Related references
Note: Only part of the references are listed.
Article
Computer Science, Artificial Intelligence
Zhiyong An et al.
Summary: The low reliability of feature and tracking box detection is a problem in visual object tracking. This study proposes a robust tracking method using dynamic feature weight selection to address the issues of complex scenes and tracking box adaptability.
APPLIED INTELLIGENCE
(2023)
Review
Remote Sensing
Muhammad Yeasir Arafat et al.
Summary: In recent years, there has been increasing interest in unmanned aerial vehicles (UAVs), also known as drones, in both academia and industries. The advancements in UAV technologies, including artificial intelligence, component miniaturization, and computer vision, have made them more affordable and accessible for various applications and services. The integration of computer vision with UAVs has enabled them to perform autonomous operations in terms of visual navigation, localization, and obstacle avoidance. However, their limited ability to navigate in GPS-blind environments has become a challenge. Visual-based approaches using cheaper and more flexible visual sensors have shown advantages in UAV navigation, particularly due to the rapid development of computer vision. This study aims to provide a comprehensive review of vision-based UAV navigation techniques, categorize and extensively review existing techniques, compare them qualitatively, and discuss open issues and research challenges.
Article
Engineering, Electrical & Electronic
Kaixuan Gao et al.
Summary: By constructing CAPR images and using the SSQ-Net deep learning model and robustness enhancement method, this study improves the accuracy and robustness of CCUAV positioning in challenging environments such as urban canyons, by exploiting multipath effects and interference instead of considering them as detriments.
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS
(2023)
Article
Automation & Control Systems
Nasser Gyagenda et al.
Summary: This paper presents an account of GNSS-independent navigation solutions for UAVs and evaluates the components of navigation including perception, localization, and motion planning. The review results show that only 16% of the research proposed full navigation solutions, while the rest focused on individual components. In addition to the navigation solutions, this paper also contributes with an adapted UAV classification scheme, technology maturity assessment, and analysis of integrity monitoring frameworks.
ROBOTICS AND AUTONOMOUS SYSTEMS
(2022)
Article
Environmental Sciences
Chuan Xu et al.
Summary: The study introduces a deep learning-based method for matching multiview satellite and UAV images, with the innovation of a joint descriptor to address differences between heterologous space-sky images, achieving better matching accuracy and efficiency.
Article
Engineering, Aerospace
Kan Ren et al.
Summary: This paper proposes a quality-aware template matching method based on scale-adaptive deep convolutional features to match remote sensing images taken by an unmanned aerial vehicle (UAV) with satellite remote sensing images with geolocation information, in order to determine the specific geographic location of the target object captured by the UAV. Experimental results demonstrate the effectiveness and superiority of the method.
CHINESE JOURNAL OF AERONAUTICS
(2022)
Review
Geochemistry & Geophysics
Changhong Fu et al.
IEEE GEOSCIENCE AND REMOTE SENSING MAGAZINE
(2022)
Article
Computer Science, Artificial Intelligence
Shuiwang Li et al.
Summary: Unmanned aerial vehicle (UAV)-based tracking has been widely applied in various fields and discriminative correlation filters (DCF) have shown high efficiency and robustness in UAV tracking community. However, the existing DCF-based methods still need improvement in terms of efficiency and accuracy. This paper proposes residue-aware correlation filters that utilize the residue nature of videos and a scale refinement strategy to enhance the performance of DCF-based trackers.
PATTERN RECOGNITION
(2022)
Article
Engineering, Electrical & Electronic
Zhiqiang Hou et al.
Summary: In this paper, a deep learning-based target drift discriminative network is proposed to judge whether the target is lost in visual tracking. The network, which does not require an artificially set threshold, achieves better target discriminative effect through training and selection of difficult samples. Experimental results demonstrate the superior performance of the method on various datasets.
JOURNAL OF ELECTRONIC IMAGING
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Gabriele Berton et al.
Summary: Visual Geo-localization is the task of estimating the position where a photo was taken by comparing it with a database of known location images. Researchers developed a new dataset covering an entire city and created a highly scalable training technique called CosPlace. This technique achieved state-of-the-art performance and proved to be robust to domain changes.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Moez Krichen et al.
Summary: The development of drones has positive implications for employment and industrial development, but also presents security challenges and risks. This paper focuses on security challenges related to drone communications and discusses potential countermeasures such as blockchain technology, machine learning, fog computing, and software defined networks.
2022 2ND INTERNATIONAL CONFERENCE OF SMART SYSTEMS AND EMERGING TECHNOLOGIES (SMARTTECH 2022)
(2022)
Article
Computer Science, Information Systems
Sifat Rezwan et al.
Summary: This paper comprehensively surveys and categorizes several AI approaches for autonomous UAV navigation, including mathematical-based optimization and model-based learning approaches. The characteristics, types, navigation models, and applications of UAVs are highlighted, and the open research directions are discussed.
Article
Computer Science, Artificial Intelligence
Jiayi Ma et al.
Summary: Image matching is a fundamental task in various visual applications, and with the development of deep learning techniques, there has been an increasing number of methods proposed in this field. However, the challenge remains in choosing the suitable method for specific applications and designing image matching methods with superior performance. This comprehensive review and analysis provide insights into classical and latest techniques, and offer prospects for future development in image matching technologies.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2021)
Review
Automation & Control Systems
Andy Couturier et al.
Summary: Research on unmanned aerial vehicles is increasing due to their affordability and availability. Absolute visual localization has emerged as a main approach for vision-based localization, which aims to locate the UAV in a reference map or imagery. Existing approaches in this field include template matching, feature points matching, deep learning, and visual odometry.
ROBOTICS AND AUTONOMOUS SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Jiang Hai et al.
Summary: The paper introduces a novel fully convolutional network based on the Retinex theory to address the degradation of low-light images captured by UAV, effectively improving visual quality and matching performance. Extensive experiments demonstrate the method outperforms existing ones quantitatively and qualitatively, successfully achieving UAV self-localization under different illumination conditions.
APPLIED ARTIFICIAL INTELLIGENCE
(2021)
Article
Robotics
Kevin Eckenhoff et al.
Summary: This article proposes a real-time consistent multi-IMU multi-camera (MIMC) VINS estimator that seamlessly fuses multimodal information from an arbitrary number of uncalibrated cameras and IMUs within an efficient multi-state constraint Kalman filter framework. The system is able to provide smooth, uninterrupted, and accurate 3-D motion tracking even when some sensors fail, and is validated through Monte Carlo simulations and real-world experiments.
IEEE TRANSACTIONS ON ROBOTICS
(2021)
Article
Environmental Sciences
Lirong Ding et al.
Summary: Cross-view image matching, especially between UAV and satellite views, is an important research area with significant potential applications in localization and navigation. This study introduces a novel cross-view matching method (LCM) based on location classification, addressing the imbalance of input samples between satellite and UAV images. LCM simplifies the retrieval problem into a classification problem and considers the impact of feature vector size on matching accuracy, showing higher accuracies compared to previous studies. The LCM model demonstrates satisfactory bidirectional matching between UAV and satellite views, contributing to UAV-view image localization and UAV navigation applications.
Article
Environmental Sciences
Xupei Zhang et al.
Summary: This paper proposes a novel learning local features extraction method using deep neural networks to match reference and real-time images with extreme appearance changes. By combining dense local features and corresponding descriptors, the method achieves state-of-the-art performance in infrared aerial images and satellite reference images. Through an iterative training scheme, high-quality corresponding features are automatically generated and continuously improved, resulting in significant performance improvements compared to other methods.
Article
Chemistry, Analytical
Yongho Ko et al.
Summary: Unmanned Aerial Vehicles (UAVs) are crucial in various fields, but are increasingly vulnerable to security attacks. It is essential to design robust security protocols to ensure secure communication, especially in military scenarios where perfect forward secrecy and non-repudiation are crucial.
Review
Environmental Sciences
Sainab Feroz et al.
Summary: The application of Unmanned Aerial Vehicles (UAVs) in bridge monitoring, in conjunction with remote sensing technologies, has been gaining momentum in recent years due to enhanced accessibility, cost efficiency, deterrence of traffic closure, and improved safety during inspection. This study conducted a comprehensive review of the integration of UAVs with remote sensing technologies, analyzing data acquisition methods such as visual imagery, infrared thermography, LiDAR, and other sensors. Sixty-five journal and conference papers published in the last two decades on NDT-based UAV systems were scrutinized, comparing stand-alone and integrated NDT-UAV methods, and discussing the facilitation of bridge inspection using UAVs in terms of ease of use, accuracy, cost-efficiency, data collection tools, and simulation platforms. Challenges and future perspectives of UAV-NDT technologies were also highlighted.
Article
Engineering, Multidisciplinary
Mohamed Ramadan et al.
Summary: This research compared the performance of recent detection, description, and matching techniques, with ORB detector, ORB descriptor, and either BruteForce-Hamming or BruteForce-HammingLUT matchers favored for indoor environments.
AIN SHAMS ENGINEERING JOURNAL
(2021)
Review
Computer Science, Artificial Intelligence
Xingyu Jiang et al.
Summary: This paper introduces the fundamental problem of multimodal image matching and analyzes existing research methods and applications. It then provides a detailed summary and comparison of multimodal image matching methods in different research fields, and outlines future trends in related areas.
INFORMATION FUSION
(2021)
Article
Engineering, Electrical & Electronic
Gunasekaran Raja et al.
Summary: The paper introduces a Particle Filter-based Indoor Navigation (PFIN) framework for drone navigation, utilizing Quadcopter Mapping Algorithm and Optimized Localization Algorithm to enhance precision and velocity estimation. The efficiency of the algorithms is demonstrated through SITL and HITL simulations, showcasing reduced position error and improved UAV exploration precision.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2021)
Article
Automation & Control Systems
Zi-Hao Wang et al.
Summary: A cooperative navigation system using Ground-Aerial Vehicle Cooperation has been developed, showcasing innovations in data interaction, navigation framework, and environment reconstruction. Experimental results demonstrate the effectiveness of the system.
Article
Computer Science, Artificial Intelligence
Sixing Hu et al.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2020)
Article
Computer Science, Hardware & Architecture
Panagiotis Radoglou-Grammatikis et al.
Article
Computer Science, Artificial Intelligence
Fabio Bellavia et al.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2020)
Article
Computer Science, Artificial Intelligence
Hu Lin et al.
Article
Economics
Fatma Outay et al.
TRANSPORTATION RESEARCH PART A-POLICY AND PRACTICE
(2020)
Article
Engineering, Aerospace
Derek Chen et al.
NAVIGATION-JOURNAL OF THE INSTITUTE OF NAVIGATION
(2019)
Article
Computer Science, Information Systems
Miao Liu et al.
IEEE INTERNET OF THINGS JOURNAL
(2019)
Article
Engineering, Electrical & Electronic
Ioannis Mademlis et al.
IEEE TRANSACTIONS ON BROADCASTING
(2019)
Article
Construction & Building Technology
Inhae Ha et al.
BUILDING AND ENVIRONMENT
(2018)
Article
Computer Science, Artificial Intelligence
Relja Arandjelovic et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2018)
Article
Chemistry, Analytical
Yujin Chen et al.
Article
Remote Sensing
Yuncheng Lu et al.
GEO-SPATIAL INFORMATION SCIENCE
(2018)
Article
Geography, Physical
Xue Wan et al.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2016)
Article
Robotics
Michael J. Milford et al.
IEEE TRANSACTIONS ON ROBOTICS
(2008)
