检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Zhang, Xu Yang, Kailun Lin, Jiacheng Yuan, Jin Li, Zhiyong Li, Shutao College of Computer Science and Electronic Engineering Hunan University Changsha410082 China School of Robotics The National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha410082 China College of Electrical and Information Engineering The Key Laboratory of Visual Perception and Artificial Intelligence of Hunan Province Hunan University Changsha410082 China

Integration of diverse visual prompts like clicks, scribbles, and boxes in interactive image segmentation significantly facilitates users’ interaction as well as improves interaction efficiency. However, existing studies primarily encode the position or pixel regions of prompts without considering the contextual areas around them, resulting in insufficient prompt feedback, which is not conducive to performance acceleration. To tackle this problem, this paper proposes a simple yet effective Probabilistic Visual Prompt Unified Transformer (PVPUFormer) for interactive image segmentation, which allows users to flexibly input diverse visual prompts with the probabilistic prompt encoding and feature post-processing to excavate sufficient and robust prompt features for performance boosting. Specifically, we first propose a Probabilistic Prompt-unified Encoder (PPuE) to generate a unified one-dimensional vector by exploring both prompt and non-prompt contextual information, offering richer feedback cues to accelerate performance improvement. On this basis, we further present a Prompt-to-Pixel Contrastive (P2C) loss to accurately align both prompt and pixel features, bridging the representation gap between them to offer consistent feature representations for mask prediction. Moreover, our approach designs a Dual-cross Merging Attention (DMA) module to implement bidirectional feature interaction between image and prompt features, generating notable features for performance improvement. A comprehensive variety of experiments on several challenging datasets demonstrates that the proposed components achieve consistent improvements, yielding state-of-the-art interactive segmentation performance. Our code is available at https://***/XuZhang1211/PVPUFormer. Copyright © 2023, The Authors. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

MonoDiff9D: Monocular Category-Level 9D Object Pose Estimation via Diffusion Model

arXiv

引用

arXiv 2025年

作者： Liu, Jian Sun, Wei Yang, Hui Zheng, Jin Geng, Zichen Rahmani, Hossein Mian, Ajmal National Engineering Research Center for Robot Visual Perception and Control Technology College of Electrical and Information Engineering China School of Robotics Hunan University Changsha410082 China Central South University Changsha410082 China Lancaster University LA1 4YW United Kingdom The University of Western Australia WA6009 Australia

Object pose estimation is a core means for robots to understand and interact with their environment. For this task, monocular category-level methods are attractive as they require only a single RGB camera. However, current methods rely on shape priors or CAD models of the intra-class known objects. We propose a diffusion-based monocular category-level 9D object pose generation method, MonoDiff9D. Our motivation is to leverage the probabilistic nature of diffusion models to alleviate the need for shape priors, CAD models, or depth sensors for intra-class unknown object pose estimation. We first estimate coarse depth via DINOv2 from the monocular image in a zero-shot manner and convert it into a point cloud. We then fuse the global features of the point cloud with the input image and use the fused features along with the encoded time step to condition MonoDiff9D. Finally, we design a transformer-based denoiser to recover the object pose from Gaussian noise. Extensive experiments on two popular benchmark datasets show that MonoDiff9D achieves state-of-the-art monocular category-level 9D object pose estimation accuracy without the need for shape priors or CAD models at any stage. Our code will be made public at https://***/CNJianLiu/MonoDiff9D. Copyright © 2025, The Authors. All rights reserved.

关键词： Image coding

来源：评论

学校读者我要写书评

暂无评论

E-3DGS: 3D Gaussian Splatting with Exposure and Motion Events

arXiv

引用

arXiv 2024年

作者： Yin, Xiaoting Shi, Hao Bao, Yuhan Bing, Zhenshan Liao, Yiyi Yang, Kailun Wang, Kaiwei State Key Laboratory of Modern Optical Instrumentation Zhejiang University China School of Robotics and National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University China College of Information Science and Electronic Engineering Zhejiang University China The Chair of Robotics AI and Real-Time Systems Technical University of Munich Germany

Achieving 3D reconstruction from images captured under optimal conditions has been extensively studied in the vision and imaging fields. However, in real-world scenarios, challenges such as motion blur and insufficient illumination often limit the performance of standard frame-based cameras in delivering high-quality images. To address these limitations, we incorporate a transmittance adjustment device at the hardware level, enabling event cameras to capture both motion and exposure events for diverse 3D reconstruction scenarios. Motion events (triggered by camera or object movement) are collected in fast-motion scenarios when the device is inactive, while exposure events (generated through controlled camera exposure) are captured during slower motion to reconstruct grayscale images for high-quality training and optimization of event-based 3D Gaussian Splatting (3DGS). Our framework supports three modes: High-Quality Reconstruction using exposure events, Fast Reconstruction relying on motion events, and Balanced Hybrid optimizing with initial exposure events followed by high-speed motion events. On the EventNeRF dataset, we demonstrate that exposure events significantly improve fine detail reconstruction compared to motion events and outperform frame-based cameras under challenging conditions such as low illumination and overexposure. Furthermore, we introduce EME-3D, a real-world 3D dataset with exposure events, motion events, camera calibration parameters, and sparse point clouds. Our method achieves faster and higher-quality reconstruction than event-based NeRF and is more cost-effective than methods combining event and RGB data. By combining motion and exposure events, E-3DGS sets a new benchmark for event-based 3D reconstruction with robust performance in challenging conditions and lower hardware demands. The source code and dataset will be available at https://***/MasterHow/E-3DGS. Copyright © 2024, The Authors. All rights reserved.

关键词： Exposure controls

来源：评论

学校读者我要写书评

暂无评论

Implicit Modality Mining: An End-to-End Method for Multimodal Information Extraction

引用

Journal of Electronic research and Application 2024年第2期8卷 124-139页

作者： Jinle Lu Qinglang Guo School of Cyber Science and Technology University of Science and Technology of ChinaHefei 230027Anhui ProvinceChina National Engineering Research Center for Public Safety Risk Perception and Control by Big Data(RPP) CETC Academy of Electronics and Information Technology Group Co.Ltd.China Academic of Electronics and Information TechnologyBeijing 100041China

Multimodal named entity recognition(MNER)and relation extraction(MRE)are key in social media analysis but face challenges like inefficient visual processing and non-optimal modality interaction.(1)Heavy visual embedding:the process of visual embedding is both time and computationally expensive due to the prerequisite extraction of explicit visual cues from the original image before input into the multimodal ***,these approaches cannot achieve efficient online reasoning;(2)suboptimal interaction handling:the prevalent method of managing interaction between different modalities typically relies on the alternation of self-attention and cross-attention mechanisms or excessive dependence on the gating *** explicit modeling method may fail to capture some nuanced relations between image and text,ultimately undermining the model’s capability to extract optimal *** address these challenges,we introduce Implicit Modality Mining(IMM),a novel end-to-end framework for fine-grained image-text correlation without heavy visual *** uses an Implicit Semantic Alignment module with a Transformer for cross-modal clues and an Insert-Activation module to effectively utilize these *** approach achieves state-of-the-art performance on three datasets.

关键词： Multimodal Named entity recognition Relation extraction Patch projection

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Path Finding Using Imitation-Reinforcement Learning with Transformer

Multi-Agent Path Finding Using Imitation-Reinforcement Learn...

引用

IEEE International Conference on robotics and Biomimetics

作者： Lin Chen Yaonan Wang Zhiqiang Miao Yang Mo Mingtao Feng Zhen Zhou School of Electrical and Information Engineering Hunan University Changsha China National Engineering Research Center for Robot Visual Perception and Control Technology Changsha China School of Computer Science and Technology Xidian University Xian China

ISBN: (纸本)9781665481106

Multi-Agent Path Finding is a problem of finding the optimal set of paths for multiple agents from the starting position to the goal without conflict, which is essential to large-scale robotic systems. Imitation and reinforcement learning are applied to solve the MAPF problem and have achieved certain results, which provides a feasible solution for the path planning problem of large-scale robot systems. The current method improves the performance of distributed strategy-guided agent planning paths in complex environments by introducing the communication between graph neural networks and agents but dramatically reduces the system's robustness. This paper develops a novel imitation reinforcement learning framework by introducing Transformer, which enables algorithms to perform well in complex environments without relying on communication between agents. Compared with its counterparts, experiments show that the policy trained by our method guides the agent to drive from the initial position to the goal without collision and achieve better performance.

关键词： Learning systems robot kinematics Biomimetics Reinforcement learning Transformers Robustness Path planning

来源：评论

学校读者我要写书评

暂无评论

HierDAMap: Towards Universal Domain Adaptive BEV Mapping via Hierarchical Perspective Priors

arXiv

引用

arXiv 2025年

作者： Li, Siyu Cao, Yihong Shi, Hao Zang, Yongsheng He, Xuan Yang, Kailun Li, Zhiyong School of Robotics the National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha410082 China State Key Laboratory of Extreme Photonics and Instrumentation Zhejiang University Hangzhou310027 China College of Computer Science and Electronic Engineering Hunan University Changsha410082 China Hunan Vanguard Group Corporation Limited Changsha410100 China

The exploration of Bird’s-Eye View (BEV) mapping technology has driven significant innovation in visual perception technology for autonomous driving. BEV mapping models need to be applied to the unlabeled real world, making the study of unsupervised domain adaptation models an essential path. However, research on unsupervised domain adaptation for BEV mapping remains limited and cannot perfectly accommodate all BEV mapping tasks. To address this gap, this paper proposes HierDAMap, a universal and holistic BEV domain adaptation framework with hierarchical perspective priors. Unlike existing research that solely focuses on image-level learning using prior knowledge, this paper explores the guiding role of perspective prior knowledge across three distinct levels: global, sparse, and instance levels. With these priors, HierDA consists of three essential components, including Semantic-Guided Pseudo Supervision (SGPS), Dynamic-Aware Coherence Learning (DACL), and Cross-Domain Frustum Mixing (CDFM). SGPS constrains the cross-domain consistency of perspective feature distribution through pseudo labels generated by vision foundation models in 2D space. To mitigate feature distribution discrepancies caused by spatial variations, DACL employs uncertainty-aware predicted depth as an intermediary to derive dynamic BEV labels from perspective pseudo-labels, thereby constraining the coarse BEV features derived from corresponding perspective features. CDFM, on the other hand, leverages perspective masks of view frustum to mix multi-view perspective images from both domains, which guides cross-domain view transformation and encoding learning through mixed BEV labels. Furthermore, this paper introduces intra-domain feature exchange data augmentation to enhance the efficiency of domain adaptation learning. The proposed method is verified on multiple BEV mapping tasks, such as BEV semantic segmentation, high-definition semantic, and vectorized mapping. It demonstrates competitive perfo

关键词： Birds

来源：评论

学校读者我要写书评

暂无评论

Decentralized Multi-robot Navigation Coupled with Spatial-Temporal RetNet Based on Deep Reinforcement Learning

Decentralized Multi-Robot Navigation Coupled with Spatial-Te...

引用

IEEE/RSJ International Conference on Intelligent robots and Systems (IROS)

作者： Lin Chen Yaonan Wang Zhiqiang Miao Mingtao Feng Yuanzhe Wang Yang Mo Zhen Zhou Hesheng Wang Danwei Wang School of Electrical and Information Engineering Hunan University Changsha China National Engineering Research Center for Robot Visual Perception and Control Technology Changsha China School of Artificial Intelligence Xidian University Xian China School of Electrical and Electrical Engineering Nanyang Technological University Nanyang Avenue Singapore Department of Automation Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Navigating robots through dynamic multi-robot environments, avoiding collisions with both other robots and obstacles, has emerged as a central challenge in robotics. The existing approaches fall short in allowing the policy network to effectively capture spatial-temporal reciprocal collision avoidance in multi-robot environments, comprising both static and dynamic obstacles, resulting in inadequate safety and efficiency in directing robot movement. In this study, we introduce a novel policy neural network called Spatial-Temporal RetNet (STR), designed to encode reciprocal collision avoidance states between robots in spatial and temporal dimensions. The goal is to improve the safety and efficacy of the policy neural network in directing robots to complete assigned tasks. The spatial state encoder module is built upon a parallel RetNet structure, which strengthens the neural network's capacity in extracting reciprocal collision avoidance states between robots in spatial dimensions. This module addresses the limitations of position encoding in transformer-based multi-robot navigation policy neural networks. We design a temporal state encoder utilizing a recurrent RetNet structure. This innovation bolsters the multi-robot navigation policy neural network's capability to capture features in the temporal dimension of multi-robot movements. It addresses the limitations of transformer-based multi-robot navigation policy neural networks, particularly in recurrently inferring information across time dimensions. Simulation experiments were conducted to showcase the superior safety and effectiveness of our proposed method compared to previous state-of-the-art approaches in guiding robots to accomplish tasks.

关键词： Training Technological innovation Navigation Neural networks Transformers Feature extraction Encoding Safety Collision avoidance robots

来源：评论

学校读者我要写书评

暂无评论

Efficient Photothermal Catalytic Oxidation Enabled by Three-Dimensional Nanochannel Substrates

引用

Environmental Science and technology 2024年第11期58卷 5153-5161页

作者： Li, Yifei Zhang, Qianpeng Chong, Yanan Huang, Wei-Hsiang Chen, Chi-Liang Jin, Xiaojing Chen, Guangxu Fan, Zhiyong Qiu, Yongcai Ye, Daiqi School of Environment and Energy State Key Laboratory of Luminescent Materials and Devices Guangdong Provincial Key Laboratory of Atmospheric Environment and Pollution Control South China University of Technology Guangdong Guangzhou510000 China State Key Laboratory of Photovoltaic Science and Technology Shanghai Frontiers Science Research Base of Intelligent Optoelectronics and Perception Institute of Optoelectronics Fudan University Shanghai200433 China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Clear Water Bay Kowloon999077 Hong Kong State Key Laboratory of Advanced Displays and Optoelectronics Technologies The Hong Kong University of Science and Technology Clear Water Bay Kowloon999077 Hong Kong National Synchrotron Radiation Research Center 101 Hsin-Ann Road Hsinchu Science Park Hsinchu30076 Taiwan Taipei10607 Taiwan College of Light Chemical Industry and Materials Engineering Shunde Polytechnic Foshan528333 China

Photothermal catalysis exhibits promising prospects to overcome the shortcomings of high-energy consumption of traditional thermal catalysis and the low efficiency of photocatalysis. However, there is still a challenge to develop catalysts with outstanding light absorption capability and photothermal conversion efficiency for the degradation of atmospheric pollutants. Herein, we introduced the Co3O4 layer and Pt nanoclusters into the three-dimensional (3D) porous membrane through the atomic layer deposition (ALD) technique, leading to a Pt/Co3O4/AAO monolithic catalyst. The 3D ordered nanochannel structure can significantly enhance the solar absorption capacity through the light-trapping effect. Therefore, the embedded Pt/Co3O4 catalyst can be rapidly heated and the O2 adsorbed on the Pt clusters can be activated to generate sufficient O2- species, exhibiting outstanding activity for the diverse VOCs (toluene, acetone, and formaldehyde) degradation. Optical characterization and simulation calculation confirmed that Pt/Co3O4/AAO exhibited state-of-the-art light absorption and a notable localized surface plasmon resonance (LSPR) effect. In situ diffuse reflectance infrared Fourier transform spectrometry (in situ DRIFTS) studies demonstrated that light irradiation can accelerate the conversion of intermediates during toluene and acetone oxidation, thereby inhibiting byproduct accumulation. Our finding extends the application of AAO’s optical properties in photothermal catalytic degradation of air pollutants. © 2024 American Chemical Society.

关键词： Catalysis

来源：评论

学校读者我要写书评

暂无评论

Representing Domain-Mixing Optical Degradation for Real-World Computational Aberration Correction via Vector Quantization

arXiv

引用

arXiv 2024年

作者： Jiang, Qi Yi, Zhonghua Gao, Shaohua Gao, Yao Qian, Xiaolong Shi, Hao Sun, Lei Niu, JinXing Wang, Kaiwei Yang, Kailun Bai, Jian State Key Laboratory of Extreme Photonics and Instrumentation College of Optical Science and Engineering Zhejiang University Hangzhou310027 China National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha410082 China Intelligent Optics & Photonics Research Center Jiaxing Research Institute Zhejiang University Jiaxing314031 China School of Mechanical Engineering North China University of Water Resources and Electric Power Zhenzhou450045 China

Relying on paired synthetic data, existing learning-based Computational Aberration Correction (CAC) methods are confronted with the intricate and multifaceted synthetic-to-real domain gap, which leads to suboptimal performance in real-world applications. In this paper, in contrast to improving the simulation pipeline, we deliver a novel insight into real-world CAC from the perspective of Unsupervised Domain Adaptation (UDA). By incorporating readily accessible unpaired real-world data into training, we formalize the Domain Adaptive CAC (DACAC) task, and then introduce a comprehensive Real-world aberrated images (Realab) dataset to benchmark it. The setup task presents a formidable challenge due to the intricacy of understanding the target optical degradation domain. To this intent, we propose a novel Quantized Domain-Mixing Representation (QDMR) framework as a potent solution to the issue. centering around representing and quantizing the optical degradation which is consistent across different images, QDMR adapts the CAC model to the target domain from three key aspects: (1) reconstructing aberrated images of both domains by a VQGAN to learn a Domain-Mixing Codebook (DMC) characterizing the optical degradation;(2) modulating the deep features in CAC model with DMC to transfer the target domain knowledge;and (3) leveraging the trained VQGAN to generate pseudo target aberrated images from the source ones for convincing target domain supervision. Extensive experiments on both synthetic and real-world benchmarks reveal that the models with QDMR consistently surpass the competitive methods in mitigating the synthetic-to-real gap, which produces visually pleasant real-world CAC results with fewer artifacts. Codes and datasets are made publicly available at https://***/zju-jiangqi/QDMR. Copyright © 2024, The Authors. All rights reserved.

关键词： Vector quantization

来源：评论

学校读者我要写书评

暂无评论

LF-PGVIO: A Visual-Inertial-Odometry Framework for Large Field-of-View Cameras using Points and Geodesic Segments

arXiv

引用

arXiv 2023年

作者： Wang, Ze Yang, Kailun Shi, Hao Zhang, Yufan Xu, Zhijie Gao, Fei Wang, Kaiwei The State Key Laboratory of Extreme Photonics and Instrumentation The National Engineering Research Center of Optical Instrumentation Zhejiang University Hangzhou310027 China The School of Robotics The National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha410082 China The School of Computing and Engineering University of Huddersfield HuddersfieldHD1 3DH United Kingdom The State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou310027 China

In this paper, we propose LF-PGVIO, a Visual-Inertial-Odometry (VIO) framework for large Field-of-View (FoV) cameras with a negative plane using points and geodesic segments. The purpose of our research is to unleash the potential of point-line odometry with large-FoV omnidirectional cameras, even for cameras with negative-plane FoV. To achieve this, we propose an Omnidirectional Curve Segment Detection (OCSD) method combined with a camera model which is applicable to images with large distortions, such as panoramic annular images, fisheye images, and various panoramic images. The geodesic segment is sliced into multiple straight-line segments based on the radian and descriptors are extracted and recombined. Descriptor matching establishes the constraint relationship between 3D line segments in multiple frames. In our VIO system, line feature residual is also extended to support large-FoV cameras. Extensive evaluations on public datasets demonstrate the superior accuracy and robustness of LF-PGVIO compared to state-of-the-art methods. The source code will be made publicly available at https://***/flysoaryun/LF-PGVIO. Copyright © 2023, The Authors. All rights reserved.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：