Article
Computer Science, Interdisciplinary Applications
Georgios Petrakis, Angelos Antonopoulos, Achilles Tripolitsiotis, Dimitris Trigkakis, Panagiotis Partsinevelos
Summary: In this study, a surveying method that combines stereoscopic vision and visual markers is proposed, which achieves centimeter-level accuracy in localizing specific and arbitrary points. The method utilizes stereo SLAM algorithm to localize the camera system and map the study area, and then detects visual markers placed in the area. Using a multi-view geometry method and an optimization algorithm, the coordinates of the markers and a point cloud are exported in a local coordinate system. Extensive experiments validate the feasibility of the methodology, achieving horizontal and vertical errors of 10 cm or better.
EARTH SCIENCE INFORMATICS
(2023)
Article
Engineering, Electrical & Electronic
Qingxi Zeng, Haonan Yu, Xufang Ji, Xiaodong Tao, Yixuan Hu
Summary: This paper presents a fast and robust monocular visual-inertial odometry (VIO) algorithm for autonomous navigation of unmanned aerial vehicles (UAVs). The algorithm utilizes a semidirect method for tracking and incorporates edgelet features and a quadtree-based feature extraction algorithm to enhance its robustness. In the back end, a sliding-window-based nonlinear optimization method is used for image and inertial information fusion. Experimental results demonstrate the algorithm's capability to operate in challenging scenarios and achieve comparable accuracy to state-of-the-art VIO algorithms while improving tracking speed.
IEEE SENSORS JOURNAL
(2023)
Article
Environmental Sciences
Yongwoo Lee, Junkang An, Inwhee Joe
Summary: This paper proposes a method to create a new flight route during the autonomous flight of an unmanned aerial vehicle by self-recognition and judgment. By effectively utilizing the hardware resources of small computers, objects can be quickly and accurately recognized, and quick detection and avoidance can be achieved through filtering and object resizing.
Article
Environmental Sciences
In-Ho Kim, Hyung-Jo Jung, Sungsik Yoon, Jong Woong Park
Summary: In this paper, a non-contact cable estimation method using a vision sensor mounted on an unmanned aerial vehicle is proposed. Through marker detection, a target cable among many cables can be identified, and the motion of the structure can be quickly captured using the extracted feature points. The cable tension can be estimated via the vibration method using the modal frequencies derived from the cable displacement.
Article
Engineering, Electrical & Electronic
Zhuyin Li, Andrea Giorgetti, Sithamparanathan Kandeepan
Summary: This paper proposes a method for multiple PU localization based on UAV-mounted antenna array's measurement of received power, with two algorithms applied to estimate the number and positions of PUs from the score map. Despite being a blind method, it exhibits excellent localization accuracy in large outdoor scenarios.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2021)
Article
Computer Science, Information Systems
Huitai Hou, Qing Xu, Chaozhen Lan, Wanjie Lu, Yongxian Zhang, Zhixiang Cui, Jianqi Qin
Summary: With the growing maturity of UAV technology, a localization method based on deep learning features of satellite imagery is proposed to improve accuracy in pose estimation in GNSS-denied environments. This method utilizes a top-view optical camera, satellite imageries with geographic coordinates, and a digital elevation model for stable registration, and includes a local optimization method based on bundle adjustment for improved accuracy and robustness. Experiment results show an average localization error within 15 meters under different trajectories when the UAV's relative altitude is 0.5 km.
Article
Engineering, Marine
Di Lu, Chengke Xiong, Hexiong Zhou, Chenxin Lyu, Rui Hu, Caoyang Yu, Zheng Zeng, Lian Lian
Summary: The study introduces an improved design of a multimodal hybrid aerial underwater vehicle capable of level and vertical flight, hovering, and underwater glide. The innovation lies in the novel configuration and lightweight pneumatic buoyancy system to balance flight payload and underwater weight. The prototype, named Nezha III, demonstrates excellent performance in different modes and remarkable capability of diving to 50 meters depth.
Article
Engineering, Electrical & Electronic
Hunter Stuckey, Amer Al-Radaideh, Liang Sun, Wei Tang
Summary: The paper presents a 3D localization and attitude estimation system for tracking a UAV using a single camera without prior knowledge of the environment. The proposed method offers a simple yet accurate solution for tracking the location and attitude of a UAV, surpassing similar state-of-the-art systems in accuracy and detection range.
IEEE SENSORS JOURNAL
(2022)
Article
Automation & Control Systems
Yuanda Wang, Wenzhang Liu, Jian Liu, Changyin Sun
Summary: This paper investigates the visual navigation and control of a cooperative USV-UAV system for marine search and rescue. A deep learning-based visual detection architecture is developed to extract positional information from UAV images, improving accuracy and efficiency. A reinforcement learning-based USV control strategy is proposed, which can learn a motion control policy with enhanced disturbance rejection ability. Simulation results show stable and accurate position estimation and satisfactory control ability under wave disturbances.
Article
Computer Science, Information Systems
Yonghui Liang, Yuqing He, Junkai Yang, Weiqi Jin, Mingqi Liu
Summary: This research presents a new monocular vision-based pipeline for accurate vehicle localization, combining convolutional blocks and target detection algorithms to improve accuracy. By converting bounding boxes to actual depth and angle, the method shows high accuracy and efficiency on the KITTI dataset.
Article
Robotics
Chenxin Lyu, Di Lu, Chengke Xiong, Rui Hu, Yufei Jin, Jianhu Wang, Zheng Zeng, Lian Lian
Summary: This research presents the design and testing of a novel hybrid aerial underwater vehicle (HAUV) called Nezha III. It features a piston-driven underwater glide strategy and combines the characteristics of an underwater glider and a fixed-wing vertical takeoff and landing aircraft. The vehicle prototype was built and field experiments were conducted to evaluate its performance. The experiment results show that Nezha III has extended underwater endurance and operational depth compared to existing HAUVs.
JOURNAL OF FIELD ROBOTICS
(2022)
Article
Geochemistry & Geophysics
Vlad-Cristian Miclea, Sergiu Nedevschi
Summary: Environment perception by computing depth is crucial for unmanned aerial vehicle (UAV) systems. However, due to limited payload capacity, most drones are equipped with a single camera, making it challenging to use depth perception methods based on LiDAR or stereo reconstruction. In this study, we propose a novel approach for monocular depth estimation (MDE) on aerial images using a customized CNN. Additionally, we introduce a learning-based correction method to improve accuracy at both short and long ranges. Our method demonstrates accurate and reliable depth estimation in various aerial scenarios, as shown on synthetic and real-life images captured by a drone.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Chemistry, Analytical
Xiaoyu Yang, Nisha Bao, Wenwen Li, Shanjun Liu, Yanhua Fu, Yachun Mao
Summary: Soil nutrient is crucial for improving farmland quality and product, and imaging spectrometry shows potential for rapid monitoring. This study explores preprocessing and modeling methods for hyperspectral images obtained via UAV to estimate soil organic matter and total nitrogen in farmland. Results show that a combination of methods including Mulitplicative Scattering Correction and feature selection through particle swarm optimization can enhance prediction accuracy compared to traditional models like SVM and PLSR.
Article
Robotics
Ryoga Shimizu, Yasunori Sugita
Summary: This paper proposes an integration method of estimation results for cooperative localization by UAV and UGV. The point estimation result of the UAV is converted to a normal distribution and introduced as the observation likelihood of the UGV, while the particle pose with maximum weight from the UGV's distribution estimation result is added to the current pose constraint in UAV optimization. The results show that stable localization of both robots can be achieved by correcting with the estimation result of the other even in an environment where either one is disadvantageous for localization.
Article
Environmental Sciences
Yunpeng Ma, Qingwu Li, Lulu Chu, Yaqin Zhou, Chang Xu
Summary: An automatic transmission line inspection system incorporating UAV remote sensing with binocular visual perception technology has been developed in this paper, which can accurately detect and locate insulators on power equipment in real time. A two-stage strategy is proposed for precise identification of insulators, and a real-time object spatial localization method combining binocular stereo vision and GPS is further introduced. Experiment results show the system meets the requirements of robustness and accuracy in insulator detection and spatial localization in practical engineering.
Article
Chemistry, Analytical
Edmundo Guerra, Yolanda Bolea, Javier Gamiz, Antoni Grau
Article
Computer Science, Information Systems
Juan-Carlos Trujillo, Rodrigo Munguia, Sarquis Urzua, Antoni Grau
Article
Chemistry, Analytical
Juan-Carlos Trujillo, Rodrigo Munguia, Sarquis Urzua, Edmundo Guerra, Antoni Grau
Article
Chemistry, Multidisciplinary
Javier Gamiz, Antoni Grau, Herminio Martinez, Yolanda Bolea
APPLIED SCIENCES-BASEL
(2020)
Article
Engineering, Electrical & Electronic
Antoni Grau, Marina Indri, Lucia Lo Bello, Thilo Sauter
Summary: Robots have been a part of automation systems for a long time, undergoing a revolution fueled by Industry 4.0 and IoT concepts. The evolution of robotics from traditional isolated robotic cells to collaborative robots is highlighted, along with the role of robotics in the Industry 4.0 framework. Future directions for robotics involve contributions from new materials, sensors, and actuators, but there are also barriers and challenges to be addressed for wider deployment in the SME world.
IEEE INDUSTRIAL ELECTRONICS MAGAZINE
(2021)
Article
Chemistry, Analytical
Rodrigo Munguia, Juan-Carlos Trujillo, Edmundo Guerra, Antoni Grau
Summary: This paper presents a hybrid visual-based SLAM architecture that combines the strengths of different methodologies. It uses filter-based and optimization techniques for local and global map construction and maintenance, and integrates additional sensors in a monocular-based SLAM system for unmanned aerial vehicles.
Article
Engineering, Electrical & Electronic
Jorge Jimenez, Cristobal Padilla, Antoni Grau
Summary: The ASTEROID project aims to develop MCT FPAs of =2k(2) class. A research conducted by the IFAE validated the reliability of hybridization between the ROIC and MCT detector using indium bumps' soldering technique. The number of damaged pixels was measured through thermal cycling and image analysis.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Engineering, Electrical & Electronic
Jorge Jimenez, Antoni Grau, Cristobal Padilla
Summary: The ASTEROID project aims to develop high-performance infrared FPAs for astronomical scientific missions in Europe and promote self-sufficiency. IFAE will lead the task of validating detector performance, including assessing the reliability between the readout integrated circuit and the MCT detector through multiple low-temperature thermal cycles.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Edmundo Guerra, Yolanda Bolea, Rodrigo Munguia, Antoni Grau
ADVANCES IN HUMAN FACTORS IN ROBOTS AND UNMANNED SYSTEMS
(2020)