检索结果-内蒙古大学图书馆

Partially calibrated semi-generalized pose from hybrid point correspondences

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Bhayani, Snehal Larsson, Viktor Sattler, Torsten Heikkilä, Janne Kukelova, Zuzana Center for Machine Vision and Signal Analysis University of Oulu Finland Czech Institute of Informatics Robotics and Cybernetics Czech Technical University Prague Czech Republic Computer Vision and Geometry Group Department of Computer Science ETH Zürich Switzerland Visual Recognition Group Faculty of Electrical Engineering Czech Technical University Prague Czech Republic

In this paper we study the problem of estimating the semi-generalized pose of a partially calibrated camera, i.e., the pose of a perspective camera with unknown focal length w.r.t. a generalized camera, from a hybrid set of 2D-2D and 2D-3D point correspondences. We study all possible camera configurations within the generalized camera system. To derive practical solvers to previously unsolved challenging configurations, we test different parameterizations as well as different solving strategies based on state-of-the-art methods for generating efficient polynomial solvers. We evaluate the three most promising solvers, i.e., the H51f solver with five 2D-2D correspondences and one 2D-3D correspondence viewed by the same camera inside generalized camera, the H32f solver with three 2D-2D and two 2D-3D correspondences, and the H13f solver with one 2D-2D and three 2D-3D correspondences, on synthetic and real data. We show that in the presence of noise in the 3D points these solvers provide better estimates than the corresponding absolute pose solvers. Copyright © 2022, The Authors. All rights reserved.

关键词： Cameras

Towards Source-free Domain Adaptive Semantic Segmentation via Importance-aware and Prototype-contrast Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Cao, Yihong Zhang, Hui Lu, Xiao Xiao, Zheng Yang, Kailun Wang, Yaonan College of Computer Science and Electronic Engineering Hunan University Changsha410082 China National Engineering Research Center of Robot Vision Perception and Control Technology School of Robotics Hunan University Changsha410082 China College of Engineering and Design Hunan Normal University Changsha410082 China

Domain adaptive semantic segmentation enables robust pixel-wise understanding in real-world driving scenes. Source-free domain adaptation, as a more practical technique, addresses the concerns of data privacy and storage limitations in typical unsupervised domain adaptation methods, making it especially relevant in the context of intelligent vehicles. It utilizes a well-trained source model and unlabeled target data to achieve adaptation in the target domain. However, in the absence of source data and target labels, current solutions cannot sufficiently reduce the impact of domain shift and fully leverage the information from the target data. In this paper, we propose an end-to-end source-free domain adaptation semantic segmentation method via Importance-Aware and Prototype-Contrast (IAPC) learning. The proposed IAPC framework effectively extracts domain-invariant knowledge from the well-trained source model and learns domain-specific knowledge from the unlabeled target domain. Specifically, considering the problem of domain shift in the prediction of the target domain by the source model, we put forward an importance-aware mechanism for the biased target prediction probability distribution to extract domain-invariant knowledge from the source model. We further introduce a prototype-contrast strategy, which includes a prototype-symmetric cross-entropy loss and a prototype-enhanced cross-entropy loss, to learn target intra-domain knowledge without relying on labels. A comprehensive variety of experiments on two domain adaptive semantic segmentation benchmarks demonstrates that the proposed end-to-end IAPC solution outperforms existing state-of-the-art methods. The source code is publicly available at https://***/yihong-97/Source-free-IAPC. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

CT-ICP: Real-time elastic LiDAR odometry with loop closure

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Dellenbach, Pierre Deschaud, Jean-Emmanuel Jacquet, Bastien Goulette, François MINES ParisTech PSL University Centre for Robotics Paris75006 France Kitware Computer Vision Team Villeurbanne69100 France

— Multi-beam LiDAR sensors are increasingly used in robotics, particularly for autonomous cars for localization and perception tasks. However, perception is closely linked to the localization task and the robot’s ability to build a fine map of its environment. For this, we propose a new real-time LiDAR odometry method called CT-ICP, as well as a complete SLAM with loop closure. The principle of CT-ICP is to use an elastic formulation of the trajectory, with a continuity of poses intra-scan and discontinuity between scans, to be more robust to high frequencies in the movements of the sensor. The registration is based on scan-to-map with a dense point cloud as map structured in sparse voxels to operate in real time. At the same time, a fast method of loop closure detection using elevation images and an optimization of poses by graph allows to obtain a complete SLAM purely on LiDAR. To show the robustness of the method, we tested it on seven datasets: KITTI, KITTI-raw, KITTI-360, KITTI-CARLA, ParisLuco, Newer College, and NCLT in driving and high-frequency motion scenarios. The CT-ICP odometry is implemented in C++ and available online. The loop detection and pose graph optimization is in the framework pyLiDAR-SLAM in Python and also available online. CT-ICP is currently first, among those giving access to a public code, on the KITTI odometry leaderboard, with an average Relative Translation Error (RTE) of 0.59% and an average time per scan of 60ms on a CPU with a single thread. © 2021, CC BY.

关键词： Optical radar

LMR: A Large-Scale Multi-Reference Dataset for Reference-based Super-Resolution

学校读者我要写书评

暂无评论

LMR: A Large-Scale Multi-Reference Dataset for Reference-bas...

International Conference on computer vision (ICCV)

作者： Lin Zhang Xin Li Dongliang He Fu Li Errui Ding Zhaoxiang Zhang University of Chinese Academy of Sciences Institute of Automation Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems School of Future Technology UCAS Department of Computer Vision Technology (VIS) Baidu Inc. Center for Artificial Intelligence and Robotics HKISI_CAS

It is widely agreed that reference-based super-resolution (RefSR) achieves superior results by referring to similar high quality images, compared to single image super-resolution (SISR). Intuitively, the more references, the better performance. However, previous RefSR methods have all focused on single-reference image training, while multiple reference images are often available in testing or practical applications. The root cause of such training-testing mismatch is the absence of publicly available multi-reference SR training datasets, which greatly hinders research efforts on multi-reference super-resolution. To this end, we construct a large-scale, multi-reference super-resolution dataset, named LMR. It contains 112, 142 groups of 300×300 training images, which is 10× of the existing largest RefSR dataset. The image size is also some times larger. More importantly, each group is equipped with 5 reference images with different similarity levels. Furthermore, we propose a new baseline method for multi-reference super-resolution: MRefSR, including a Multi-Reference Attention Module (MAM) for feature fusion of an arbitrary number of reference images, and a Spatial Aware Filtering Module (SAFM) for the fused feature selection. The proposed MRefSR achieves significant improvements over state-of-the-art approaches on both quantitative and qualitative evaluations. Our code and data are available at: https://***/wdmwhh/MRefSR.

关键词：

Scene Consistency Representation Learning for Video Scene Segmentation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wu, Haoqian Chen, Keyu Luo, Yanan Qiao, Ruizhi Ren, Bo Liu, Haozhe Xie, Weicheng Shen, Linlin Computer Vision Institute Shenzhen University China Tencent YouTu Lab Shenzhen Institute of Artificial Intelligence and Robotics for Society China Guangdong Key Laboratory of Intelligent Information Processing China KAUST Saudi Arabia

A long-term video, such as a movie or TV show, is composed of various scenes, each of which represents a series of shots sharing the same semantic story. Spotting the correct scene boundary from the long-term video is a challenging task, since a model must understand the storyline of the video to figure out where a scene starts and ends. To this end, we propose an effective Self-Supervised Learning (SSL) framework to learn better shot representations from unlabeled long-term videos. More specifically, we present an SSL scheme to achieve scene consistency, while exploring considerable data augmentation and shuffling methods to boost the model generalizability. Instead of explicitly learning the scene boundary features as in the previous methods, we introduce a vanilla temporal model with less inductive bias to verify the quality of the shot features. Our method achieves the state-of-the-art performance on the task of Video Scene Segmentation. Additionally, we suggest a more fair and reasonable benchmark to evaluate the performance of Video Scene Segmentation methods. The code is made available. © 2022, CC BY.

关键词： Semantics

What's in my LiDAR odometry toolbox?

学校读者我要写书评

暂无评论

arXiv 2021年

With the democratization of 3D LiDAR sensors, precise LiDAR odometries and SLAM are in high demand. New methods regularly appear, proposing solutions ranging from small variations in classical algorithms to radically new paradigms based on deep learning. Yet it is often difficult to compare these methods, notably due to the few datasets on which the methods can be evaluated and compared. Furthermore, their weaknesses are rarely examined, often letting the user discover the hard way whether a method would be appropriate for a use case. In this paper, we review and organize the main 3D LiDAR odometries into distinct categories. We implemented several approaches (geometric based, deep learning based, and hybrid methods) to conduct an in-depth analysis of their strengths and weaknesses on multiple datasets, guiding the reader through the different LiDAR odometries available. Implementation of the methods has been made publicly available at: https://***/Kitware/pyLiDAR-SLAM. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep learning

Detection and depth estimation for domestic waste in outdoor environments by sensors fusion

学校读者我要写书评

暂无评论

arXiv 2022年

作者： de Páez-Ubieta, Ignacio L. Velasco-Sánchez, Edison Puente, Santiago T. Candelas, Francisco A. AUtomatics RObotics and Artificial Vision Lab Computer Science Research Institute University of Alicante San Vicente del Raspeig University Campus s/n San Vicente del Raspeig Alicante03690 Spain

In this work, we estimate the depth in which domestic waste are located in space from a mobile robot in outdoor scenarios. As we are doing this calculus on a broad range of space (0.3 - 6.0 m), we use RGB-D camera and LiDAR fusion. With this aim and range, we compare several methods such as average, nearest, median and center point, applied to those which are inside a reduced or non-reduced Bounding Box (BB). These BB are obtained from segmentation and detection methods which are representative of these techniques like Yolact, SOLO, You Only Look Once (YOLO)v5, YOLOv6 and YOLOv7. Results shown that, applying a detection method with the average technique and a reduction of BB of 40%, returns the same output as segmenting the object and applying the average method. Indeed, the detection method is faster and lighter in comparison with the segmentation one. The committed median error in the conducted experiments was 0.0298 ± 0.0544 m. © 2022, CC BY-NC-ND.

关键词： Mobile robots

Image-based Navigation in Real-World Environments via Multiple Mid-level Representations: Fusion Models, Benchmark and Efficient Evaluation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Rosano, Marco Furnari, Antonino Gulino, Luigi Santoro, Corrado Farinella, Giovanni Maria FPV@IPLAB - Department of Mathematics and Computer Science University of Catania Catania Italy Robotics Laboratory Department of Mathematics and Computer Science University of Catania Catania Italy OrangeDev s.r.l. Firenze Italy Cognitive Robotics and Social Sensing Laboratory ICAR-CNR Palermo Italy Next Vision s.r.l. Catania Italy

Robot visual navigation is a relevant research topic. Current deep navigation models conveniently learn the navigation policies in simulation, given the large amount of experience they need to collect. Unfortunately, the resulting models show a limited generalization ability when deployed in the real world. In this work we explore solutions to facilitate the development of visual navigation policies trained in simulation that can be successfully transferred in the real world. We first propose an efficient evaluation tool to reproduce realistic navigation episodes in simulation. We then investigate a variety of deep fusion architectures to combine a set of mid-level representations, with the aim of finding the best merge strategy that maximize the real world performances. Our experiments, performed both in simulation and on a robotic platform, show the effectiveness of the considered mid-level representations-based models and confirm the reliability of the evaluation tool. The 3D models of the environment and the code of the validation tool are publicly available at the following link: https://***/EmbodiedVN/ © 2022, CC BY-NC-SA.

关键词： Reinforcement learning

Image-Based Navigation in Real-World Environments Via Multiple Mid-Level Representations: Fusion Models, Benchmark and Efficient Evaluation

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Rosano, Marco Furnari, Antonino Gulino, Luigi Santoro, Corrado Farinella, Giovanni Maria FPV@IPLAB Department of Mathematics and Computer Science University of Catania Catania Italy Robotics Laboratory Department of Mathematics and Computer Science University of Catania Catania Italy OrangeDev s.r.l. Firenze Italy Cognitive Robotics and Social Sensing Laboratory ICAR-CNR Palermo Italy Next Vision s.r.l. Catania Italy

Robot visual navigation is a relevant research topic. Current deep navigation models mostly learn the navigation policies in simulation. This is convenient, given the efficiency offered by simulators to collect the required training experience. Unfortunately, the resulting models show a limited generalization ability when deployed in the real world. In this work we investigate the problem of learning robust visual navigation policies in simulation that can successfully transferred in the real world. We propose an evaluation tool to reproduce realistic navigation episodes in simulation. We then study whether the mid-level visual representations, that have proven to be effective in previous applications, can be successfully used in simulation to solve the domain gap. Our experiments, performed both in simulation and on a robotic platform, show the proposed evaluation tool can provide results which are consistent with the ones obtained in the real world. © 2022, The Authors. All rights reserved.

关键词： Reinforcement learning