检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Luo, Xianrui Peng, Juewen Xian, Ke Wu, Zijin Cao, Zhiguo Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

We consider the problem of realistic bokeh rendering from a single all-in-focus image. Bokeh rendering mimics aesthetic shallow depth-of-field (DoF) in professional photography, but these visual effects generated by existing methods suffer from simple flat background blur and blurred in-focus regions, giving rise to unrealistic rendered results. In this work, we argue that realistic bokeh rendering should i) model depth relations and distinguish in-focus regions, ii) sustain sharp in-focus regions, and iii) render physically accurate Circle of Confusion (CoC). To this end, we present a Defocus to Focus (D2F) framework to learn realistic bokeh rendering by fusing defocus priors with the all-in-focus image and by implementing radiance priors in layered fusion. Since no depth map is provided, we introduce defocus hallucination to integrate depth by learning to focus. The predicted defocus map implies the blur amount of bokeh and is used to guide weighted layered rendering. In layered rendering, we fuse images blurred by different kernels based on the defocus map. To increase the reality of the bokeh, we adopt radiance virtualization to simulate scene radiance. The scene radiance used in weighted layered rendering reassigns weights in the soft disk kernel to produce the CoC. To ensure the sharpness of in-focus regions, we propose to fuse upsampled bokeh images and original images. We predict the initial fusion mask from our defocus map and refine the mask with a deep network. We evaluate our model on a large-scale bokeh dataset. Extensive experiments show that our approach is capable of rendering visually pleasing bokeh effects in complex scenes. In particular, our solution receives the runner-up award in the AIM 2020 Rendering Realistic Bokeh Challenge. © 2023, CC BY-NC-ND.

关键词： image fusion

来源：评论

学校读者我要写书评

暂无评论

Multiple Unmanned Surface Vehicle Coverage control in Dynamic Environments

Multiple Unmanned Surface Vehicle Coverage Control in Dynami...

引用

Neuromorphic Computing (ICNC), International Conference on

作者： Hong Chen Dingxin He Huantao Mao Yong Yang Zhi-Wei Liu School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Huazhong University of Science and Technology Wuhan China

This paper investigates the area coverage problem for multiple Unmanned Surface Vehicles (USVs) in dynamic environments. Multiple USVs are employed to execute the coverage task using the Voronoi Partition method for task allocation. Parameter adaptive laws are employed to estimate the parameters of the sensing function and the Voronoi cell centroids for updating the target positions in dynamic environments. Additionally, considering the influence of water surface disturbances, a nonholonomic underactuated model analysis is conducted for the USV under non-full constraints, resulting in a motion strategy for USVs. This enables the multiple USVs to effectively cover the task area. Finally, simulation results are presented to validate the effectiveness of the coverage scheme designed in this paper and the ability of USVs to effectively cover dynamic environments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Relative-Posture-Fixed Model Predictive Human-Following control with Visibility Constraints in Obstacle Environments 8

Relative-Posture-Fixed Model Predictive Human-Following Cont...

引用

8th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2023

作者： Zhang, Yikun Huang, Jian Yu, Jinqi Zhu, Yaonan Hasegawa, Yasuhisa School of Artificial Intelligence and Automation Huazhong University of Science and Technology Key Laboratory for Image Processing and Intelligent Control Wuhan430074 China Shenzhen Huazhong University of Science and Technology Research Institute ShenZhen518060 China Nagoya University Department of Micronano Mechanical Science and Engineering Nagoya464-8603 Japan

ISBN: (纸本)9798350300178

The relative-posture-fixed human following is critical for the human-robot interaction and cooperation in daily scenes such as domestic service and healthcare. However, few of previous researches have discussed the difficulties faced by mobile robots in the real world, including the limitation of sensing range and hindrance from obstacles. For practicality, in this paper we investigate the relative-posture-fixed following control with collision avoidance and visibility constraints. The control task is formulated as a receding-horizon optimization problem and solved under the Nonlinear Model Predictive control (NMPC) framework, while an Extended Kalman Filter (EKF) based human trajectory predict algorithm is integrated into the robot controller. The effectiveness of the proposed algorithm is verified in a simulation, and the results demonstrate a promising performance of our controller for the human-following task in complicated environments. © 2023 IEEE.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Thermal Safety Analysis and Dynamic control Strategy for Mode Switching Process of Reversible Solid Oxide Cell System

Thermal Safety Analysis and Dynamic Control Strategy for Mod...

引用

Chinese control Conference (CCC)

作者： Wei Zhao Guoqiang Liu Zexin Li Xi Li Key Laboratory of Image Processing and Intelligent Control of Education Ministry School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan Hubei China

Reversible solid oxide cells (rSOC) can operate in both electrolysis mode and in fuel cell mode with high efficiency and reduced cost using the same device for both functions. When used in dynamic operation with intermittent electrical power sources, rSOC system switches from the fuel cell (SOFC) to electrolyzer (SOEC) and vice versa depending on load and grid peculiarities. This can lead to temperature profiles within the stack that can potentially lead to the failure of the stack and eventually the system. In the present work, a system-level dynamic model of rSOC is established and validated against experimental data. Subsequently, detailed dynamic thermal behavior of stack during the switching between the two modes is analyzed, and a temperature management controller based on Model Predict control method (MPC) is proposed. Gas flow and temperature at the stack inlet are controlled by air flow and bypass valves, avoiding problems associated with temperature overshoot during transient operation. The simulation results show that the temperature controller has the ability to follow fast thermal changes while maintaining thermal safety, which indicates the competitiveness of the controller.

关键词：

来源：评论

学校读者我要写书评

暂无评论

When Epipolar Constraint Meets Non-local Operators in Multi-View Stereo

arXiv

引用

arXiv 2023年

作者： Liu, Tianqi Ye, Xinyi Zhao, Weiyue Pan, Zhiyu Shi, Min Cao, Zhiguo Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

Learning-based multi-view stereo (MVS) method heavily relies on feature matching, which requires distinctive and descriptive representations. An effective solution is to apply non-local feature aggregation, e.g., Transformer. Albeit useful, these techniques introduce heavy computation overheads for MVS. Each pixel densely attends to the whole image. In contrast, we propose to constrain non-local feature augmentation within a pair of lines: each point only attends the corresponding pair of epipolar lines. Our idea takes inspiration from the classic epipolar geometry, which shows that one point with different depth hypotheses will be projected to the epipolar line on the other view. This constraint reduces the 2D search space into the epipolar line in stereo matching. Similarly, this suggests that the matching of MVS is to distinguish a series of points lying on the same line. Inspired by this point-to-line search, we devise a line-to-point non-local augmentation strategy. We first devise an optimized searching algorithm to split the 2D feature maps into epipolar line pairs. Then, an Epipolar Transformer (ET) performs non-local feature augmentation among epipolar line pairs. We incorporate the ET into a learning-based MVS baseline, named ET-MVSNet. ET-MVSNet achieves state-of-the-art reconstruction performance on both the DTU and Tanks-and-Temples benchmark with high efficiency. Code is available at https://***/TQTQliu/ET-MVSNet. Copyright © 2023, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Mixture-of-Experts for Open Set Domain Adaptation: A Dual-Space Detection Approach

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年

作者： Du, Zhenbang An, Jiayu Tu, Yunlu Hong, Jiahao Wu, Dongrui Key Laboratory of the Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

Open Set Domain Adaptation (OSDA) copes with the distribution and label shifts between the source and target domains simultaneously, performing accurate classification for known classes while identifying unknown class samples in the target domain. Most existing OSDA approaches, depending on the final image feature space of deep models, require manually-tuned thresholds, and may easily misclassify unknown samples as known classes. Mixture-of-Experts (MoE) could be a remedy. Within an MoE, different experts handle distinct input features, producing unique expert routing patterns for various classes in a routing feature space. As a result, unknown class samples may display different expert routing patterns to known classes. This paper proposes Dual-Space Detection, which exploits the inconsistencies between the image feature space and the routing feature space to detect unknown class samples without any threshold. A Graph Router is further introduced to better make use of the spatial information among the image patches. Experiments on three datasets validated the effectiveness and superiority of our approach. © 2020 IEEE.

关键词： Mixture-of-Experts Open Set Domain Adaptation Routing Feature

来源：评论

学校读者我要写书评

暂无评论

Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity

arXiv

引用

arXiv 2024年

作者： Zhang, Huaxin Xu, Xiaohao Wang, Xiang Zuo, Jialong Huang, Xiaonan Gao, Changxin Zhang, Shanjun Yu, Li Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology China University of Michigan Ann Arbor United States Kanagawa University Japan

How can we enable models to comprehend video anomalies occurring over varying temporal scales and contexts? Traditional Video Anomaly Understanding (VAU) methods focus on frame-level anomaly prediction, often missing the interpretability of complex and diverse real-world anomalies. Recent multimodal approaches leverage visual and textual data but lack hierarchical annotations that capture both short-term and long-term anomalies. To address this challenge, we introduce HIVAU-70k, a large-scale benchmark for hierarchical video anomaly understanding across any granularity. We develop a semi-automated annotation engine that efficiently scales high-quality annotations by combining manual video segmentation with recursive free-text annotation using large language models (LLMs). This results in over 70,000 multi-granular annotations organized at clip-level, event-level, and video-level segments. For efficient anomaly detection in long videos, we propose the Anomaly-focused Temporal Sampler (ATS). ATS integrates an anomaly scorer with a density-aware sampler to adaptively select frames based on anomaly scores, ensuring that the multimodal LLM concentrates on anomaly-rich regions, which significantly enhances both efficiency and accuracy. Extensive experiments demonstrate that our hierarchical instruction data markedly improves anomaly comprehension. The integrated ATS and visual-language model outperform traditional methods in processing long videos. Our benchmark and model are publicly available at https: //***/pipixin321/HolmesVAU. Copyright © 2024, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Temperature Gradient Analyses of a Tubular Solid Oxide Fuel Cell Fueled by Methanol

引用

Transactions of Tianjin University 2023年第1期29卷 14-30页

作者： Qidong Xu Meiting Guo Lingchao Xia Zheng Li Qijiao He Dongqi Zhao Keqing Zheng Meng Ni Department of Building and Real Estate Research Institute for Sustainable Urban Development(RISUD)&Research Institute for Smart Energy(RISE)The Hong Kong Polytechnic UniversityHong Kong 999077China School of Artifi cial Intelligence and Automation Key Laboratory of Image Processing and Intelligent ControlHuazhong University of Science and TechnologyWuhan 430074China School of Low-Carbon Energy and Power Engineering China University of Mining and TechnologyXuzhou 221116China

Thermal management in solid oxide fuel cells(SOFC)is a critical issue due to non-uniform electrochemical reactions and convective fl ows within the ***,a 2D mathematical model is established herein to investigate the thermal responses of a tubular methanol-fueled *** show that unlike the low-temperature condition of 873 K,where the peak temperature gradient occurs at the cell center,it appears near the fuel inlet at 1073 K because of the rapid temperature rise induced by the elevated current *** the large heat convection capacity,excessive air could not eff ectively eliminate the harmful temperature gradient caused by the large current ***,optimal control of the current density by properly selecting the operating potential could generate a local thermal neutral ***,the maximum axial temperature gradient could be reduced by about 18%at 973 K and 20%at 1073 K when the air with a 5 K higher temperature is ***,despite the higher electrochemical performance observed,the cell with a counter-fl ow arrange-ment featured by a larger hot area and higher maximum temperature gradients is not preferable for a ceramic SOFC system considering thermal ***,this study could provide insightful thermal information for the operating condition selection,structure design,and stability assessment of realistic SOFCs combined with their internal reforming process.

关键词： Solid oxide fuel cell Modeling Methanol fuel Temperature gradient Internal reforming

来源：评论

学校读者我要写书评

暂无评论

A Gaze-Guided Human Locomotion Intention Recognition and Volitional control Method for Knee-Ankle Prostheses

引用

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Chen, Xinxing Chen, Zhaokai Wang, Yuxuan Yin, Shucong Chen, Chuheng Huang, Jian Fu, Chenglong Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control Hubei Key Laboratory of Brain-inspired Intelligent Systems School of Artificial Intelligence and Automation Wuhan430074 China Southern University of Science and Technology Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities Shenzhen518055 China Shanghai Jiaotong University Shanghai China

This paper presents a novel gaze-guided volitional control method for knee-ankle prostheses, designed to enhance the precision and intuitiveness of prosthetic control in complex locomotion tasks. The method utilizes an eye-tracking system coupled with an RGBD camera to estimate 3D gaze points, which are then used to construct a gaze attention map. This map serves as the basis for predicting human locomotion intentions, enabling the prosthesis to accurately step on the intended foot placement. Experimental validation was conducted with both a healthy subject and an amputee subject, focusing on level-ground walking and stair ascent tasks. The results demonstrated that the prosthesis could achieve precise foot placement, with a mean error of 1.22 cm ± 3.14 cm for the healthy subject and 3.40 cm ± 0.66 cm for the amputee subject during level-ground walking. In stair ascent tasks, the system successfully adapted to various gait patterns, with the prosthetic joint angles closely matching natural human movements. The proposed method also effectively reduced the root mean square error (RMSE) of 3D gaze estimation to 2.70 cm, 2.63 cm, and 1.97 cm along the x, y, and z axes, respectively. These findings indicate that the gaze-guided volitional control method not only enhances the functionality of knee-ankle prostheses but also offers a more intuitive interface for users, aligning prosthetic actions with the user’s visual focus and intentions. © 2016 IEEE.

关键词： Knee prostheses

来源：评论

学校读者我要写书评

暂无评论

Disentangling Spatial and Temporal Learning for Efficient image-to-Video Transfer Learning

Disentangling Spatial and Temporal Learning for Efficient Im...

引用

International Conference on Computer Vision (ICCV)

作者： Zhiwu Qing Shiwei Zhang Ziyuan Huang Yingya Zhang Changxin Gao Deli Zhao Nong Sang Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Alibaba Group ARC National University of Singapore

Recently, large-scale pre-trained language-image models like CLIP have shown extraordinary capabilities for understanding spatial contents, but naively transferring such models to video recognition still suffers from unsatisfactory temporal modeling capabilities. Existing methods insert tunable structures into or in parallel with the pre-trained model, which either requires back-propagation through the whole pre-trained model and is thus resource-demanding, or is limited by the temporal reasoning capability of the pre-trained structure. In this work, we present DiST, which disentangles the learning of spatial and temporal aspects of videos. Specifically, DiST uses a dual-encoder structure, where a pre-trained foundation model acts as the spatial encoder, and a lightweight network is introduced as the temporal encoder. An integration branch is inserted between the encoders to fuse spatio-temporal information. The disentangled spatial and temporal learning in DiST is highly efficient because it avoids the back-propagation of massive pre-trained parameters. Meanwhile, we empirically show that disentangled learning with an extra network for integration benefits both spatial and temporal understanding. Extensive experiments on five benchmarks show that DiST delivers better performance than existing state-of-the-art methods by convincing gaps. When pre-training on the large-scale Kinetics-710, we achieve 89.7% on Kinetics-400 with a frozen ViT-L model, which verifies the scalability of DiST. Codes and models can be found in https://***/alibaba-mmai-research/DiST.

关键词：

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：