检索结果-内蒙古大学图书馆

32nd ACM International Conference on Multimedia, MM 2024

作者： Zhu, Jiangtong Yang, Zhao Shi, Yinan Fang, Jianwu Xue, Jianru Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China Beijing China

ISBN: (纸本)9798400706868

Online vector map construction based on visual data can bypass the processes of data collection, post-processing, and manual annotation required by traditional map construction, which significantly enhances map-building efficiency. However, existing work treats the online mapping task as a local range perception task, overlooking the spatial scalability required for map construction. We propose IC-Mapper, an instance-centric online mapping framework, which comprises two primary components: 1) Instance-centric temporal association module: For the detection queries of adjacent frames, we measure them in both feature and geometric dimensions to obtain the matching correspondence between instances across frames. 2) Instance-centric spatial fusion module: We integrate features from the detected instances of the current frame with BEV features and spatially sampled points from the historical map. Then, we concatenate point sets with the same ID to achieve real-time map expansion and updating. Based on the nuScenes dataset, we evaluate our approach on detection, tracking, and global mapping metrics. Experimental results demonstrate the superiority of IC-Mapper against other state-of-the-art methods. Code will be released on https://***/Brickzhuantou/IC-Mapper. © 2024 Owner/Author.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Under-Display ToF Imaging with Efficient Transformer

Under-Display ToF Imaging with Efficient Transformer

引用

2023 IEEE International Conference on Visual Communications and Image Processing, VCIP 2023

作者： Sun, Yuan Wei, Hao Qiao, Xin Deng, Pengchao Ge, Chenyang Xi'An Jiaotong University Institute of Artificial Intelligence and Robotics China

ISBN: (纸本)9798350359855

Demand for full screen in consumer electronics has propelled the development of under-display image processing. For time-of-flight cameras, they are usually placed under TOLED display. Due to the presence of pixels and display patterns in the TOLED panel, depth maps from under-display time-of-flight (UD-ToF) are noisy, blurry, and inaccurate. We propose a non-local method based on Vision Transformer for UD-ToF depth restoration to address these issues. Specifically, a novel feature attention block is designed to incorporate non-local depth features. Additionally, we take ToF raw measurements rather than the depth map as input, allowing the network to extract informative features from the raw domain. We conduct comprehensive experiments on real RUD-TOF and synthetic SUD-TOF benchmark datasets, and the results indicate that the proposed transformer-based method achieves better performance than the state-of-The-Art algorithms. © 2023 IEEE.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

How Much Energy Do Bounded Rational Participants Share in Vehicle-to-Grid (V2G)?

How Much Energy Do Bounded Rational Participants Share in Ve...

引用

2023 IEEE PES Innovative Smart Grid Technologies Europe, ISGT EUROPE 2023

作者： Sun, Chenxi Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

ISBN: (纸本)9798350396782

In this paper, we study an energy trading problem at EV charging stations under a Vehicle-to-Grid (V2G) setting. We formulate a non-cooperative game between bounded rational EV owners who submit energy trading bids before participating in the V2G system. The prospect theory is used to model the behaviors of the bounded rational EV owners, whose actual sojourn times can be different from the bids due to uncertainty. We propose a best response based algorithm to find pure strategy Nash Equilibrium(s) and further explore how the bounded rational participants would like to trade/share energy, compared with traditional energy sharing models based on the expected hypothesis. We further provide experimental results to validate our method. © 2023 IEEE.

关键词： Electric vehicle energy trading/sharing non-cooperative game prospect theory vehicle-to-grid

来源：评论

学校读者我要写书评

暂无评论

Multi-modal Camera and One-beam LiDAR Fusion Network for Low-cost 3D Object Detection

Multi-modal Camera and One-beam LiDAR Fusion Network for Low...

引用

2024 IEEE International Conference on robotics and Biomimetics, ROBIO 2024

作者： Wang, Rongxin Chen, Ronghai Yang, Meng Lan, Xuguang Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University P.R. China

ISBN: (纸本)9781665481090

3D object detection is a fundamental technique for scene perception of autonomous robots. Recent methods rely heavily on muti-beam LiDAR such as 64-beam, which is limited by the cost and power in practical applications. Monocular camera or one-beam LiDAR provides optional ways for this problem. However, the front one is inherently ill-posed in depth prediction and the latter one could not well infer semantics, size and pose of 3D objects. In addition, the fusion of camera and one-beam LiDAR is not well studied in recent methods. We specifically investigate a framework of 3D object detection by fusing monocular camera and one-beam LiDAR. Different from recent multi-modal techniques, which primarily rely on LiDAR data, our solution mainly utilizes camera to detect 3D objects and one-beam LiDAR as a supplement. First, a high-quality depth map is predicted from an RGB image and one-beam LiDAR points with a two-branch network and a global-local normal gradient loss. Second, pseudo-LiDAR points are converted from the depth map and further corrected by the one-beam LiDAR points. Finally, corrected pseudo-LiDAR points are fed into a mature LiDAR-based 3D detector. Our method is verified on KITTI test set and compared to twelve recent baselines of LiDAR-based, RGB-based and multi-modal methods. Extensive results verify that our method achieves 38.00, 27.36 and 22.92 of AP40 (IoU=0.7) in easy, moderate and hard modes, which significantly outperforms all the baselines. © 2024 IEEE.

关键词： Ultrasonic cameras

来源：评论

学校读者我要写书评

暂无评论

Non-uniform Deblurring by Deep Sharpness Edge Guided Model

Non-uniform Deblurring by Deep Sharpness Edge Guided Model

引用

2023 IEEE International Conference on Visual Communications and Image Processing, VCIP 2023

作者： Wei, Hao Ge, Chenyang Qiao, Xin Deng, Pengchao Xi'An Jiaotong University Institute of Artificial Intelligence and Robotics China

ISBN: (纸本)9798350359855

In this paper, we propose a two-branch deblurring framework. Given a blurred image, we first extract the edge map and employ an edge refinement network to recover the structure. Then the refined edge map is utilized to guide the subsequent deblurring process for correct structure recovery. Specifically, we develop a lightweight omni-dimensional attention module for long-range dependencies modeling and plug it into the edge refinement network, which effectively handles blur patterns with high variation. Furthermore, we propose a dynamic feature upsample module, which integrates dynamic convolution with upsampling and adaptively deals with the non-uniform blur. Extensive experiments show that our method outperforms state-of-The-Art methods. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Visual-Linguistic Feature Alignment with Semantic and Kinematic Guidance for Referring Multi-Object Tracking

引用

IEEE Transactions on Multimedia 2025年 27卷 3034-3044页

作者： Li, Yizhe Zhou, Sanping Qin, Zheng Wang, Le National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Shaanxi Xi'an710049 China

Referring Multi-Object Tracking (RMOT) aims to dynamically track an arbitrary number of referred targets in a video sequence according to the language expression. Previous methods mainly focus on cross-modal fusion at the feature level with designed structures. However, the insufficient visual-linguistic alignment is prone to causing visual-linguistic mismatches, leading to some targets being tracked but not correctly referred especially when facing the language expression with complex semantics or motion descriptions. To this end, we propose to conduct visual-linguistic alignment with semantic and kinematic guidance to effectively align the visual features with more diverse language expressions. In this paper, we put forward a novel end-to-end RMOT framework SKTrack, which follows the transformer-based architecture with a Language-Guided Decoder (LGD) and a Motion-Aware Aggregator (MAA). In particular, the LGD performs deep semantic interaction layer-by-layer in a single frame to enhance the alignment ability of the model, while the MAA conducts temporal feature fusion and alignment across multiple frames to enable the alignment between visual targets and language expression with motion descriptions. Extensive experiments on the Refer-KITTI and Refer-KITTI-v2 demonstrate that SKTrack achieves state-of-the-art performance and verify the effectiveness of our framework and its components. © 1999-2012 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Human-robot object handover:Recent progress and future direction

引用

Biomimetic intelligence & robotics 2024年第1期4卷 1-13页

作者： Haonan Duan Yifan Yang Daheng Li Peng Wang Institute of Automation Chinese Academy of SciencesBeijing 100190China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science and InnovationChinese Academy of SciencesHong Kong 999077China

Human-robot object handover is one of the most primitive and crucial capabilities in human-robot *** is of great significance to promote robots to truly enter human production and life scenarios and serve human in numerous *** progressions in the field of human-robot object handover have been made by *** article reviews the recent literature on human-robot object *** this end,we summarize the results from multiple dimensions,from the role played by the robot(receiver or giver),to the end-effector of the robot(parallel-jaw gripper or multi-finger hand),to the robot abilities(grasp strategy or motion planning).We also implement a human-robot object handover system for anthropomorphic hand to verify human-robot object handover *** review aims to provide researchers and developers with a guideline for designing human-robot object handover methods.

关键词： Human-robot interactions Object handover

来源：评论

学校读者我要写书评

暂无评论

Towards Autonomous Cardiac Ultrasound Scanning: Combining Physician Expertise and Machine intelligence

IEEE Transactions on Medical Robotics and Bionics

引用

IEEE Transactions on Medical robotics and Bionics 2025年第2期7卷 782-792页

作者： Hao, Mingrui Zhang, Pengcheng Hou, Xilong Gu, Xiaolin Zhou, Xiao-Hu Hou, Zeng-Guang Chen, Chen Wang, Shuangyi Institute of Automation Chinese Academy of Sciences National Key Laboratory for Multi-Modal Artificial Intelligence Systems Beijing100190 China University of Chinese Academy of Sciences School of Artificial Intelligence Beijing100043 China Hong Kong Institute of Science and Innovation Chinese Academy of Sciences Centre for Artificial Intelligence and Robotics Hong Kong Hong Kong Lingshu Medical Company Suzhou215123 China

Echocardiography serves as a prevalent modality for both heart disease diagnosis and procedural guidance in medical applications. Nevertheless, the conventional echocardiography examination heavily relies on the manual dexterity of the sonographer, leading to the suboptimal repeatability. Despite the extensive exploration of robot-assisted ultrasound systems, achieving a heightened level of automation in examinations and enhancing the practicality of these robotic platforms for primary utilization remain formidable challenges within the field. In this study, we introduce an innovative automatic acquisition method for cardiac views using a novel ultrasound robot. The method is designed to autonomously traverse and scan target positions and angular ranges to search and identify the target cardiac views. First, the target positions and angular ranges were derived from a professional sonographer's practice on 14 cases. Then, an automatic traversal scanning method is designed integrating visual guidance, human-machine collaboration, and path planning within the framework of a novel parallel mechanism-based ultrasound robot. Finally, we explore deep metric learning to search for target ultrasound images in the traversed ultrasound video. Experiments on the test set to evaluate the target ultrasound view searching algorithm achieved a mAP of 98.8% and a Rank-1 accuracy of 98.23%. Our method has been successfully validated by data from five subjects, achieving the acquisition of standard parasternal long-axis and short-axis cardiac views essential for diagnosis, demonstrating the effectiveness of the proposed method. © 2018 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Object Detection via Dual-Domain Feature Fusion and Patch-Level Attention

引用

清华大学学报自然科学版（英文版） 2025年第3期30卷 1237-1250页

作者： Guangli Ren Jierui Liu Mengyao Wang Peiyu Guan Zhiqiang Cao Junzhi Yu State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Department of Advanced Manufacturing and Robotics Peking UniversityBeijing 100871China

Few-shot object detection receives much attention with the ability to detect novel class objects using limited annotated *** transfer learning-based solution becomes popular due to its simple training with good accuracy,however,it is still challenging to enrich the feature diversity during the training *** fine-grained features are also insufficient for novel class *** deal with the problems,this paper proposes a novel few-shot object detection method based on dual-domain feature fusion and patch-level *** original base domain,an elementary domain with more category-agnostic features is superposed to construct a two-stream backbone,which benefits to enrich the feature *** better integrate various features,a dual-domain feature fusion is designed,where the feature pairs with the same size are complementarily fused to extract more discriminative ***,a patch-wise feature refinement termed as patch-level attention is presented to mine internal relations among the patches,which enhances the adaptability to novel *** addition,a weighted classification loss is given to assist the fine-tuning of the classifier by combining extra features from FPN of the base training *** this way,the few-shot detection quality to novel class objects is *** on PASCAL VOC and MS COCO datasets verify the effectiveness of the method.

关键词： few-shot object detection dual-domain feature fusion patch-level attention

来源：评论

学校读者我要写书评

暂无评论

Fully 3D Printed Soft Electrostatic Loudspeaker 30

Fully 3D Printed Soft Electrostatic Loudspeaker

引用

30th International Conference on Mechatronics and Machine Vision in Practice, M2VIP 2024

作者： Li, Jisen Xiao, Fei Cheng, Anjing Luo, Zhen Zhu, Jian The Chinese Univ of Hong Kong Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

ISBN: (纸本)9798350391916

Loudspeakers are essential components in human-machine interaction, enabling auditory communication between devices and users. However, most conventional loudspeakers are constructed from rigid materials, resulting in poor compliance and limiting their application in wearable technologies. In this paper, we introduce a novel soft loudspeaker fabricated using a customized 3D printer. This loudspeaker is made entirely of silicone rubber, which provides excellent compliance and biocompatibility, making it suitable for integration into wearable devices. The fabrication process involves the use of advanced multi-material 3D printing techniques to create a structure that can operate without the need for prestretch, enhancing its flexibility and ease of use. Experimental results demonstrate that the soft loudspeaker can produce satisfactory audio output when tested with real music input. The acoustic performance, including sound quality and volume, shows a close resemblance to traditional loudspeakers, while offering the added benefits of flexibility and comfort for the user. © 2024 IEEE.

关键词： Electrostatic loudspeakers

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：