the overall model performance, as it severely deprives key features of under-represented classes. This study proposes datalevel approaches that adopt and extend prior sampling algorithms for object detection problems. The devised techniques try to reduce the number of redundant outputs obtained from sampling methods and reduce the iteration required to achieve the target imbalance ratio by employing a systematic flow. In such a process, the class distribution of an original dataset is used as a guideline for selecting candidates for subsequent processes. Our results show that the modified dataset can reduce the length of a training process shown by fewer iterations required to achieve the final metrics of its original dataset version and lower training losses in each iteration. Additionally, the modified dataset can improve the F-score (F1) and precision metric of object detection algorithm by up to 6%. [ABSTRACT FROM AUTHOR]

The number of wheat ears per unit area is crucial for assessing wheat yield, but automated wheat ear counting still faces significant challenges due to factors like lighting, orientation, and density variations. Departing from most static image analysis methodologies, this study introduces Wheat-FasterYOLO, an efficient real-time model designed to detect, track, and count wheat ears in video sequences. This model uses FasterNet as its foundational feature extraction network, significantly reducing the model's parameter count and improving the model's inference speed. We also incorporate deformable convolutions and dynamic sparse attention into the feature extraction network to enhance its ability to capture wheat ear features while reducing the effects of intricate environmental conditions. To address information loss during up-sampling and strengthen the model's capacity to extract wheat ear features across varying feature map scales, we integrate a path aggregation network (PAN) with the content-aware reassembly of features (CARAFE) up-sampling operator. Furthermore, the incorporation of the Kalman filter-based target-tracking algorithm, Observation-centric SORT (OC-SORT), enables real-time tracking and counting of wheat ears within expansive field settings. Experimental results demonstrate that Wheat-FasterYOLO achieves a mean average precision (mAP) score of 94.01% with a small memory usage of 2.87MB, surpassing popular detectors such as YOLOX and YOLOv7-Tiny. With the integration of OC-SORT, the composite higher order tracking accuracy (HOTA) and counting accuracy reached 60.52% and 91.88%, respectively, while maintaining a frame rate of 92 frames per second (FPS). This technology has promising applications in wheat ear counting tasks. [ABSTRACT FROM AUTHOR]

We propose an adaptive unmanned aerial vehicle (UAV)‐assisted object recognition algorithm for urban surveillance scenarios. For UAV‐assisted surveillance, UAVs are equipped with learning‐based object recognition models and can collect surveillance image data. However, owing to the limitations of UAVs regarding power and computational resources, adaptive control must be performed accordingly. Therefore, we introduce a self‐adaptive control strategy to maximize the time‐averaged recognition performance subject to stability through a formulation based on Lyapunov optimization. Results from performance evaluations on real‐world data demonstrate that the proposed algorithm achieves the desired performance improvements. [ABSTRACT FROM AUTHOR]

Copyright of Ingeniería (0121-750X) is the property of Ingenieria and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The accurate detection and recognition of human actions play a pivotal role in aerial surveillance, enabling the identification of potential threats and suspicious behavior. Several approaches have been presented to address this problem, but the limitation still remains in devising an accurate and robust solution. To this end, this paper presents an effective action recognition framework for aerial surveillance, employing the YOLOv8-Pose keypoints extraction algorithm and a customized sequential ConvLSTM (Convolutional Long Short-Term Memory) model for classifying the action. We performed a detailed experimental evaluation and comparison on the publicly available Drone Action dataset. The evaluation and comparison of the proposed framework with several existing approaches on the publicly available Drone Action dataset demonstrate its effectiveness, achieving a very encouraging performance. The overall accuracy of the framework on three provided dataset splits is 74%, 80%, and 70%, with a mean accuracy of 74.67%. Indeed, the proposed system effectively captures the spatial and temporal dynamics of human actions, providing a robust solution for aerial action recognition. [ABSTRACT FROM AUTHOR]

In Leaders of a Beautiful Struggle v. Baltimore Police Department, the Fourth Circuit Court of Appeals held that Aerial Investigation Research (AIR), Baltimore’s aerial surveillance program, violated the Fourth Amendment because it was not authorized by a warrant. AIR was constitutionally problematic, but not for the reason given by the Fourth Circuit. AIR, like many other technologically-enhanced policing programs that rely on closed-circuit television (CCTV), automated license plate readers and the like, involves the collection and retention of information about huge numbers of people. Because individualized suspicion does not exist with respect to any of these people’s information, an individual-specific warrant requirement can never be met by such a program. When police engage in suspicionless searches and seizures of the type exemplified by AIR, a different regulatory approach is needed, one that provides the protection against arbitrariness that the warrant process affords but does not require findings that specific people have violated the law. This Article argues that this regulatory alternative can be derived from administrative law principles. The logic of administrative law dictates that legislatures and agency rulemaking must be involved any time a policing agency wants to establish a program that will intentionally affect sizeable numbers of concededly innocent people. If administrative law principles applied, programs like AIR would not be permitted unless a legislature has delegated appropriate authority to the relevant police agency, implemented regulations have survived notice-and-comment and hard look judicial review, and the agency carried out the program in an even-handed fashion that minimizes discretion. At the same time, contrary to the holding in Leaders of a Beautiful Stuggle, if these requirements are met, the Fourth Amendment—at least the part of it requiring warrants and probable cause—would be irrelevant. [ABSTRACT FROM AUTHOR]

In aerial surveillance systems, achieving optimal object detection precision is of paramount importance for effective monitoring and reconnaissance. This article presents a novel approach to enhance object detection accuracy through the integration of Delaunay triangulation with multi-unmanned aerial vehicle (UAV) systems. The methodology involves positioning multiple UAVs at pre-specified locations using the Delaunay triangulation algorithm with performance of O (n log n). This is compared with the conventional single UAV approach at a near distance. Our findings reveal that the collaborative efforts of multiple UAVs, guided by Delaunay triangulation, significantly improves object detection accuracy, especially when compared to a single UAV operating in close proximity. This research employs advanced image processing techniques to identify objects in the area under surveillance. Results indicate a substantial enhancement in the collective surveillance capabilities of the multi-UAV system, demonstrating its efficacy in unconstrained scenarios. This research not only contributes to the optimization of aerial surveillance operations but also underscores the potential of spatially informed UAV networks for applications demanding heightened object detection accuracy. The integration of Delaunay triangulation with multi-UAV systems emerges as a promising strategy for advancing the capabilities of aerial surveillance in scenarios ranging from security and emergency response to environmental monitoring.

Aerial vehicle detection has significant applications in aerial surveillance and traffic control. The pictures captured by the UAV are characterized by many tiny objects and vehicles obscuring each other, significantly increasing the detection challenge. In the research of detecting vehicles in aerial images, there is a widespread problem of missed and false detections. Therefore, we customize a model based on YOLOv5 to be more suitable for detecting vehicles in aerial images. Firstly, we add one additional prediction head to detect smaller-scale objects. Furthermore, to keep the original features involved in the training process of the model, we introduce a Bidirectional Feature Pyramid Network (BiFPN) to fuse the feature information from various scales. Lastly, Soft-NMS (soft non-maximum suppression) is employed as a prediction frame filtering method, alleviating the missed detection due to the close alignment of vehicles. The experimental findings on the self-made dataset in this research indicate that compared with YOLOv5s, the mAP@0.5 and mAP@0.5:0.95 of YOLOv5-VTO increase by 3.7% and 4.7%, respectively, and the two indexes of accuracy and recall are also improved. [ABSTRACT FROM AUTHOR]

The phenomenal growth in the utilization of commercial unmanned aerial vehicles (UAVs) or drones leads to an urgent need for new approaches to ensure safety in the sky. Effective aerial surveillance requires patrolling swarms to react according to the various behaviors demonstrated by intruding swarms, but existing approaches are not practical when dealing with a large number of drones. Specifically, predicting the behaviors or planned paths of the intruding swarms is highly challenging as intruders may perform evasive strategies to avoid detection. Therefore, this work utilizes heuristic search strategies and investigates how various intruder behaviors affect the search performance. To investigate the search performance, a swarm versus swarm simulator is developed. Using the simulator, first, a comparative study is performed to evaluate how intruders' behaviors can affect the performance of the patrolling swarm. Subsequently, three approaches, including single-objective optimization, multi-objective optimization, and Lévy flight, are compared in terms of their detection performance in a bounded space. The results suggest that multi-objective optimization outperforms both single-objective optimization and Lévy flight-based approaches. Furthermore, our results show that intruders have a lower chance of being tracked when moving in a dense crowd, and this finding reaffirms the schooling behaviors of fish. In a specific simulation scenario, the total percentage of detection is above 90%. However, the detection percentage is highly related to other factors such as search space, number of patrolling UAVs, and the intruders' behaviors. [ABSTRACT FROM AUTHOR]

In this paper, a novel bat algorithm with an asymmetrical weighed variational method (AWVM-BA) is proposed. The proposed algorithm employs the BA with a point-to-point modified asymmetrical variation above the three-dimensional flying region, which treats the space as sets of geodesics in a second order Euclidean weighed warped space. Mutation and the local selection procedure can be avoided at the same time, which solves the problem of a local optimum in concave regions. As shown in the results, the proposed algorithm does not have much impact on the calculation complexity and time in convex regions. It can greatly reduce the calculation time and avoid local optimization in concave regions. The disadvantage of the proposed algorithm is that the iteration number increases comparatively faster with the increase in the deviation of the wind speed. Therefore, it requires a higher hardware calculation ability. [ABSTRACT FROM AUTHOR]

New approaches are required to undertake the substantial task of monitoring ongoing fishing activity in marine conservation areas to ensure conservation goals are achieved. To address this need, we applied previously developed, yet currently underused, vessel tracking methods based on Automatic Identification System (AIS) and aerial surveillance ("flyovers") to Canada's Pacific marine conservation areas from 2012 to 2019. We used satellite and terrestrial‐based AIS receivers and flyover‐based visual observations to estimate illegal and legal fishing activity after 185 conservation area (CA) enactments (i.e., static, geographically defined areas with fishing regulations). We compared the effectiveness in detecting fishing activity between the AIS‐ and flyover‐based methods, and used the latter to determine that 93% of vessels were actively fishing in CAs without AIS. The AIS‐based method still detected 3303 h of fishing in CAs after enactment, and both methods estimated 22%–24% of fishing activity in CAs was illegal. The application of these methods also shed light on the complexity of fishing regulations across CAs (i.e., varying and CA‐specific restrictions). This highlighted the need to better align vessel tracking fishing gear classifications with CA regulation specifications, and conversely to simplify regulations (e.g., no‐take), for more accurate monitoring and evaluation moving forward. [ABSTRACT FROM AUTHOR]

In 2020, the Baltimore Police Department ("BPD") resurrected its dragnet aerial surveillance initiative--the Aerial Investigation Research ("AIR") program. Using a plane outfitted with high-definition cameras, BPD was able to observe the daily movements of hundreds of thousands of Baltimore residents. Sophisticated technology such as the AIR program poses significant conflict with Fourth Amendment rights guaranteeing protection against unreasonable searches. Although the Supreme Court already ruled on the constitutionality of aerial surveillance in the 1980s, the advanced capabilities of new aerial surveillance render these decisions inapplicable in modern society. Instead, the framework presented by the Supreme Court's decision in Carpenter v. United States provides a more workable test for considering cases of mass aerial surveillance. This Note argues that Carpenter's privacy-protective approach to new technologies provides a better lens for analyzing modern mass aerial surveillance. This Note uses the AIR program and the Fourth Circuit's decision in Leaders of a Beautiful Struggle v. Baltimore Police Department as an emblematic example of how Carpenter should be applied to future instances of mass aerial surveillance. [ABSTRACT FROM AUTHOR]

One of the United Nations (UN) Sustainable Development Goals is climate action (SDG-13), and wildfire is among the catastrophic events that both impact climate change and are aggravated by it. In Australia and other countries, large-scale wildfires have dramatically grown in frequency and size in recent years. These fires threaten the world's forests and urban woods, cause enormous environmental and property damage, and quite often result in fatalities. As a result of their increasing frequency, there is an ongoing debate over how to handle catastrophic wildfires and mitigate their social, economic, and environmental repercussions. Effective prevention, early warning, and response strategies must be well-planned and carefully coordinated to minimise harmful consequences to people and the environment. Rapid advancements in remote sensing technologies such as ground-based, aerial surveillance vehicle-based, and satellite-based systems have been used for efficient wildfire surveillance. This study focuses on the application of space-borne technology for very accurate fire detection under challenging conditions. Due to the significant advances in artificial intelligence (AI) techniques in recent years, numerous studies have previously been conducted to examine how AI might be applied in various situations. As a result of its special physical and operational requirements, spaceflight has emerged as one of the most challenging application fields. This work contains a feasibility study as well as a model and scenario prototype for a satellite AI system. With the intention of swiftly generating alerts and enabling immediate actions, the detection of wildfires has been studied with reference to the Australian events that occurred in December 2019. Convolutional neural networks (CNNs) were developed, trained, and used from the ground up to detect wildfires while also adjusting their complexity to meet onboard implementation requirements for trusted autonomous satellite operations (TASO). The capability of a 1-dimensional convolution neural network (1-DCNN) to classify wildfires is demonstrated in this research and the results are assessed against those reported in the literature. In order to enable autonomous onboard data processing, various hardware accelerators were considered and evaluated for onboard implementation. The trained model was then implemented in the following: Intel Movidius NCS-2 and Nvidia Jetson Nano and Nvidia Jetson TX2. Using the selected onboard hardware, the developed model was then put into practice and analysis was carried out. The results were positive and in favour of using the technology that has been proposed for onboard data processing to enable TASO on future missions. The findings indicate that data processing onboard can be very beneficial in disaster management and climate change mitigation by facilitating the generation of timely alerts for users and by enabling rapid and appropriate responses. [ABSTRACT FROM AUTHOR]

The use of Unmanned Aerial Vehicles (UAVs) has expanded rapidly in ecological conservation and agriculture, with a growing literature describing their potential applications in global health efforts including vector control. Vector-borne diseases carry severe public health and economic impacts to over half of the global population yet conventional approaches to the surveillance and treatment of vector habitats is typically laborious and slow. The high mobility of UAVs allows them to reach remote areas that might otherwise be inaccessible to ground-based teams. Given the rapidly expanding examples of these tools in vector control programmes, there is a need to establish the current knowledge base of applications for UAVs in this context and assess the strengths and challenges compared to conventional methodologies. This review aims to summarize the currently available knowledge on the capabilities of UAVs in both malaria control and in vector control more broadly in cases where the technology could be readily adapted to malaria vectors. This review will cover the current use of UAVs in vector habitat surveillance and deployment of control payloads, in comparison with their existing conventional approaches. Finally, this review will highlight the logistical and regulatory challenges in scaling up the use of UAVs in malaria control programmes and highlight potential future developments. [ABSTRACT FROM AUTHOR]

The article is devoted to the relevant direction of acoustic detection of UAVs, in connection with the increasing demands on aerial surveillance and reconnaissance systems. The physical fields that can be detected by a UAV detection device are very diverse: electromagnetic, optical, and acoustic. In turn, the acoustic field is characterized by a band of noise-like signals that can be interpreted as useful and interfering. Moreover, a wide range of UAVs is not always subject to detection. Therefore, it would be desirable to obtain an acoustic device that could provide signal variability over time. In addition, the properties of the acoustic field include spatial selectivity - the direction of arrival of the useful signal. There are also spectral features due to the fact that the signal we are considering is broadband. Therefore, parallel use of several detection paths is recommended to increase reliability. In this regard, it is expedient to consider a device that implements the principles of parallel and sequential spectral analysis. The range calculations should be carried out according to the main level of acoustic localization with subsequent correction of the energy range of action with the features of atmospheric distribution of sound velocity. Thus, the above provisions and the general state of development of UAV noise direction finding devices indicate that the proposed work is useful and relevant in a wide range of applications. The purpose of the article is to expand methods of UAV detection using spectral analysis tools in conditions of broadband interference and signals. The scientific novelty of the proposed work lies in the use of acoustic localization methodology for the task of UAV noise direction finding in conditions of isotropic and anisotropic acoustic interference. As a result of experiments conducted in natural and laboratory conditions, it was determined that the detection path based on mutual spectrum was the most efficient and informative among the detection paths based on intensity, mutual spectrum, and narrowband spectrum. The predicted detection range of UAVs was calculated, which includes both geometric and energetic distances. The structure, operating principle, and display of measurement results in laboratory and natural conditions were implemented using the LabView software package. The results of this work may help in the development of an acoustic air noise localization system that implements the principles of detecting noise-like signals using spectral and correlation methods and can be applied as part of a multisensor complex for detecting and direction finding of UAVs. [ABSTRACT FROM AUTHOR]

Abstract New approaches are required to undertake the substantial task of monitoring ongoing fishing activity in marine conservation areas to ensure conservation goals are achieved. To address this need, we applied previously developed, yet currently underused, vessel tracking methods based on Automatic Identification System (AIS) and aerial surveillance (“flyovers”) to Canada's Pacific marine conservation areas from 2012 to 2019. We used satellite and terrestrial‐based AIS receivers and flyover‐based visual observations to estimate illegal and legal fishing activity after 185 conservation area (CA) enactments (i.e., static, geographically defined areas with fishing regulations). We compared the effectiveness in detecting fishing activity between the AIS‐ and flyover‐based methods, and used the latter to determine that 93% of vessels were actively fishing in CAs without AIS. The AIS‐based method still detected 3303 h of fishing in CAs after enactment, and both methods estimated 22%–24% of fishing activity in CAs was illegal. The application of these methods also shed light on the complexity of fishing regulations across CAs (i.e., varying and CA‐specific restrictions). This highlighted the need to better align vessel tracking fishing gear classifications with CA regulation specifications, and conversely to simplify regulations (e.g., no‐take), for more accurate monitoring and evaluation moving forward.

In recent years, due to the rapid development of Internet of things (IoTs), various physical things (objects) in IoTs are smart enough to make their own decisions without the involvement of humans. The smart devices embedded in a drone can sense, collect, and transmit real-time data back to the controller from a designated environment via wireless communication technologies. The mobility, flexibility, reliability and energy efficiency of drones makes them more widely used in IoT environments such as commercial, military, entertainment applications, traffic surveillance and aerial photography. In a generalized IoD architecture, we have communications among the drones in a flying zone, among the drones and the control server, and also among the drones and authorized user. IoD still has many critical issues that need to be addressed, such as data access being carried out through a public channel and battery operated drones. To address these concerns in IoD communications, in this paper, an efficient authentication and secure communication scheme with privacy preservation is proposed and it only uses secure one-way hash function and bitwise XOR operations when control server, drone and user mutually authenticate each other. After the successful authentication, both IoD-based participants can agree on a common session key to secure the subsequent communication messages. The widely accepted ProVerif and BAN logic analysis have been used to assure that the proposed scheme is provably secure against existing well-known security attacks and ensures privacy. Finally, a comparative analysis is presented to demonstrate the proposed scheme preserves efficiency when compared to existing competitive schemes. [ABSTRACT FROM AUTHOR]

The Blockchain concept has erupted from decentralized digital currency world and has reached a high penetration in other areas where the certification of transactions and its immutability is required. The experience on elevated security to event time driven data assertion was transferred from the digital currency to the data driven enterprise world. In applications were highly regulated and certified data intensive systems are needed, Blockchain becomes a strong solution. Areas like the management of the lifecycle of reusable rockets, aeronautics, aerial surveillance, aviation safety, wind turbine and solar farms, electric grids and others, the amount of generated data to be registered and certified is considerable. Many implemented Blockchain solutions tend to register and add to the Blockchain, large amounts of data that reduce the Blockchain management and usability. This work proposes a Hybrid Pointer Based Blockchain solution to overcome the issues, by integrating several parallel services that work side by side with distributed, secured and certified peer node systems that guarantee the data immutability and interconnection to the different blockchains that interact with each other. The proposed Blockchain solution presented in this work interacts with the peer nodes edge services, from software services to hardware generated data and AI assessments. [ABSTRACT FROM AUTHOR]

Image deraining aims to restore the clean scenes of rainy images, which facilitates a number of outdoor vision systems, such as autonomous driving, unmanned aerial vehicles and surveillance systems. This paper proposes a high-resolution detail-recovering image deraining network (HDRD-Net) to effectively remove rain streaks and recover lost details, as well as improving the quality of derained images. HDRD-Net consists of three sub-networks. First, we combine the residual network and Squeeze-and-Excitation block for rain streak removal. Second, we integrate the Structure Detail Context Aggregation block into the detail-recovering network to extract detail features form rainy images. Third, a dual super-resolution reconstruction network is utilized to enhance the quality of derained images. In addition, we extend the Rain100 dataset by incorporating low-resolution rainy images to construct a new Rain100++ dataset for high-resolution image deraining. Experimental results on several datasets show that HDRD-Net outperforms state-of-the-art methods in terms of rain removal, detail preservation and visual quality. [ABSTRACT FROM AUTHOR]

The occurrence of litter in natural areas is nowadays one of the major environmental challenges. The uncontrolled dumping of solid waste in nature not only threatens wildlife on land and in water, but also constitutes a serious threat to human health. The detection and monitoring of areas affected by litter pollution is thus of utmost importance, as it allows for the cleaning of these areas and guides public authorities in defining mitigation measures. Among the methods used to spot littered areas, aerial surveillance stands out as a valuable alternative as it allows for the detection of relatively small such regions while covering a relatively large area in a short timeframe. In this study, remotely piloted aircraft systems equipped with multispectral cameras are deployed over littered areas with the ultimate goal of obtaining classification maps based on spectral characteristics. Our approach employs classification algorithms based on random forest approaches in order to distinguish between four classes of natural land cover types and five litter classes. The obtained results show that the detection of various litter types is feasible in the proposed scenario and the employed machine learning algorithms achieve accuracies superior to 85% for all classes in test data. The study further explores sources of errors, the effect of spatial resolution on the retrieved maps and the applicability of the designed algorithm to floating litter detection. [ABSTRACT FROM AUTHOR]

The accurate detection and recognition of human actions play a pivotal role in aerial surveillance, enabling the identification of potential threats and suspicious behavior. Several approaches have been presented to address this problem, but the limitation still remains in devising an accurate and robust solution. To this end, this paper presents an effective action recognition framework for aerial surveillance, employing the YOLOv8-Pose keypoints extraction algorithm and a customized sequential ConvLSTM (Convolutional Long Short-Term Memory) model for classifying the action. We performed a detailed experimental evaluation and comparison on the publicly available Drone Action dataset. The evaluation and comparison of the proposed framework with several existing approaches on the publicly available Drone Action dataset demonstrate its effectiveness, achieving a very encouraging performance. The overall accuracy of the framework on three provided dataset splits is 74%, 80%, and 70%, with a mean accuracy of 74.67%. Indeed, the proposed system effectively captures the spatial and temporal dynamics of human actions, providing a robust solution for aerial action recognition.

The last two decades have seen an incessant growth in the use of Unmanned Aerial Vehicles (UAVs) equipped with HD cameras for developing aerial vision-based systems to support civilian and military tasks, including land monitoring, change detection, and object classification. To perform most of these tasks, the artificial intelligence algorithms usually need to know, a priori, what to look for, identify. or recognize. Actually, in most operational scenarios, such as war zones or post-disaster situations, areas and objects of interest are not decidable a priori since their shape and visual features may have been altered by events or even intentionally disguised (e.g., improvised explosive devices (IEDs)). For these reasons, in recent years, more and more research groups are investigating the design of original anomaly detection methods, which, in short, are focused on detecting samples that differ from the others in terms of visual appearance and occurrences with respect to a given environment. In this paper, we present a novel two-branch Generative Adversarial Network (GAN)-based method for low-altitude RGB aerial video surveillance to detect and localize anomalies. We have chosen to focus on the low-altitude sequences as we are interested in complex operational scenarios where even a small object or device can represent a reason for danger or attention. The proposed model was tested on the UAV Mosaicking and Change Detection (UMCD) dataset, a one-of-a-kind collection of challenging videos whose sequences were acquired between 6 and 15 m above sea level on three types of ground (i.e., urban, dirt, and countryside). Results demonstrated the effectiveness of the model in terms of Area Under the Receiving Operating Curve (AUROC) and Structural Similarity Index (SSIM), achieving an average of 97.2% and 95.7%, respectively, thus suggesting that the system can be deployed in real-world applications. [ABSTRACT FROM AUTHOR]

With the rapid increase of vehicles in recent years, traffic surveillance becomes a crucial issue of traffic management. Since the traditional static sensor-based surveillance system can only passively monitor traffic, this paper considers the usage of unmanned aerial vehicles (UAVs), which can proactively conduct traffic surveillance thanks to the excellent mobility of UAVs. Specifically, we consider the navigation problem of a network of UAVs to effectively monitor a group of ground targets which move along a curvy road. A surveillance optimization problem is stated, and a distributed navigation algorithm for the UAV network is developed. It is proved that the proposed algorithm is locally optimal. Simulations confirm the effectiveness of the proposed navigation algorithm. [ABSTRACT FROM AUTHOR]

The scientific and technological progress registered in the last decades has contributed to the development of radars with supreme radar detection abilities to better detect the air attack means of the enemy. These means, in turn, have contributed to the improvement of the parameters of the airborne surveillance systems in order to detect and to counter aerial threats. The structural and functional dynamics of the aerial surveillance systems have pursued continuous adaptation to the complexity of the battlefield environment in modern warfare, ensuring the information necessary for the coherent and effective engagement of forces in the conduct of military operations. [ABSTRACT FROM AUTHOR]

This article discusses a recently published book titled "Australian perspectives on global air and space power: past, present, future." The book provides insights into Australia's air and space power capabilities and their historical development. Divided into five parts, the book covers topics such as Australia's role in global conflicts, the evolution of the Royal Australian Air Force (RAAF), and the future vulnerabilities and innovations in air and space power. While the book offers valuable insights, it is noted that the structure of the book could be improved, and there is a lack of diversity in perspectives, with only five out of 20 authors being women. Nonetheless, the book provides useful criticisms and recommendations for Australian policy-makers to consider in shaping the country's strategic direction. [Extracted from the article]

Goal-guided behavior and destination-directed motion appear in a wide range of human activities and physical processes. Taking advantage of such predictive information can produce better system models and state estimates. This paper focuses on modeling and filtering issues of linear dynamic systems with linear destination constraints. We examine deficiencies of the existing destination constrained (DC) estimation methods. Basically, they resort to post-treatment by imposing destination constraints on updated states only. Viewing destination constraints as an attribute implicit of the state evolution, we propose to incorporate the destination constraints accordingly, particularly on the predictive distribution of the whole state sequence. We construct a congruous DC dynamic model by sufficiently refining the relaxed dynamics with the destination constraint using the state augmentation technique, and analyze its characterization and properties. Next, for the proposed DC model, we develop an optimal DC state estimator and describe its properties. Finally, in the context of aerial surveillance, the superiority of the proposed estimator to existing DC estimators is verified by simulation results, and the effectiveness of the proposed DC dynamic model is demonstrated using real data. [ABSTRACT FROM AUTHOR]

This article examines the violent clashes between Hamas and Israel along the Gaza Fence (30 March 2018–27 December 2019) from a psychological operations (PSYOP) perspective. It shows how Hamas managed, through a skilful combination of mass riots, media manipulation, and quick adaptation to changing circumstances to subvert the strategic priorities of the Israel Defence Forces (IDF), wear down Israeli morale, and erode Israel's sovereignty in its southern region – all this while deterring Israel from launching a large-scale military operation in Gaza. As such, the Gaza Fence clashes provide an example of a PSYOP-based strategy that can be applied to other border conflict zones, such as Morocco, Saudi Arabia, Mexico, and Islamist insurrections. [ABSTRACT FROM AUTHOR]

This letter addressesa path planning problem for a team of mobile robots, such as unmanned aerial vehicles, patrolling a ground region for surveillance. An effective navigation algorithm is developed and proved to be asymptotically optimal in the sense that the ratio of the revisit period of the algorithm and the minimum possible revisit period converges to one as the area of the region tends to infinity. Illustrative examples and comparisons with an existing method show the efficiency of the developed approach. [ABSTRACT FROM AUTHOR]

The unmanned aerial vehicle (UAV) is one of the mobile robots which has grown rapidly in popularity in recent years. UAVs have been used in various activities to convey important information on the aerial transportation system. However, an application to get real-time information from UAVs remains a challenging task. Therefore, this paper presents an integration system to optimise the use of UAVs for aerial surveillance. The proposed system explains the design and implementation a UAV system which consists of on-board and ground stations. The on-board system has the function to send UAV flight data, send aerial images and carry items using a gripper which equipped with sensors to detect obstacles. The ground station has the function to control UAV flights, receive and display UAV flight data and aerial images, display the attitude of the UAV and send commands to move the camera and gripper. Flight controllers in this system use non-linear complementary filter on SO(3) to estimate the attitude of the UAV and proportional-integral (PI) controller to stabilise the UAV flight. By providing the real-time acquisition data of the UAV, we believe this system can be a useful tool for many implementations using UAV. [ABSTRACT FROM AUTHOR]