检索结果-内蒙古大学图书馆

An Iterative Deep Homography Network Based on Correlation Content Calculation for High-Precision Image Registration of Fly-Capture Imaging System

学校读者我要写书评

暂无评论

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Qiu Fang Changqing Gao Tianjian Jiang Xianen Zhou Yaonan Wang National Engineering Research Center for Robot Visual Perception and Control Technology School of Electrical and Information Engineering Hunan University Changsha Hunan China Jiangxi Communication Terminal Industry Technology Research Institute Company Ltd. Ji’an Jiangxi China

This article presents a novel iterative deep homography network based on correlation content calculation (IDHN-CCC) for high-precision image registration of a fly-capture imaging system. The new high-precision fly-capture imaging (HFI) system is designed to obtain high-resolution images of radar microwave components (RMCs) and improve surface defect detection efficiency and autonomy while reducing hardware costs. The HFI consists of four subsystems: image acquisition mechanism, control system, image registration algorithm, and software system, which could achieve clear capture and precise imaging of RMC at high speed. The system adopts the IDHN-CCC algorithm to reduce the impact of motion errors on imaging stitching quality, which does not rely on precise camera motion positioning and coordinate transformation to achieve high-precision registration of multiple continuous shooting images. The experimental studies demonstrated the advantages of the IDHN-CCC-based HFI, which can achieve RMC images in low overlap rate fly-capture scenes with high registration accuracy.

关键词： Imaging Image registration Feature extraction control systems Accuracy Radar imaging Cameras Microwave imaging Costs Estimation

Diff9D: Diffusion-Based Domain-Generalized Category-Level 9-DoF Object Pose Estimation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Liu, Jian Sun, Wei Yang, Hui Deng, Pengchao Liu, Chongpei Sebe, Nicu Rahmani, Hossein Mian, Ajmal National Engineering Research Center for Robot Visual Perception and Control Technology College of Electrical and Information Engineering School of Robotics State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Hunan University Changsha410082 China Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an710049 China Department of Information Engineering and Computer Science University of Trento Trento38123 Italy School of Computing and Communications Lancaster University LA1 4YW United Kingdom Department of Computer Science The University of Western Australia WA6009 Australia

Nine-degrees-of-freedom (9-DoF) object pose and size estimation is crucial for enabling augmented reality and robotic manipulation. Category-level methods have received extensive research attention due to their potential for generalization to intra-class unknown objects. However, these methods require manual collection and labeling of large-scale real-world training data. To address this problem, we introduce a diffusion-based paradigm for domain-generalized category-level 9-DoF object pose estimation. Our motivation is to leverage the latent generalization ability of the diffusion model to address the domain generalization challenge in object pose estimation. This entails training the model exclusively on rendered synthetic data to achieve generalization to real-world scenes. We propose an effective diffusion model to redefine 9-DoF object pose estimation from a generative perspective. Our model does not require any 3D shape priors during training or inference. By employing the Denoising Diffusion Implicit Model, we demonstrate that the reverse diffusion process can be executed in as few as 3 steps, achieving near real-time performance. Finally, we design a robotic grasping system comprising both hardware and software components. Through comprehensive experiments on two benchmark datasets and the real-world robotic system, we show that our method achieves state-of-the-art domain generalization performance. Our code will be made public at https://***/CNJianLiu/Diff9D. Copyright © 2025, The Authors. All rights reserved.

关键词： Augmented reality

Globally-Optimal Contrast Maximisation for Event Cameras

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Peng, Xin Gao, Ling Wang, Yifu Kneip, Laurent The Mobile Perception Lab of School of Information Science and Technology ShanghaiTech University The Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences University of Chinese Academy of Sciences China The Mobile Perception Lab of School of Information Science and Technology ShanghaiTech University China The Shanghai Engineering Research Center of Intelligent Vision and Imaging China The Australian National University Australia

Event cameras are bio-inspired sensors that perform well in challenging illumination conditions and have high temporal resolution. However, their concept is fundamentally different from traditional frame-based cameras. The pixels of an event camera operate independently and asynchronously. They measure changes of the logarithmic brightness and return them in the highly discretised form of time-stamped events indicating a relative change of a certain quantity since the last event. New models and algorithms are needed to process this kind of measurements. The present work looks at several motion estimation problems with event cameras. The flow of the events is modelled by a general homographic warping in a space-time volume, and the objective is formulated as a maximisation of contrast within the image of warped events. Our core contribution consists of deriving globally optimal solutions to these generally non-convex problems, which removes the dependency on a good initial guess plaguing existing methods. Our methods rely on branch-and-bound optimisation and employ novel and efficient, recursive upper and lower bounds derived for six different contrast estimation functions. The practical validity of our approach is demonstrated by a successful application to three different event camera motion estimation problems. Copyright © 2022, The Authors. All rights reserved.

关键词： Motion estimation

CoBEV: Elevating Roadside 3D Object Detection with Depth and Height Complementarity

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Shi, Hao Pang, Chengshan Zhang, Jiaming Yang, Kailun Wu, Yuhao Ni, Huajian Lin, Yining Stiefelhagen, Rainer Wang, Kaiwei The State Key Laboratory of Extreme Photonics and Instrumentation Zhejiang University Hangzhou310027 China The Institute for Anthropomatics and Robotics Karlsruhe Institute of Technology Karlsruhe76131 Germany The Department of Engineering Science University of Oxford OxfordOX1 3PJ United Kingdom The School of Robotics Hunan University Changsha410012 China The National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha410082 China Shanghai SUPREMIND Technology Co. Ltd. Shanghai201210 China

Roadside camera-driven 3D object detection is a crucial task in intelligent transportation systems, which extends the perception range beyond the limitations of vision-centric vehicles and enhances road safety. While previous studies have limitations in using only depth or height information, we find both depth and height matter and they are in fact complementary. The depth feature encompasses precise geometric cues, whereas the height feature is primarily focused on distinguishing between various categories of height intervals, essentially providing semantic context. This insight motivates the development of Complementary-BEV (CoBEV), a novel end-to-end monocular 3D object detection framework that integrates depth and height to construct robust BEV representations. In essence, CoBEV estimates each pixel's depth and height distribution and lifts the camera features into 3D space for lateral fusion using the newly proposed two-stage complementary feature selection (CFS) module. A BEV feature distillation framework is also seamlessly integrated to further enhance the detection accuracy from the prior knowledge of the fusion-modal CoBEV teacher. We conduct extensive experiments on the public 3D detection benchmarks of roadside camera-based DAIR-V2X-I and Rope3D, as well as the private Supremind-Road dataset, demonstrating that CoBEV not only achieves the accuracy of the new state-of-the-art, but also significantly advances the robustness of previous methods in challenging long-distance scenarios and noisy camera disturbance, and enhances generalization by a large margin in heterologous settings with drastic changes in scene and camera parameters. For the first time, the vehicle AP score of a camera model reaches 80% on DAIR-V2X-I in terms of easy mode. The source code will be made publicly available at CoBEV. Copyright © 2023, The Authors. All rights reserved.

关键词： Feature Selection

Exploring Video-Based Driver Activity Recognition under Noisy Labels

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Fan, Linjuan Wen, Di Peng, Kunyu Yang, Kailun Zhang, Jiaming Liu, Ruiping Chen, Yufan Zheng, Junwei Wu, Jiamin Han, Xudong Stiefelhagen, Rainer Institute for Anthropomatics and Robotics Karlsruhe Institute of Technology Germany School of Robotics National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha China Shanghai AI Lab China University of Sussex United Kingdom

As an open research topic in the field of deep learning, learning with noisy labels has attracted much attention and grown rapidly over the past ten years. Learning with label noise is crucial for driver distraction behavior recognition, as real-world video data often contains mislabeled samples, impacting model reliability and performance. However, label noise learning is barely explored in the driver activity recognition field. In this paper, we propose the first label noise learning approach for the driver activity recognition task. Based on the cluster assumption, we initially enable the model to learn clustering-friendly low-dimensional representations from given videos and assign the resultant embeddings into clusters. We subsequently perform co-refinement within each cluster to smooth the classifier outputs. Furthermore, we propose a flexible sample selection strategy that combines two selection criteria without relying on any hyperparameters to filter clean samples from the training dataset. We also incorporate a self-adaptive parameter into the sample selection process to enforce balancing across classes. A comprehensive variety of experiments on the public Drive&Act dataset for all granularity levels demonstrates the superior performance of our method in comparison with other label-denoising methods derived from the image classification field. The source code is available at https://***/ilonafan/DAR-noisy-labels. Copyright © 2025, The Authors. All rights reserved.

关键词： Object recognition

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

10 GHz Robust polarization modulation towards high-speed satellite-based quantum communication

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Zexu Xu, Huaxing Li, Ju Huang, Jinquan Han, Hui Wang, Changlei Zhang, Ping Yin, Feifei Xu, Kun Liu, Bo Dai, Yitang State Key Laboratory of Information Photonics and Optical Communications Beijing University of Posts and Telecommunications Beijing100876 China National Engineering Research Center for Public Safety Risk Perception and Control by Big Data China Academy of Electronics and Information Technology Beijing100041 China CETC Academy of Electronics and Information Technology Group Co. Ltd. Beijing100041 China College of Advanced Interdisciplinary Studies National University of Defense Technology Changsha410073 China School of Electronics and Communication Engineering Sun Yat-sen University Guangdong Shenzhen518107 China College of Computer National University of Defense Technology Changsha4100730 China

In practical satellite-based quantum key distribution (QKD) systems, the preparation and transmission of polarization-encoding photons suffer from complex environmental effects and high channel-loss. Consequently, the hinge to enhancing the secure key rate (SKR) lies in achieving robust, low-error and high-speed polarization modulation. Although the schemes that realize self-compensation exhibit remarkable robustness. Their modulation speed is constrained to approximately 2 GHz to avoid the interaction between the electrical signal and the reverse optical pulses. Here we utilize the non-reciprocity of the lithium niobate modulators and eliminate the modulation on the reverse optical pulses. As this characteristic is widely available in the radio-frequency band, the modulation speed is no longer limited by the self-compensating optics and can be further increased. The measured average intrinsic QBER of the different polarization states at 10 GHz system repetition frequency is as low as 0.53% over 10 min without any compensation. And the experiment simulation shows that the proposed scheme extends the transmission distance to more than 350 km. Our work can be be efficient performed to the high-speed and high-loss satellite-based quantum communication scenario. © 2024, CC BY.

关键词： Quantum communication

A Novel Pose Estimation Method of Object in robotic Manipulation Using vision-Based Tactile Sensor 5th

学校读者我要写书评

暂无评论

A Novel Pose Estimation Method of Object in Robotic Manipula...

5th International Conference on Cognitive Systems and Signal Processing, ICCSIP 2020

作者： Zhao, Dan Sun, Fuchun Zhou, Quan Wang, Zongtao Beijing National Research Center for Information Science and Technology Department of Computer Science and Technology Tsinghua University Beijing100083 China AnHui Province Key Laboratory of Special Heavy Load Robot Anhui University of Technology Ma Anshan China Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University Qinhuangdao066000 China

ISBN: (纸本)9789811623356

The computer vision techniques have been widely used in the robotic manipulation for perception and positioning. However, duo to the inaccuracy of camera calibration and measurement, there is a greatly need for more accurate method to estimate the object pose especially for robotic precise manipulation. In this paper, we propose a novel pose estimation method of object in robotic manipulation using a vision-based tactile sensor. The structure of the tactile sensor and the proposed model are introduced in detail, and verification experiments have been performed. The results show the advantages and better performance of the proposed method. © 2021, Springer Nature Singapore Pte Ltd.

关键词： robot vision

Combining Transformer and Convolutional Neural Network for Smoke Detection 9th

学校读者我要写书评

暂无评论

Combining Transformer and Convolutional Neural Network for...

9th International Forum on Digital Multimedia Communication, IFTC 2022

作者： Gong, Yafei Lian, Xinkang Ma, Xuanchao Xia, Zhifang Zhou, Chengxu Faculty of Information Technology Beijing University of Technology Beijing China Engineering Research Center of Intelligent Perception and Autonomous Control Ministry of Education Beijing China Beijing Laboratory of Smart Environmental Protection Beijing China Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing China Beijing Artificial Intelligence Institute Beijing China National Information Center Beijing China School of Electronic and Information Engineering Liaoning University of Technology Liaoning Jinzhou China Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian University of Technology Dalian China

ISBN: (纸本)9789819908554

Smoke detection plays a crucial role in the safety production of petrochemical enterprises and fire prevention. Image-based machine learning and deep learning methods have been widely studied. Recently, many works have applied the transformer to solve problems faced by computer vision tasks (such as classification and object detection). To our knowledge, there are few studies using the transformer structure to detect smoke. In order to research the application potential and improve the performance of the transformer in the smoke detection field, we propose a model consisting of two transformer encoders and a convolutional neural network (CNN) module. The first transformer encoder can be used to establish the global relationship of an image, and the CNN structure can provide additional local information to the transformer. The fusion of global information and local information is conducive to the second transfer encoder to make better decisions. Experiments results on large-size dataset for industrial smoke detection illustrate the effectiveness of the proposed model. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Smoke