Article
Computer Science, Information Systems
Wuwei Wang, Ke Zhang, Meibo Lv, Jingyu Wang
Summary: This paper introduces a novel DCF-based tracker that processes the training set through a smooth and steeply decreasing function, achieving better performance. Experimental results demonstrate that the method outperforms other state-of-the-art trackers in terms of accuracy and efficiency.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Software Engineering
Jiazhao Zhang, Chenyang Zhu, Lintao Zheng, Kai Xu
Summary: The method proposed in this study tackles the challenges of fast-motion camera tracking using random optimization techniques, particularly Particle Filter Optimization (PFO). By updating a particle swarm template (PST), the method can efficiently drive thousands of particles to quickly and robustly locate and cover a good local optimum. The evaluation metric based on depth-model conformance allows the method to effectively track camera poses under fast motion, mitigating the effects of motion blur.
ACM TRANSACTIONS ON GRAPHICS
(2021)
Article
Computer Science, Information Systems
Xue-Feng Zhu, Xiao-Jun Wu, Tianyang Xu, Zhen-Hua Feng, Josef Kittler
Summary: In this study, attention mechanisms in Discriminative Correlation Filter (DCF) based visual object tracking were investigated and a channel-specific spatial attention method (A(3) DCF tracker) was proposed. This method improves the tracker performance by imposing spatial sparsity in the filter learning stage and performing post processing on the identified spatial patterns.
IEEE TRANSACTIONS ON MULTIMEDIA
(2022)
Article
Construction & Building Technology
Cassio K. Hui, Tess X. Luo, Wallace W. Lai, Ray K. Chang
Summary: This study proposes a method to synchronize GPR scans in areas with poor or no GNSS coverage, using a mobile mapping system (MMS) backpack guided by SLAM. It aims to improve the efficiency of GPR surveys in dense urban areas where good GNSS coverage is unavailable.
TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Lina Gao, Bing Liu, Ping Fu, Mingzhu Xu, Junbao Li
Summary: A novel dynamic saliency discriminative correlation filter for visual tracking is proposed in this paper, which effectively highlights the target through introducing saliency information and multi-feature integration to alleviate the boundary effect. Extensive experiments validate its competitive performance compared to other state-of-the-art trackers.
APPLIED INTELLIGENCE
(2022)
Article
Chemistry, Analytical
Roman Adamek, Martin Brablc, Patrik Vavra, Barnabas Dobossy, Martin Formanek, Filip Radil
Summary: In this work, we propose analytical functions that approximate the variances of 2D pose estimates obtained from fiducial markers. We demonstrate the effectiveness of our approach in a 2D robot localisation experiment, where we present a method for estimating covariance model parameters and fusing pose estimates from multiple markers.
Article
Robotics
Andrei Cramariuc, Lukas Bernreiter, Florian Tschopp, Marius Fehr, Victor Reijgwart, Juan Nieto, Roland Siegwart, Cesar Cadena
Summary: The integration of multiple sensor modalities and deep learning into SLAM systems is an important area of research. It enables robustness in challenging environments and interoperability of heterogeneous multi-robot systems. Maplab 2.0 provides an open-source platform for developing and integrating new modules and features into a fully-fledged SLAM system. Extensive experiments show that maplab 2.0 achieves comparable accuracy to the state-of-the-art benchmark and demonstrates flexibility in various use cases.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2023)
Article
Instruments & Instrumentation
Yueping Huang, Xiaofeng Li, Ruitao Lu, Naixin Qi
Summary: In this study, a real-time RGB-T object tracking algorithm based on sparse response-consistency discriminative correlation filters is proposed. By jointly learning discriminative correlation filters of visual and thermal infrared modalities through sparse response consistency, an adaptive spatial regularization strategy is introduced to mitigate the boundary effects of the correlation filter-based tracking algorithm. Furthermore, an adaptive decision-fusion and updating strategy is designed to efficiently utilize the complementarity of visual and thermal infrared modalities, reducing the adverse impact of unreliable modalities on tracking performance and boosting the running speed.
INFRARED PHYSICS & TECHNOLOGY
(2023)
Article
Computer Science, Information Systems
Michal Mihalik, Branislav Malobicky, Peter Peniak, Peter Vestenicky
Summary: In this article, a new approach to address the issue of active SLAM is proposed. The already functional SLAM algorithm was used and modified for the specific case. Matlab was the main software tool used, and all proposed methods were experimentally verified on a mobile robotic system. LiDAR was used as the primary sensor. After mapping the environment, a grid map was created, enabling autonomous mapping of the environment.
Article
Computer Science, Information Systems
Anas Charroud, Karim El Moutaouakil, Ali Yahyaouy
Summary: Self-driving systems need to interact with the environment and perform tasks. Localization and mapping are essential concepts for perception. The article proposes a mapping and localization architecture based on Lidar measurements, and compares and tests different methods for particle selection. Results indicate that this method performs well in real-time localization and computational efficiency.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Chemistry, Multidisciplinary
Jooeun Song, Joongjin Kook
Summary: SLAM technology is increasingly important for providing high-quality AR content on mobile devices. The proposed mobile SLAM system combines stand-alone and mapping server types to make SLAM operation and map generation more efficient. This open-source project is expected to support the development of AR content in a mobile environment.
APPLIED SCIENCES-BASEL
(2022)
Article
Chemistry, Analytical
Yu Miao, Alan Hunter, Ioannis Georgilas
Summary: OctoMap is an efficient mapping framework for building occupancy maps, but it has limitations. This study presents a method that uses the context of neighboring points to improve the mapping method of OctoMap. By considering the distance relationship between points, the proposed method achieves a 10% improvement over the optimal performance of OctoMap, as shown in the experimental results.
Article
Computer Science, Artificial Intelligence
Fabrizio Romanelli, Francesco Martinelli, Simone Mattogno
Summary: This paper discusses a solution to the Simultaneous Localization and Mapping (SLAM) problem for a moving agent using Visual Odometry (VO) and Ultra Wide Band (UWB) antennas. The proposed approach utilizes a switching observer and a Robust EKF algorithm to achieve comparable performance to a VO algorithm even before closing the loop. It also includes a resilient module to evaluate the reliability of the position estimation. The approach is robust to unmodeled disturbances and adapts to sensor failures.
JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS
(2023)
Article
Computer Science, Interdisciplinary Applications
David Jurado-Rodriguez, Rafael Munoz-Salinas, Sergio Garrido-Jurado, Rafael Medina-Carnicer
Summary: This study provides a comprehensive evaluation of the most relevant marker systems, comparing them in terms of sensitivity, specificity, accuracy, computational cost, and performance under occlusion. Recommendations on which method to use based on the application requirements are offered.
Article
Quantum Science & Technology
Yong-Mei Li, Hai-Ling Liu, Shi-Jie Pan, Su-Juan Qin, Fei Gao, Qiao-Yan Wen
Summary: Discriminative canonical correlation analysis (DCCA) is a powerful supervised feature extraction technique that has wide applications in pattern recognition for two sets of multivariate data. It consists of mean-centering and solving the generalized eigenvalue problem. To handle the high cost of DCCA in large high-dimensional samples, we propose a quantum DCCA algorithm that achieves a polynomial speedup in certain conditions.
QUANTUM INFORMATION PROCESSING
(2023)
Article
Engineering, Electrical & Electronic
Rafael Munoz-Salinas, Hamid Sarmadi, Dario Cazzato, Rafael Medina-Carnicer
Article
Computer Science, Artificial Intelligence
Rafael Munoz-Salinas, R. Medina-Carnicer
PATTERN RECOGNITION
(2020)
Article
Computer Science, Artificial Intelligence
Nicolas Luis Fernandez Garcia, Luis Del-Moral Martinez, Angel Carmona Poyato, Francisco Jose Madrid Cuevas, Rafael Medina Carnicer
PATTERN RECOGNITION LETTERS
(2020)
Article
Computer Science, Interdisciplinary Applications
Hamid Sarmadi, Rafael Munoz-Salinas, M. Alvaro Berbis, Antonio Luna, R. Medina-Carnicer
Summary: This research introduces a mobile interactive augmented reality framework for patient positioning in radiation therapy, utilizing pointcloud processing and algorithm combination to achieve precise tracking of the patient and camera, demonstrating good results in patient positioning.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2021)
Article
Computer Science, Hardware & Architecture
Antonio Fuentes-Alventosa, Juan Gomez-Luna, Jose Maria Gonzalez-Linares, Nicolas Guil, R. Medina-Carnicer
Summary: CAVLC, a high-performance entropy method for video and image compression, is widely used in the H.264 standard. While hardware accelerators have been designed, high-performance software implementations of CAVLC, especially GPU-based ones, are limited. In this paper, a new efficient GPU-based implementation of CAVLC called CAVLCU is introduced, which outperforms existing GPU-based implementations.
JOURNAL OF SUPERCOMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Antonio Fuentes-Alventosa, Juan Gomez-Luna, R. Medina-Carnicer
Summary: The Canny algorithm is a commonly used edge detector with superior performance in noisy environments, but it suffers from a time-consuming process. To address the limitations of GPU implementations, a novel GPU-based unsupervised and distributed Canny edge detector is proposed in this paper, which achieves real-time requirements and outperforms existing GPU and FPGA implementations.
JOURNAL OF REAL-TIME IMAGE PROCESSING
(2022)
Article
Computer Science, Artificial Intelligence
Nicolas Luis Fernandez-Garcia, Luis Del-Moral Martinez, Angel Carmona-Poyato, Francisco Jose Madrid-Cuevas, Rafael Medina-Carnicer
Summary: This document presents two proposals regarding the evaluation of polygonal approximations. Firstly, a new measurement called normalized compression ratio and adjustment error (NCA) is proposed to provide a fair evaluation of the performance of polygonal approximations of 2D closed curves. Secondly, a new evaluation methodology based on the optimal quality curve concept is proposed for assessing the measurements. The experiments show that NCA obtains the best results and can be used to fairly evaluate the performance of polygonal approximations.
PATTERN RECOGNITION
(2023)
Article
Chemistry, Analytical
Francisco J. Romero-Ramirez, Rafael Munoz-Salinas, Manuel J. Marin-Jimenez, Miguel Cazorla, Rafael Medina-Carnicer
Summary: This paper proposes a novel visual SLAM approach that efficiently combines keypoints and artificial markers, allowing for a substantial reduction in computing time and memory required without noticeably degrading the tracking accuracy.
Article
Chemistry, Analytical
Rafael Aguilar-Ortega, Rafael Berral-Soler, Isabel Jimenez-Velasco, Francisco J. Romero-Ramirez, Manuel Garcia-Marin, Jorge Zafra-Palma, Rafael Munoz-Salinas, Rafael Medina-Carnicer, Manuel J. Marin-Jimenez
Summary: This article introduces the use of deep learning for pose estimation in physical rehabilitation, aiming to help doctors monitor patients' recovery progress more effectively. The study evaluates and compares different pose estimation methods and examines the impact of subject position and camera viewpoint on the results, as well as the necessity of 3D estimation. The findings provide useful insights for optimizing rehabilitation monitoring.
Article
Computer Science, Information Systems
David Jurado-Rodriguez, Rafael Munoz-Salinas, Sergio Garrido-Jurado, Rafael Medina-Carnicer
Summary: This work presents a novel method for designing, detecting, and tracking customizable fiducial markers as alternatives to traditional tools like QR codes and ArUco, offering a more visually appealing option without sacrificing performance.
Article
Computer Science, Information Systems
Hamid Sarmadi, Rafael Munoz-Salinas, Miguel A. Olivares-Mendez, Rafael Medina-Carnicer
Summary: This study proposes a new method using event cameras to detect and decode binary square markers, which detects edges of the markers by detecting line segments in an image created from events and decodes the bit value of marker cells using events on their borders. Experimental results show that the performance of this method is superior to the traditional RGB ArUco marker detector.