相关参考文献
注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article
Computer Science, Artificial Intelligence
Zhi Tian et al.
Summary: CondInst is a simple yet effective framework for instance and panoptic segmentation, which uses dynamic conditional convolutions to attend to the instances and achieves improved accuracy and faster inference speed.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Software Engineering
Kevin Yu et al.
Summary: The study proposes the concept of "Duplicated Reality" to allow users to remotely annotate the working area in AR while being co-located with others. Results from a user study show almost identical objective and subjective outcomes compared to in-situ augmentation, except for a decrease in the consulting user's awareness of co-located users when using the proposed method. The addition of duplicating the working area into a designated consulting area provides new interaction paradigms for future co-located AR collaboration systems.
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
(2022)
Article
Environmental Sciences
Rui Zhai et al.
Summary: This study proposes a method for achieving high-precision localization in complex urban environments by integrating vision and GNSS, and utilizing semantic information for positioning. The experiments showed that the proposed algorithm improved the performance of visual localization and achieved continuous high-accuracy positioning in GNSS-challenged environments.
Article
Environmental Sciences
Ursula Kaelin et al.
Summary: A novel tracking system is developed to validate the accuracy and reliability of onboard sensors for object detection and localization in realistic conditions. The system can determine the position and orientation of a vehicle, meeting certain pose requirements, and allowing for flexible installation in different environments.
Article
Automation & Control Systems
Hanjiang Hu et al.
Summary: This paper proposes a coarse-to-fine localization method based on image retrieval, which uses multi-domain image translation and gradient-weighted similarity activation mapping loss to extract domain-invariant features and improve localization accuracy. Experiments demonstrate the effectiveness and strong generalization ability of the proposed method in challenging environments.
IEEE-CAA JOURNAL OF AUTOMATICA SINICA
(2022)
Article
Computer Science, Artificial Intelligence
Carl Toft et al.
Summary: This paper presents a visual localization approach and evaluates its accuracy by expanding existing datasets. The performance of state-of-the-art localization approaches is also discussed. The researchers release a portion of the datasets for research purposes and aim to stimulate further research in related areas.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Environmental Sciences
Xuan He et al.
Summary: In this paper, a LiDAR-inertial-GNSS fusion positioning algorithm based on voxelized accurate registration was proposed to address the insufficient accuracy and accumulated error of LiDAR-inertial odometry (LIO) point cloud registration in urban environments. The algorithm utilizes curvature segmentation for voxelized point cloud downsampling and constructs a point cloud registration model based on nearest neighbors. An iterative termination threshold is set to reduce local optimal solutions. The algorithm achieves more continuous and accurate position and attitude estimation and map reconstruction in urban environments.
Article
Environmental Sciences
Daniel Wilson et al.
Summary: This paper presents a novel two-stage technique for object geo-localization from images, which is applicable to various fields such as land surveying, self-driving, and asset management. Current methods have limitations and assumptions that restrict their usability in real-world applications. The authors propose a new approach that can detect and geo-localize dense, multi-class objects in low frame rate inputs, and introduce a public dataset for future research.
Article
Robotics
Mona Gridseth et al.
Summary: This letter presents a method for autonomously localizing a robot using a neural network and classical pose estimator. The network predicts sparse keypoints with descriptors, which are used for localization. The method is validated through experiments, demonstrating successful path following in various lighting conditions.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Engineering, Electrical & Electronic
Yujie Wang
Summary: With the rapid development of modern science and technology, the importance of multi-sensor information fusion target tracking technology in computer vision has been increasing. This article proposes a multi-sensor multi-target tracking algorithm based on random finite set, discussing the theory and application of random sets, as well as the significance of probability hypothesis density in tracking. Experimental results show the algorithm's effectiveness in tracking maneuvering targets and the superiority of the unscented Kalman filter over the extended Kalman filter in filtering error and estimation accuracy.
IEEE SENSORS JOURNAL
(2021)
Article
Computer Science, Artificial Intelligence
Akihiko Torii et al.
Summary: Accurate visual localization can be achieved through 3D structure-based methods or 2D image retrieval-based methods. Large-scale 3D models are not strictly necessary, and combining image-based methods with local reconstructions can improve pose accuracy.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2021)
Proceedings Paper
Automation & Control Systems
Chengcheng Guo et al.
Summary: This paper presents a cost-effective vehicle localization system for autonomous driving using cameras as primary sensors. The method maps visual semantics to landmarks in HD map, initializes the system by combining GPS measurement and pose searching, and refines vehicle pose by aligning semantic segmentation results with photometric consistency.
2021 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS)
(2021)
Proceedings Paper
Automation & Control Systems
Markus Herb et al.
Summary: The paper presents a novel approach to vehicle localization in dense semantic maps using semantic segmentation, which addresses the fundamental requirement of accurate and reliable localization for autonomous vehicles to utilize map information in higher-level tasks. By formulating the localization task as a direct image alignment problem on semantic images, the approach achieves robust tracking of vehicle pose in semantically labeled maps without the need for additional keypoint features or expensive LiDAR sensors, demonstrating wide applicability and real-time performance.
2021 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS)
(2021)
Proceedings Paper
Computer Science, Interdisciplinary Applications
Manuel Diaz-Zapata et al.
Summary: This paper introduces a panoptic segmentation network based on YOLOv3, which achieves real-time inference by adding semantic and instance segmentation branches and achieves performance similar to state-of-the-art methods in some metrics.
2021 IEEE 45TH ANNUAL COMPUTERS, SOFTWARE, AND APPLICATIONS CONFERENCE (COMPSAC 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Jaime Spencer et al.
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2020)
Article
Environmental Sciences
Runzhi Wang et al.
Proceedings Paper
Imaging Science & Photographic Technology
Tianxin Shi et al.
2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)
(2019)
Article
Computer Science, Artificial Intelligence
Relja Arandjelovic et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2018)
Article
Computer Science, Artificial Intelligence
Linus Svarm et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2017)
Article
Computer Science, Artificial Intelligence
Torsten Sattler et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2017)
Article
Robotics
Raul Mur-Artal et al.
IEEE TRANSACTIONS ON ROBOTICS
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Liu Liu et al.
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
(2017)