检索结果-内蒙古大学图书馆

Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)

作者： Yuta Iinuma Takuto Ozawa Sou Nobukawa Nobuhiko Wagatsuma Keiichiro Inagaki Graduate School of Information and Computer Science Chiba Institute of Technology Japan Department of Computer Science Chiba Institute of Technology Narashino Japan Department of Information Science Toho University Japan Department of Artificial Intelligence and Robotics Chubu University Japan

To further reduce the number of traffic accidents, it has been necessary in recent years to develop advanced driver assistance systems with functions that provide optimal assistance based on driving performance. Recent studies have used electroencephalogram (EEG) to comprehensively evaluate the complex neural process of visual, perceptual, attentional, and motor functions. Microstate analysis, which reflects the interactions of global neural networks by measuring the temporal transition of brain activity, is widely used to capture complex cognitive processes. In this context, we hypothesized that microstate analysis is a suitable method for capturing driving-experience-dependent performance using EEG. To prove our hypothesis, we evaluated the EEG data of novice and expert drivers while they viewed driving scenes using microstate analysis to detect driving-experience-dependent performance using EEG. The results showed that the dynamic characteristic of EEG concerning driving-experience-dependent performance reflected efficient cognitive control and suppressed redundant bottom-up attention. This finding may be widely utilized for estimating the driving-experience-dependent performance of advanced driver assistant systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pixel-Level Semantic Correspondence Through Layout-Aware Representation Learning and Multi-Scale Matching Integration

Pixel-Level Semantic Correspondence Through Layout-Aware Rep...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Yixuan Sun Zhangyue Yin Haibo Wang Yan Wang Xipeng Qiu Weifeng Ge Wenqiang Zhang Academy for Engineering & Technology Fudan University Shanghai China Engineering Research Center of AI & Robotics Ministry of Education China School of Computer Science Fudan University Shanghai China

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Establishing precise semantic correspondence across object instances in different images is a fundamental and challenging task in computer vision. In this task, difficulty arises often due to three challenges: confusing regions with similar appearance, inconsistent object scale, and indistinguishable nearby pixels. Recognizing these challenges, our paper proposes a novel semantic matching pipeline named LPMFlow toward extracting fine-grained semantics and geometry layouts for building pixel-level semantic correspondences. LPMFlow consists of three modules, each addressing one of the aforementioned challenges. The layout-aware representation learning module uniformly encodes source and target tokens to distinguish pixels or regions with similar appearances but different geometry semantics. The progressive feature superresolution module outputs four sets of 4D correlation tensors to generate accurate semantic flow between objects in different scales. Finally, the matching flow integration and refinement module is exploited to fuse matching flow in different scales to give the final flow predictions. The whole pipeline can be trained end-to-end, with a balance of computational cost and correspondence details. Extensive experiments based on benchmarks such as SPair-71K, PF-PASCAL, and PF-WILLOW have proved that the proposed method can well tackle the three challenges and outperform the previous methods, es-pecially in more stringent settings. Code is available at https://***/YXSUNMADMAX/LPMFlow.

关键词： Representation learning geometry computer vision Tensors Fuses Semantics Pipelines

来源：评论

学校读者我要写书评

暂无评论

Design of a Novel Latch with Quadruple-Node-Upset Recovery for Harsh Radiation Hardness

Design of a Novel Latch with Quadruple-Node-Upset Recovery f...

引用

International Test Conference in Asia (ITC-Asia)

作者： Aibin Yan Chao Zhou Shaojie Wei Jie Cui Zhengfeng Huang Patrick Girard Xiaoqing Wen School of Computer Science and Technology Anhui University Hefei China School of Microelectronics Hefei University of Technology Hefei China Laboratory of Informatics Robotics and Microelectronics of Montpellier University of Montpellier / CNRS Montpellier France Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology Fukuoka Japan

As CMOS processes continue to shrink, nano-scale CMOS latches have become increasingly sensitive to multiple-node upset (MNU) errors caused by radiation. To tolerate MNU, a novel quadruple-node-upset (QNU) self-recoverable latch is proposed in this paper. The proposed latch is mainly constructed from six blocks of three-level C-elements (TLCEs) and six inverters. With the mutual feedback of the various TLCEs, the proposed latch can recover from any QNU. Furthermore, due to the clock gating methodology and a high-speed transmission path, the proposed latch has lower overhead in terms of power dissipation and transmission delay. Simulation results show that the proposed latch achieves high reliability with moderate overhead compared to typical existing latches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improved 3D photon counting imaging using singular value decomposition (SVD)

Improved 3D photon counting imaging using singular value dec...

引用

International Conference on Control, Automation and Systems ( ICCAS)

作者： Seungwoo Song Gilsu Yeo Hyun-Woo Kim Myungjin Cho Min-Chul Lee Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology Iizuka City Fukuoka Japan School of ICT Robotics and Mechanical Engineering IITC Hankyoung National University Anseong Republic of Koera

ISBN: (数字)9788993215380

ISBN: (纸本)9798331517939

In this paper, we propose improved three-dimensional (3D) photon counting imaging using singular value decomposition (SVD). In conventional 3D photon counting imaging can visualize 3D image under photon-starved conditions. However, the conventional method has problems that it may not visualize 3D image under extremely photon-starved conditions and the quality of visualized image may be degraded. To solve this problem, we apply SVD to image before applying the photon counting integral imaging in this paper. To verify feasibility of our method, we implement experiments and show the experimental results. In addition, for numerical comparison, the image quality assessment methods such as structural similarity index map (SSIM) and blind/referenceless image spatial quality evaluator (BRISQUE) are calculated.

关键词： Image quality Visualization Three-dimensional displays Image resolution Noise Indexes Image reconstruction Photonics Singular value decomposition Meteorology

来源：评论

学校读者我要写书评

暂无评论

Controllable Segmentation-Based Text-Guided Style Editing

arXiv

引用

arXiv 2025年

作者： Li, Jingwen Chandrasekar, Aravind Rocha, Mariana Li, Chao Chen, Yuqing Department of Computer Science Fudan University China School of AI and Robotics AuroraTech Labs United States Vision Intelligence Group Federal University of Rio de Janeiro Brazil Dept. of Computer Science Eastern Asia Institute of Technology Beijing China

We present a novel approach for controllable, region-specific style editing driven by textual prompts. Building upon the state-space style alignment framework introduced by StyleMamba, our method integrates a semantic segmentation model into the style transfer pipeline. This allows users to selectively apply text-driven style changes to specific segments (e.g., "turn the building into a cyberpunk tower") while leaving other regions (e.g., "people" or "trees") unchanged. By incorporating region-wise condition vectors and a region-specific directional loss, our method achieves high-fidelity transformations that respect both semantic boundaries and user-driven style descriptions. Extensive experiments demonstrate that our approach can flexibly handle complex scene stylizations in real-world scenarios, improving control and quality over purely global style transfer methods. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Study on Autonomous Delivery of Guidewire Based on Improved YOLOV5s on Vascular Model Platform

Study on Autonomous Delivery of Guidewire Based on Improved ...

引用

2022 IEEE International Conference on robotics and Biomimetics, ROBIO 2022

作者： Wang, Shuang Liu, Zheng Shu, Xiongpeng Cao, Yongfeng Zhang, Ling Xie, Le School of Materials Science and Engineering Shanghai Jiao Tong University Shanghai200240 China School of Mathematics and Computer Science Quanzhou Normal University Quanzhou362000 China Institute of Forming Technology and Equipment Institute of Medical Robotics Shanghai Jiao Tong University Shanghai200240 China

ISBN: (纸本)9781665481090

Cardiovascular interventional surgery robot is an effective means to solve the problem of X-ray radiation injury and physiological fatigue of surgeons. With the development of robotics, robotic autonomous surgery has become one of the research hotspots. However, the current intelligence level of cardiovascular interventional surgery robots is low. Aiming at the guidewire delivery process of the designed cardiovascular interventional surgery robot, this paper proposes a new control strategy based on improved YOLOV5s deep learning algorithm, which can realize the autonomous delivery of the guidewire under image navigation. The development of the vascular model platform experiment proved the feasibility of the scheme. © 2022 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

A study on obtaining accurate height information of red blood cells in digital holographic microscopy (DHM)

A study on obtaining accurate height information of red bloo...

引用

International Conference on Control, Automation and Systems ( ICCAS)

作者： Kosei Nakamura Hyun-Woo Kim Myungjin Cho Min-Chul Lee Department of Computer Science and Networks Kyushu Institute of Technology Iizuka Fukuoka Japan School of ICT Robotics and Mechanical Engineering IITC Hankyoung National University Anseong Republic of Korea

ISBN: (数字)9788993215380

ISBN: (纸本)9798331517939

Digital holographic microscopy (DHM) is used in the fields of microbiological research and disease diagnosis. Especially in the medical field, it is required to obtain the precise shape information of red blood cells and living cells for disease diagnosis. To obtain the highly accurate three-dimensional profile of an object, it is necessary to set parameters accurately on the system and perform the analysis. In DHM, it is especially important to set the refractive index of the medium surrounding the object accurately. However, the refractive index varies depending on the temperature and the humidity of the experimental environment, as well as on the sample preparation method, and it is difficult to derive the appropriate refractive index. This is a problem in the medical field, which requires the accurate three-dimensional information. Therefore, in this paper, we propose a method to derive the optimum refractive index and to obtain the accurate height information of red blood cells by conducting experiments using two types of lasers with different wavelengths and comparing the height information of red blood cells obtained with each laser. By using the proposed method, the optimu m refractive index of the surrounding medium and the accurate height information of the red blood cells are obtained.

关键词： Temperature dependence Accuracy Red blood cells Shape Microscopy Lasers Refractive index Process control Medical diagnosis Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Deeper Introspective SLAM: How to Avoid Tracking Failures Over Longer Routes?

Deeper Introspective SLAM: How to Avoid Tracking Failures Ov...

引用

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

作者： Kanwal Naveed Muhammad Latif Anjum Wajahat Hussain Donghwan Lee Robotics & Machine Intelligence (ROMI) Lab School of Electrical Engineering and Computer Science (SEECS) National University of Sciences and Technology Islamabad Pakistan Reinforcement Learning Research Lab School of Electrical Engineering Korea Advanced Institute of Science and Technology (KAIST) Daejeon South Korea

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Large scale active exploration has recently revealed limitations of visual SLAM’s tracking ability. Active view planning methods based on reinforcement learning have been proposed to improve visual tracking *** this work, we expose the limitations of deep reinforcement learning-based visual SLAM over longer routes. We demonstrate that additional modalities (depth, scene layout) offer little improvement. Furthermore, reward shaping is not the main reason behind the shortsightedness of the state-of-the-art visual SLAM tracker. We propose a novel video vision transformer-based architecture that improves the farsightedness of the visual tracker, which results in the completion of longer routes with efficient *** of 60 challenging routes, our approach manages to complete 56 routes, which is a three-fold improvement over the state-of-the-art active view mapping (DI-SLAM) baseline. Interestingly, ORB-SLAM3 was unable to complete a single route without tracking failure. Our code is available at https://***/w935spuz.

关键词： Visualization Simultaneous localization and mapping Codes Layout Transformers Deep reinforcement learning Robustness Planning Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

An Improvement of Loop Closure Detection Based on BoW for RatSLAM 37

An Improvement of Loop Closure Detection Based on BoW for Ra...

引用

37th Youth Academic Annual Conference of Chinese Association of Automation, YAC 2022

作者： Xu, Jianjun Yan, Nanya Tang, Fengzhen Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences School of Computer Science and Technology Beijing China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China

ISBN: (纸本)9781665465366

The visual perception of the original RatSLAM algorithm works directly on the intensities of image pixels and thus is greatly affected by illuminations, weathers, and other factors. The algorithm may result in perception errors and mapping failures in some situations. Therefore, this paper proposes an image sequence matching algorithm based on a visual dictionary model termed as Bag of Words (BoW) and the dynamic island mechanism to realize fast and accurate scene recognition. The feature vector of scene image is generated by the ORB algorithm, and then the image matching is transformed into the calculation of the distance between image feature vectors, improving the efficiency of image matching. The dynamic island mechanism is used as a detection algorithm to realize the sequence matching of the environment, improving the accuracy of loop closure detection. Experiments are performed in different environments, showing that the visual processing performance and mapping performance of the proposed algorithm are significantly better than the existing RatSLAM algorithm. © 2022 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Modeling and analysis of a CT-guided lung puncture robot

Modeling and analysis of a CT-guided lung puncture robot

引用

2022 IEEE International Conference on robotics and Biomimetics, ROBIO 2022

作者： Zhang, Ling Wang, Shuang Shu, Xiongpeng Xie, Le Shanghai Jiao Tong University School of Materials Science and Engineering Shanghai200240 China Quanzhou Normal University School of Mathematics and Computer Science Quanzhou362000 China Institute of Forming Technology and Equipment Institute of Medical Robotics Shanghai Jiao Tong University Shanghai200240 China

ISBN: (纸本)9781665481090

In this paper, a five-degree-of-freedom lung puncture biopsy surgical robot system was proposed to solve the clinical problem of small CT aperture and limited puncture space, and the overall size of the robot is within 20∗20∗20 cm. By kinematic analysis of the robot configuration, a working space that can completely cover the patient's chest was obtained. The design of the parallel manipulators was characterized with higher accuracy and stiffer than the serial robots, making the robot end-effector meet the remote immobile puncture effect and reduce the damage to the patient's skin surface. The finite element model of the structure was constructed and statically simulated by Abaqus, and the deformation and strength of the mechanism met the requirements during the operation. © 2022 IEEE.

关键词： Degrees of freedom (mechanics)

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：