No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Boosting Aircraft Monitoring and Security through Ground Surveillance Optimization with YOLOv9
... Its deployment in surveillance systems ensures that even the subtlest anomalies are detected, reducing the likelihood of security breaches. The integration of recent versions of YOLO such as YOLOv8 and YOLOv9 into security frameworks not only streamlines operations but also ensures a proactive approach to threat management, keeping public and private spaces safer across the globe [171,172]. ...
... Recent studies have significantly leveraged advanced YOLO models to enhance surveillance and security across various domains. Bakirci and Bayraktar [171] discussed optimizing ground surveillance for aircraft monitoring using YOLOv9, highlighting its efficacy in real-time security applications. Similarly, Chakraborty et al. [173] explored a multi-model approach for violence detection, incorporating YOLOv8 to improve public safety through automated surveillance. ...
This review systematically examines the progression of the You Only Look Once (YOLO) object detection algorithms from YOLOv1 to the recently unveiled YOLOv10. Employing a reverse chronological analysis, this study examines the advancements introduced by YOLO algorithms, beginning with YOLOv10 and progressing through YOLOv9, YOLOv8, and subsequent versions to explore each version's contributions to enhancing speed, accuracy, and computational efficiency in real-time object detection. The study highlights the transformative impact of YOLO across five critical application areas: automotive safety, healthcare, industrial manufacturing, surveillance, and agriculture. By detailing the incremental technological advancements in subsequent YOLO versions, this review chronicles the evolution of YOLO, and discusses the challenges and limitations in each earlier versions. The evolution signifies a path towards integrating YOLO with multimodal, context-aware, and General Artificial Intelligence (AGI) systems for the next YOLO decade, promising significant implications for future developments in AI-driven applications.
Keywords: You Only Look Once, YOLOv10 to YOLOv1, CNN, Deep learning, Object detection, Real-time object detection, Artificial intelligence, Computer vision, Healthcare, Autonomous Vehicles, Industrial manufacturing, Surveillance, Agriculture, YOLOv10, YOLOv9, YOLOv8, YOLOv7, YOLOv6, YOLOv5, YOLOv4, YOLOv3, YOLOv2, YOLO
... Another significant application of LEO satellites is in Earth observation and environmental monitoring [21]. Equipped with advanced sensors and imaging technologies, LEO satellites capture high-resolution imagery of the Earth's surface, atmosphere, and oceans [22,23]. These satellites facilitate a wide range of applications, including weather forecasting, climate monitoring, disaster management, agriculture, and urban planning [24,25]. ...
Efficient management of operations in near space, just beyond the Earth’s atmosphere, relies on the precise control of satellites positioned relatively close to our planet. Satellite systems, serving critical functions in telecommunications, observation, exploration, and more, have demonstrated their prowess as a transformative technology, consistently delivering high-precision data over numerous years. Among satellite systems, Low Earth Orbit (LEO) technology is gaining prominence due to its advantages, including lower power requirements for transmission, reduced propagation delays, and heightened coverage for polar regions. Achieving optimal efficiency from LEO satellites necessitates a thorough understanding of their fundamental orbital parameters and precise control over them. This study explores the orbital analysis and Earth coverage considerations of LEO satellites, scrutinizing orbital parameters in detail to compute coverage areas across various scenarios. Through this investigation, the potential benefits of data exchange with ground stations facilitated by LEO satellites are explored. In addition, the implications are discussed regarding the adjustment of data exchange topologies according to geographical locations and country borders.
The intelligent crack detection method is an important guarantee for the realization of intelligent operation and maintenance, and it is of great significance to traffic safety. In recent years, the recognition of road pavement cracks based on computer vision has attracted increasing attention. With the technological breakthroughs of general deep learning algorithms in recent years, detection algorithms based on deep learning and convolutional neural networks have achieved better results in the field of crack recognition. In this paper, deep learning is investigated to intelligently detect road cracks, and Faster R-CNN and Mask R-CNN are compared and analyzed. The results show that the joint training strategy is very effective, and we are able to ensure that both Faster R-CNN and Mask R-CNN complete the crack detection task when trained with only 130+ images and can outperform YOLOv3. However, the joint training strategy causes a degradation in the effectiveness of the bounding box detected by Mask R-CNN.
There are many solutions to prevent the spread of the COVID-19 virus and one of the most effective solutions is wearing a face mask. Almost everyone is wearing face masks at all times in public places during the coronavirus pandemic. This encourages us to explore face mask detection technology to monitor people wearing masks in public places. Most recent and advanced face mask detection approaches are designed using deep learning. In this article, two state-of-the-art object detection models, namely, YOLOv3 and faster R-CNN are used to achieve this task. The authors have trained both the models on a dataset that consists of images of people of two categories that are with and without face masks. This work proposes a technique that will draw bounding boxes (red or green) around the faces of people, based on whether a person is wearing a mask or not, and keeps the record of the ratio of people wearing face masks on the daily basis. The authors have also compared the performance of both the models i.e., their precision rate and inference time.
As the fastest growing segment of aviation, unmanned aerial systems (UAS) continue to increase in number, technical complexity and capabilities. Numerous civilian and commercial uses are drastically transforming civil protection, asset delivery, commercial and entertaining activities. However, UAS pose significant challenges in terms of safety, security and privacy within society. An increasing phenomenon, nowadays, is drone-related incidents near airport facilities, which are expected to proliferate in frequency, complexity and severity, as drones become larger and more powerful. Critical infrastructures need to be protected from such aerial attacks, through effective counteracting technologies, risk management and resilience plans. In this paper, we present a survey of drone incidents near airports and a literature review of sensor technologies, able to prevent, detect, identify and mitigate rogue drones. We exhibit the benefits and limitations of available counter-drone technologies (C-UAS); however, defending airports against misused drone activity is a hard problem. Therefore, we analyze three realistic attack scenarios from malicious drones and propose an effective C-UAS protection plan for each case. We discuss applicability limitations of C-UAS in the aviation context and propose a resilience action plan for airport stakeholders for defending against airborne threats from misused drones.
Face detection is one of the important tasks of object detection. Typically detection is the first stage of pattern recognition and identity authentication. In recent years, deep learning-based algorithms in object detection have grown rapidly. These algorithms can be generally divided into two categories, i.e., two-stage detector like Faster R-CNN and one-stage detector like YOLO. Although YOLO and its varieties are not so good as two-stage detectors in terms of accuracy, they outperform the counterparts by a large margin in speed. YOLO performs well when facing normal size objects, but is incapable of detecting small objects. The accuracy decreases notably when dealing with objects that have large-scale changing like faces. Aimed to solve the detection problem of varying face scales, we propose a face detector named YOLO-face based on YOLOv3 to improve the performance for face detection. The present approach includes using anchor boxes more appropriate for face detection and a more precise regression loss function. The improved detector significantly increased accuracy while remaining fast detection speed. Experiments on the WIDER FACE and the FDDB datasets show that our improved algorithm outperforms YOLO and its varieties.
In view of the lack of feature complementarity between the feature layers of Single Shot MultiBox Detector (SSD) and the weak detection ability of SSD for small objects, we propose an improved SSD object detection algorithm based on Dense Convolutional Network (DenseNet) and feature fusion, which is called DF-SSD. On the basis of SSD, we design the feature extraction network DenseNet-S-32-1 with reference to the dense connection of DenseNet, and replace the original backbone network VGG-16 of SSD with DenseNet-S-32-1 to enhance the feature extraction ability of the model. In the part of multi-scale detection, a fusion mechanism of multi-scale feature layers is introduced to organically combine low-level visual features and high-level semantic features in the network structure. Finally, a residual block is established before the object prediction to further improve the model performance. We train the DF-SSD model from scratch. The experimental results show that our model DF-SSD with 300 × 300 input achieves 81.4% mAP, 79.0% mAP, and 29.5% mAP on PASCAL VOC 2007, VOC 2012, and MS COCO datasets, respectively. Compared with SSD, the detection accuracy of DF-SSD on VOC 2007 is improved by 3.1% mAP. DF-SSD requires only 1/2 parameters to SSD and 1/9 parameters to Faster RCNN. We inject more semantic information into DF-SSD, which makes it have advanced detection effect on small objects and objects with specific relationships.
With the emergence and development of unmanned aerial vehicles (UAVs), different sensors have become more miniaturized and intelligent. UAVs equipped with various sensors are now an important approach for acquiring spatial data. Many advantages, such as low cost, short revisiting cycle, flexibility and high precision, have made UAVs powerful tools in geological, agricultural, ecological and forestry growth monitoring, as well as evaluation. Now, UAVs are a hotspot in scientific research. Their application in mining areas (MA), although still in its infancy, is developing rapidly in terms of speed, scale and service scope. This research examines aspects such as UAV platforms, different sensors and their application fields, as well as reviewing the advances of scientific research in MA at the present time. By combining current research and the functions of multiple sensors, an application framework for UAV monitoring in MA is constructed. Finally, the challenge and prospects for the development of UAVs and sensors are also considered. This research hopes to provide a technical reference, expanding the knowledge and recognition of UAV monitoring in MA, as well as an assessment of applications in mining, reclamation and environment.
This study offers a swarm system solution of a fully autonomous electric vertical take-off and landing (eVTOL) rotary wing unmanned aerial vehicles (UAV) providing optimum level of telecommunication service, communication and formation skills, casualty detection, and transportation in a natural disaster scenario in a region with areas where GPS data is corrupted. It is ensured that the swarm UAV system, which follows the guide UAV in the disaster area by taking different formations and maintains these formations in case of GPS interruptions, makes the necessary observations through embedded cameras. Moreover, in line with the decisions to be made by the system, it provides telecommunication services to as many users as possible for as long as possible with its mobile base stations and transporting the injured to suitable regions. In order to provide information to users with smart devices that support IoT, necessary information and services can be transferred to users via connector UAVs by establishing a connection between the ground station and swarm UAVs. A secure communication network is provided in response to security risks that may occur while the UAVs in the swarm communicate throughout the mission. In addition to the system working together in different formations and broken GPS situations throughout the mission, communication limits are reduced in the insecure area between the swarm and the connector UAV, where communication cannot be achieved, and the unsafe interval is minimized.
This study covers the avionics system design for an unmanned combat aerial vehicle (UCAV) that can successfully detect and lock down rival unmanned aerial vehicle targets as many times as possible in air-to-air combat. With the artificial intelligence (AI) supported development board and high resolution/wide-angle camera on it, easy detection of competitor systems is provided. The captured images and flight data are processed with the AI-algorithm working on the developer kit with 48 tensor cores on it. Moreover, flight telemetry data is transmitted to the ground station at a range of 40 km, end-to-end encrypted and with low latency. Through 2.4 GHz radio frequency control, manual control can also be performed in an encrypted way and at a sufficient distance. Designed as a hexacopter, the UCAV can also avoid locking up of counter-unmanned systems with its high maneuverability. As a result of the proper design of the avionics and electrical system architecture, it can perform different tasks such as snapshot and data transfer, as well as being able to fly fully autonomously.
Hazards potentially affect the safety of people on construction sites include falls from heights (FFH), trench and scaffold collapse, electric shock and arc flash/arc blast, and failure to use proper personal protective equipment. Such hazards are significant contributors to accidents and fatalities. Computer vision has been used to automatically detect safety hazards to assist with the mitigation of accidents and fatalities. However, as safety regulations are subject to change and become more stringent prevailing computer vision approaches will become obsolete as they are unable to accommodate the adjustments that are made to practice. This paper integrates computer vision algorithms with ontology models to develop a knowledge graph that can automatically and accurately recognise hazards while adhering to safety regulations, even when they are subjected to change. Our developed knowledge graph consists of: (1) an ontological model for hazards: (2) knowledge extraction; and (3) knowledge inference for hazard identification. We focus on the detection of hazards associated with FFH as an example to illustrate our proposed approach. We also demonstrate that our approach can successfully detect FFH hazards in varying contexts from images.
Technology has brought great benefits to human beings and has served to improve the quality of life and carry out great discoveries. However, its use can also involve many risks. Examples include mobile devices, digital cameras and video surveillance cameras, which offer excellent performance and generate a large number of images and video. These files are generally shared on social platforms and are exposed to any manipulation, compromising their authenticity and integrity. In a legal process, a manipulated video can provide the necessary elements to accuse an innocent person of a crime or to exempt a guilty person from criminal acts. Therefore, it is essential to create robust forensic methods, which will strengthen the justice administration systems and thus make fair decisions. This paper presents a novel forensic technique to detect the post-processing of digital videos with MP4, MOV and 3GP formats. Concretely, detect the social platform and editing program used to execute possible manipulation attacks. The proposed method is focused on supervised machine learning techniques. To achieve our goal, we take advantage that the social platforms and editing programs, execute filtering and compression processes on the videos when they are shared or manipulated. The result of these transformations leaves a characteristic pattern in the videos that allow us to detect the social platform or editing program efficiently. Three phases are involved in the method: 1) Dataset preparation; 2) data features extraction; 3) Supervised model creation. To evaluate the scalability of the technique in real scenarios, we used a robust, heterogeneous and far superior dataset than that used in the literature.
YOLOv9: learning what you want to learn using programmable gradient information
- C Y Wang
- I H Yeh
- H Y M Liao