检索结果-内蒙古大学图书馆

Deep Learning-Based Object Pose Estimation: A Comprehensive Survey

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Jian Sun, Wei Yang, Hui Zeng, Zhiwen Liu, Chongpei Zheng, Jin Liu, Xingyu Rahmani, Hossein Sebe, Nicu Mian, Ajmal The National Engineering Research Center for Robot Visual Perception and Control Technology College of Electrical and Information Engineering the State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Hunan University Changsha410082 China The School of Architecture and Art Central South University Changsha410082 China The Department of Automation Tsinghua University Beijing100084 China The School of Computing and Communications Lancaster University LA1 4YW United Kingdom The Department of Information Engineering and Computer Science University of Trento Trento38123 Italy The Department of Computer Science The University of Western Australia WA6009 Australia

Object pose estimation is a fundamental computer vision problem with broad applications in augmented reality and robotics. Over the past decade, deep learning models, due to their superior accuracy and robustness, have increasingly supplanted conventional algorithms reliant on engineered point pair features. Nevertheless, several challenges persist in contemporary methods, including their dependency on labeled training data, model compactness, robustness under challenging conditions, and their ability to generalize to novel unseen objects. A recent survey discussing the progress made on different aspects of this area, outstanding challenges, and promising future directions, is missing. To fill this gap, we discuss the recent advances in deep learning-based object pose estimation, covering all three formulations of the problem, i.e., instance-level, category-level, and unseen object pose estimation. Our survey also covers multiple input data modalities, degrees-of-freedom of output poses, object properties, and downstream tasks, providing the readers with a holistic understanding of this field. Additionally, it discusses training paradigms of different domains, inference modes, application areas, evaluation metrics, and benchmark datasets, as well as reports the performance of current state-of-the-art methods on these benchmarks, thereby facilitating the readers in selecting the most suitable method for their application. Finally, the survey identifies key challenges, reviews the prevailing trends along with their pros and cons, and identifies promising directions for future research. We also keep tracing the latest works at Awesome-Object-Pose-Estimation. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

NTIRE 2023 Challenge on Light Field Image Super-Resolution: Dataset, Methods and Results

学校读者我要写书评

暂无评论

NTIRE 2023 Challenge on Light Field Image Super-Resolution: ...

2023 IEEE/CVF Conference on computer vision and Pattern Recognition Workshops, CVPRW 2023

作者： Wang, Yingqian Wang, Longguang Liang, Zhengyu Yang, Jungang Timofte, Radu Guo, Yulan Jin, Kai Wei, Zeqiang Yang, Angulia Guo, Sha Gao, Mingzhi Zhou, Xiuzhuang Van Duong, Vinh Huu, Thuc Nguyen Yim, Jonghoon Jeon, Byeungwoo Liu, Yutong Cheng, Zhen Xiao, Zeyu Xu, Ruikang Xiong, Zhiwei Liu, Gaosheng Jin, Manchang Yue, Huanjing Yang, Jingyu Gao, Chen Zhang, Shuo Chang, Song Lin, Youfang Chao, Wentao Wang, Xuechun Wang, Guanghui Duan, Fuqing Xia, Wang Wang, Yan Xia, Peiqi Wang, Shunzhou Lu, Yao Cong, Ruixuan Sheng, Hao Yang, Da Chen, Rongshan Wang, Sizhe Cui, Zhenglong Chen, Yilei Lu, Yongjie Cai, Dongjun An, Ping Salem, Ahmed Ibrahem, Hatem Yagoub, Bilel Kang, Hyun-Soo Zeng, Zekai Wu, Heng National University of Defense Technology China Aviation University of Air Force China University of Würzburg Germany Eth Zürich Switzerland Sun Yat-sen University The Shenzhen Campus of Sun Yat-sen University China Bigo Technology Pte. Ltd. Singapore Smart Medical Innovation Lab Beijing University of Posts and Telecommunications China Global Explorer Ltd. Suzhou China National Engineering Research Center of Visual Technology School of Computer Science Peking University China School of Artificial Intelligence Beijing University of Posts and Telecommunications China Department of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of University of Science and Technology of China China School of Electrical and Information Engineering Tianjin University China Beijing Key Lab of Traffic Data Analysis and Mining School of Computer and Information Technology Beijing Jiaotong University China Beijing Normal University China Toronto Metropolitan University Canada Beijing Institute of Technology China Shenzhen MSU-BIT University China State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University China Beihang Hangzhou Innovation Institute Yuhang China Faculty of Applied Sciences Macao Polytechnic University China School of Communication and Information Engineering Shanghai University China School of Information and Communication Engineering Chungbuk National University Korea Republic of Guangdong University of Technology China

ISBN: (纸本)9798350302493

In this report, we summarize the first NTIRE challenge on light field (LF) image super-resolution (SR), which aims at super-resolving LF images under the standard bicubic degradation with a magnification factor of 4. This challenge develops a new LF dataset called NTIRE-2023 for validation and test, and provides a toolbox called BasicLFSR to facilitate model development. Compared with single image SR, the major challenge of LF image SR lies in how to exploit complementary angular information from plenty of views with varying disparities. In total, 148 participants have registered the challenge, and 11 teams have successfully submitted results with PSNR scores higher than the baseline method LF-InterNet [1]. These newly developed methods have set new state-of-the-art in LF image SR, e.g., the winning method achieves around 1 dB PSNR improvement over the existing state-of-the-art method DistgSSR [2]. We report the solutions proposed by the participants, and summarize their common trends and useful tricks. We hope this challenge can stimulate future research and inspire new ideas in LF image SR. © 2023 IEEE.

关键词： Image enhancement

MetaFruit Meets Foundation Models: Leveraging a Comprehensive Multi-Fruit Dataset for Advancing Agricultural Foundation Models

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Jiajia Lammers, Kyle Yin, Xunyuan Yin, Xiang He, Long Lu, Renfu Li, Zhaojian Department of Electrical and Computer Engineering Michigan State University East LansingMI United States School of Chemical and Biomedical Engineering Nanyang Technological University Singapore Department of Automation Key Laboratory of System Control and Information Processing Shanghai Jiao Tong University Shanghai China Department of Agricultural and Biological Engineering Pennsylvania State University United States United States Department of Agriculture Agricultural Research Service East LansingMI United States Department of Mechanical Engineering Michigan State University East LansingMI United States

Fruit harvesting poses a significant labor and financial burden for the industry, highlighting the critical need for advancements in robotic harvesting solutions. Machine vision-based fruit detection has been recognized as a crucial component for robust identification of fruits to guide robotic manipulation. Despite considerable progress in leveraging deep learning and machine learning techniques for fruit detection, a common shortfall is the inability to swiftly extend the developed models across different orchards and/or various fruit species. Additionally, the limited availability of pertinent data further compounds these challenges. In this work, we introduce MetaFruit, the largest publicly available multi-class fruit dataset, comprising 4,248 images and 248,015 manually labeled instances across diverse U.S. orchards. Furthermore, this study proposes an innovative open-set fruit detection system leveraging advanced vision Foundation Models (VFMs) for fruit detection that can adeptly identify a wide array of fruit types under varying orchard conditions. This system not only demonstrates remarkable adaptability in learning from minimal data through few-shot learning but also shows the ability to interpret human instructions for subtle detection tasks. The performance of the developed foundation model is comprehensively evaluated using several metrics, which outperforms the existing state-of-the-art algorithms in both our MetaFruit dataset and other open-sourced fruit datasets, thereby setting a new benchmark in the field of agricultural technology and robotic harvesting. The MetaFruit dataset (https://***/datasets/jiajiali/metafruit) and detection framework (https://***/JiajiaLi04/FMFruit) are open-sourced to foster future research in vision-based fruit harvesting, marking a significant stride toward addressing the urgent needs of the agricultural sector. © 2024, CC BY-NC-SA.

关键词： Fruits

Metafruit Meets Foundation Models: Leveraging a Comprehensive Multi-Fruit Dataset for Advancing Agricultural Foundation Models

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

Fruit harvesting poses a significant labor and financial burden for the industry, highlighting the critical need for advancements in robotic harvesting solutions. Machine vision-based fruit detection has been recognized as a crucial component for robust identification of fruits to guide robotic manipulation. Despite considerable progress in leveraging deep learning and machine learning techniques for fruit detection, a common shortfall is the inability to swiftly extend the developed models across different orchards and/or various fruit species. Additionally, the limited availability of pertinent data further compounds these challenges. In this work, we introduce MetaFruit, the largest publicly available multi-class fruit dataset, comprising 4,248 images and 248,015 manually labeled instances across diverse U.S. orchards. Furthermore, this study proposes an innovative open-set fruit detection system leveraging advanced vision Foundation Models (VFMs) for fruit detection that can adeptly identify a wide array of fruit types under varying orchard conditions. This system not only demonstrates remarkable adaptability in learning from minimal data through few-shot learning but also shows the ability to interpret human instructions for subtle detection tasks. The performance of the developed foundation model is comprehensively evaluated using several metrics, which outperforms the existing state-of-the-art algorithms in both our MetaFruit dataset and other open-sourced fruit datasets, thereby setting a new benchmark in the field of agricultural technology and robotic harvesting. The MetaFruit dataset and detection framework are open-sourced to foster future research in vision-based fruit harvesting, marking a significant stride toward addressing the urgent needs of the agricultural sector. © 2024, The Authors. All rights reserved.

关键词： Fruits

Skeleton-Based Multi-Stream Adaptive Graph Convolutional Network for Indoor Scene Action Recognition

学校读者我要写书评

暂无评论

Skeleton-Based Multi-Stream Adaptive Graph Convolutional Net...

Chinese Automation Congress (CAC)

作者： Jiazhuo Li Luefeng Chen Min Li Min Wu Witold Pedrycz Kaoru Hirota School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems and the Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education School of Automation China University of Geosciences Wuhan China Department of Electrical and Computer Engineering University of Alberta Edmonton AB Canada Polish Academy of Sciences Systems Research Institute Warsaw Poland Department of Computer Engineering Istinye University Sariyer/Istanbul Turkey Tokyo Institute of Technology Yokohama Japan Tokyo Institute of Technology Tokyo Japan

With the rapid advances in computer vision, human action recognition has gradually received attention, but the current methods still exhibit some problems in indoor environments. The human skeleton, as the framework of human motion, contains high-quality actional feature information, and the skeleton-based action recognition method effectively avoid the interference of interior background noise and has advantages in indoor action recognition. The outstanding effect of graph convolutional networks on graph structure data processing has led to its rapid development and wide application in skeleton-based action recognition. Second-order skeletal information also contains a large number of actional features but is not effectively utilized. The artificial predefined topology of the human skeleton map has limitations, and cannot reflect the interaction between limbs. To solve the above problems, this article designs an adaptive weighted multi-stream graph convolutional network (AM-GCN) based on skeletal information, using an attention mechanism to enhance the network's ability to extract actional features, and an adaptive layer to make the construction graph more flexible, incorporating second-order skeletal features through a dual-stream architecture. In this article, the NTU-RGB+D dataset has been used for the experiments, the results show that the method in this article has good results.

关键词：

Perceptual Attacks of No-Reference Image Quality Models with Human-in-the-Loop

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhang, Weixia Li, Dingquan Min, Xiongkuo Zhai, Guangtao Guo, Guodong Yang, Xiaokang Ma, Kede MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China Network Intelligence Research Department Peng Cheng Laboratory China Department of Computer Science and Electrical Engineering West Virginia University United States Department of Computer Science City University of Hong Kong Hong Kong

No-reference image quality assessment (NR-IQA) aims to quantify how humans perceive visual distortions of digital images without access to their undistorted references. NR-IQA models are extensively studied in computational vision, and are widely used for performance evaluation and perceptual optimization of man-made vision systems. Here we make one of the first attempts to examine the perceptual robustness of NR-IQA models. Under a Lagrangian formulation, we identify insightful connections of the proposed perceptual attack to previous beautiful ideas in computer vision and machine learning. We test one knowledge-driven and three data-driven NR-IQA methods under four full-reference IQA models (as approximations to human perception of just-noticeable differences). Through carefully designed psychophysical experiments, we find that all four NR-IQA models are vulnerable to the proposed perceptual attack. More interestingly, we observe that the generated counterexamples are not transferable, manifesting themselves as distinct design flows of respective NR-IQA methods. © 2022, CC BY.

关键词： Image quality

Adaptive Robust Invariant Extended Kalman filtering for Biped Robot*

学校读者我要写书评

暂无评论

Adaptive Robust Invariant Extended Kalman filtering for Bipe...

IEEE International Conference on robotics and Biomimetics

作者： Chengzhi Gao Ye Xie Shiqiang Zhu Guanyu Huang Lingyu Kong Anhuan Xie Jason Gu Dan Zhang Jun Shao Haofu Qian Research Center for Intelligent Robotics Research Institute of Interdisciplinary Innovation Zhejiang Laboratory Hangzhou China Zhejiang Engineering Research Center for Intelligent Robotics Hangzhou China Zhejiang University Hangzhou Zhejiang China Department of Electrical and Computer Engineering Dalhousie University Halifax NS Canada B3H 4R2 York University North York Toronto M3J 1P3 Canada School of Mechanical Engineering Zhejiang University Hangzhou China

ISBN: (纸本)9781665481106

The precise estimation of system states is essential for the locomotion control of biped robots to maintain balance. Currently, the estimation of system states is either based on vision data that is susceptible to the environment, or fusing data from Inertial Measurement Unit (IMU) and the kinematic calculation. Invariant Extended Kalman Filtering (IEKF) is one of the most successful fusing algorithms to estimate system state. Generally, in IEKF, the noise covariance of system state is assumed to be known. However, the noise covariance of contact point for biped is not available since the ground-contact situation normally varies and not previously known. This paper presents a new fusing algorithm-Adaptive Robust Invariant Extended Kalman Filtering (ARIEKF) to adaptively adjust the noise parameter of contact point. The proposed algorithm applied the principle of robust estimation to resist outlier effects of state, and introduced an adaptive factor for the noise covariance of state to control its outlying disturbance influences. This paper firstly completed the full state estimation of biped robot using the theory of Lie groups and invariant observer. Then, the adaptive scale factor evaluated by three-segment approach was adopted to adjust the noise covariance of contact point. Finally, both IEKF and proposed ARIEKF are applied to our biped robot-Cosmos and the accuracy of two algorithms are compared. The mean square errors of the velocity of two algorithms were evaluated using the measurements from motion capture system. Experiments demonstrated that the mean square errors of the velocity are decreased 50 percent when compared with IEKF.

关键词： Measurement units Filtering Mean square error methods Resists Observers Motion capture Kalman filters

Distributed Energy Optimization for Mobile Networks Using Potential Games

学校读者我要写书评

暂无评论

Distributed Energy Optimization for Mobile Networks Using Po...

IEEE Internatonal Conference on Mobile Adhoc and Sensor Systems (MASS)

作者： Zhizongkai Wang Hanfei Wang Zhongji Wang Yilin Xiao Yunzhi Zhao Xiaowen Li Xufeng Chen Lin Gao Fen Hou Jianwei Huang School of Electronics and Information Engineering and the Guangdong Provincial Key Laboratory of Aerospace Communication and Networking Technology Harbin Institute of Technology Shenzhen Guangdong P.R. China School of Science and Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen Key Laboratory of Crowd Intelligence Empowered Low-Carbon Energy Network and CSIJRI Joint Research Centre on Smart Energy Storage The Chinese University of Hong Kong Shenzhen Guangdong P.R. China Department of Electrical and Computer Engineering State Key Laboratory of IoT for Smart City University of Macau Macau SAR P.R. China Huawei Technologies P.R. China

ISBN: (数字)9798350363999

ISBN: (纸本)9798350364002

The rapid advancement of information and communication technology (ICT) has made the industry a significant contributor to global carbon emissions. As the foundation of ICT, next-generation mobile communication networks aim to be more powerful and energy-efficient. However, optimizing energy efficiency in real networks is challenging due to large-scale, multi-layer control variables and the dynamic environment. This paper addresses the energy efficiency optimization problem from a network perspective by controlling cross-layer variables including both cell activation status and cell priority, to minimize overall network energy consumption while ensuring user quality-of-experience, which poses an NP-hard mixed-integer nonlinear programming problem. To tackle this, we propose a non-cooperative game where each cell acts as a player, optimizing its activation status and reference signal transmission power (determining its priority). We show that the game is a potential game, guaranteeing the existence of Nash equilibrium and the convergence of simple distributed algorithms towards Nash equilibrium. We further show that the Nash equilibrium points of the game can (but not always) reach the global optimal energy efficiency. Simulation results show that our proposed method can reduce the total system cost (including both energy consumption cost and user experience loss) by up to 28% compared to existing methods in the literature. Moreover, the performance loss of our proposed method, compared to the global optimal solution, is less than 13.7%. In summary, this work offers a realistic network model, introduces a novel game-based method, and provides extensive performance evaluation, making a significant contribution to both industry and academia.

关键词： Industries Energy consumption Costs Simulation Games Nash equilibrium Energy efficiency Information and communication technology Distributed algorithms Optimization

Generalization-Enhanced Few-Shot Object Detection in Remote Sensing

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Lin, Hui Li, Nan Yao, Pengjuan Dong, Kexin Guo, Yuhan Hong, Danfeng Zhang, Ying Wen, Congcong China Academy of Electronics and Information Technology Beijing100846 China National Satellite Meteorological Center Innovation Center for FengYun Meteorological Satellite China Meteorological Administration Beijing100081 China State Key Laboratory of Hydroscience and Engineering Department of Hydraulic Engineering Tsinghua University Beijing100084 China Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100049 China School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing100083 China Department of Electrical and Computer Engineering New York University Abu Dhabi Abu Dhabi United Arab Emirates

Object detection is a fundamental task in computer vision that involves accurately locating and classifying objects within images or video frames. In remote sensing, this task is particularly challenging due to the high resolution, multi-scale features, and diverse ground object characteristics inherent in satellite and UAV imagery. These challenges necessitate more advanced approaches for effective object detection in such environments. While deep learning methods have achieved remarkable success in remote sensing object detection, they typically rely on large amounts of labeled data. Acquiring sufficient labeled data, particularly for novel or rare objects, is both challenging and time-consuming in remote sensing scenarios, limiting the generalization capabilities of existing models. To address these challenges, few-shot learning (FSL) has emerged as a promising approach, aiming to enable models to learn new classes from limited labeled examples. Building on this concept, few-shot object detection (FSOD) specifically targets object detection challenges in data-limited conditions. However, the generalization capability of FSOD models, particularly in remote sensing, is often constrained by the complex and diverse characteristics of the objects present in such environments. In this paper, we propose the Generalization-Enhanced Few-Shot Object Detection (GE-FSOD) model to improve the generalization capability in remote sensing FSOD tasks. Our model introduces three key innovations: the Cross-Level Fusion Pyramid Attention Network (CFPAN) for enhanced multi-scale feature representation, the Multi-Stage Refinement Region Proposal Network (MRRPN) for more accurate region proposals, and the Generalized Classification Loss (GCL) for improved classification performance in few-shot scenarios. GE-FSOD demonstrates superior robustness and accuracy in remote sensing FSOD tasks through these enhancements. Extensive experiments on the DIOR and NWPU VHR-10 datasets show that our

关键词： Labeled data