检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Jiang, Chaokang Wang, Guangming Miao, Yanzi Wang, Hesheng Engineering Research Center of Intelligent Control for Underground Space Ministry of Education School of Information and Control Engineering Advanced Robotics Research Center China University of Mining and Technology Xuzhou221116 China Department of Automation Key Laboratory of System Control and Information Processing Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai200240 China

3D scene flow characterizes how the points at the current time flow to the next time in the 3D Euclidean space, which possesses the capacity to infer autonomously the non-rigid motion of all objects in the scene. The previous methods for estimating scene flow from images have limitations, which split the holistic nature of 3D scene flow by estimating optical flow and disparity separately. Learning 3D scene flow from point clouds also faces the difficulties of the gap between synthesized and real data and the sparsity of LiDAR point clouds. In this paper, the generated dense depth map is utilized to obtain explicit 3D coordinates, which achieves direct learning of 3D scene flow from 2D images. The stability of the predicted scene flow is improved by introducing the dense nature of 2D pixels into the 3D space. Outliers in the generated 3D point cloud are removed by statistical methods to weaken the impact of noisy points on the 3D scene flow estimation task. Disparity consistency loss is proposed to achieve more effective unsupervised learning of 3D scene flow. The proposed method of self-supervised learning of 3D scene flow on real-world images is compared with a variety of methods for learning on the synthesized dataset and learning on LiDAR point clouds. The comparisons of multiple scene flow metrics are shown to demonstrate the effectiveness and superiority of introducing pseudo-LiDAR point cloud to scene flow estimation. © 2022, CC BY.

关键词： Three dimensional computer graphics

来源：评论

学校读者我要写书评

暂无评论

XNORAM: An Efficient Computing-in-Memory Architecture for Binary Convolutional Neural Networks with Flexible Dataflow Mapping

XNORAM: An Efficient Computing-in-Memory Architecture for Bi...

引用

2020 IEEE International Conference on Artificial Intelligence Circuits and systems, AICAS 2020

作者： Liu, Shiwei Zhu, Haozhe Chen, Chixiao Zhang, Lihua Richard Shi, C.-J. State Key Laboratory of ASIC and System China Shanghai Engineering Research Center for AI and Robotics Fudan University Shanghai China Jihua Laboratory Foshan China University of Washington SeattleWA United States

ISBN: (纸本)9781728149226

In this paper, an energy-efficient computing-inmemory architecture for binary convolutional neural networks, called XNORAM, is proposed. The XNORAM employs 6T feature cells and 10T weight cells to form one XNORAM column. Multiplexed XNOR operations are embedded in each column. To address the data reuse in convolutional neural networks, flexible dataflow mapping is supported on XNORAM to minimize the external data access. To verify the architecture, we design a 4-KB XNORAM prototype in 65nm CMOS technology. It achieves a throughput of 18. 5GOPs at 100-MHz clock rate and 1.0-V power supply. XNOR-AlexNet is performed on the design achieving 39.86 TOPS/W and 4.63 GOPS/KB utilization with only 1.3% accuracy loss comparing to the original XNOR-Net result on GPUs. © 2020 IEEE.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

GenFace: A Large-Scale Fine-Grained Face Forgery Benchmark and Cross Appearance-Edge Learning

arXiv

引用

arXiv 2024年

作者： Zhang, Yaning Yu, Zitong Wang, Tianyi Huang, Xiaobin Shen, Linlin Gao, Zan Ren, Jianfeng Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Nanyang Technological University 50 Nanyang Ave Block N 4 639798 Singapore Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518129 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University China Jinan250014 China Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin300384 China School of Computer Science University of Nottingham Ningbo China

The rapid advancement of photorealistic generators has reached a critical juncture where the discrepancy between authentic and manipulated images is increasingly indistinguishable. Thus, benchmarking and advancing techniques detecting digital manipulation become an urgent issue. Although there have been a number of publicly available face forgery datasets, the forgery faces are mostly generated using GAN-based synthesis technology, which does not involve the most recent technologies like diffusion. The diversity and quality of images generated by diffusion models have been significantly improved and thus a much more challenging face forgery dataset shall be used to evaluate SOTA forgery detection literature. In this paper, we propose a large-scale, diverse, and fine-grained high-fidelity dataset, namely GenFace, to facilitate the advancement of deepfake detection, which contains a large number of forgery faces generated by advanced generators such as the diffusion-based model and more detailed labels about the manipulation approaches and adopted generators. In addition to evaluating SOTA approaches on our benchmark, we design an innovative Cross Appearance-Edge Learning (CAEL) detector to capture multi-grained appearance and edge global representations, and detect discriminative and general forgery traces. Moreover, we devise an Appearance-Edge Cross-Attention (AECA) module to explore the various integrations across two domains. Extensive experiment results and visualizations show that our detection model outperforms the state of the arts on different settings like cross-generator, cross-forgery, and cross-dataset evaluations. Code and datasets will be available at https://***/Jenine-321/GenFace. Copyright © 2024, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

SUBPIXEL EDGE LOCALIZATION BASED ON CONVERTED INTENSITY SUMMATION UNDER STABLE EDGE REGION

arXiv

引用

arXiv 2025年

作者： Yang, Yingyuan Liang, Guoyuan Wang, Xianwen Wang, Kaiming Wang, Can Wu, Xiaojun Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China University of Chinese Academy of Sciences Beijing10049 China Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Guilin University of Technology Guilin541000 China School of Mechanical Engineering and Automation Harbin Institute of Technology at Shenzhen Shenzhen518055 China

To satisfy the rigorous requirements of precise edge detection in critical high-accuracy measurements, this article proposes a series of efficient approaches for localizing subpixel edge. In contrast to the fitting based methods, which consider pixel intensity as a sample value derived from a specific model. We take an innovative perspective by assuming that the intensity at the pixel level can be interpreted as a local integral mapping in the intensity model for subpixel localization. Consequently, we propose a straightforward subpixel edge localization method called Converted Intensity Summation (CIS). To address the limited robustness associated with focusing solely on the localization of individual edge points, a Stable Edge Region (SER) based algorithm is presented to alleviate local interference near edges. Given the observation that the consistency of edge statistics exists in the local region, the algorithm seeks correlated stable regions in the vicinity of edges to facilitate the acquisition of robust parameters and achieve higher precision positioning. In addition, an edge complement method based on extension-adjustment is also introduced to rectify the irregular edges through the efficient migration of SERs. A large number of experiments are conducted on both synthetic and real image datasets which cover common edge patterns as well as various real scenarios such as industrial PCB images, remote sensing and medical images. It is verified that CIS can achieve higher accuracy than the state-of-the-art method, while requiring less execution time. Moreover, by integrating SER into CIS, the proposed algorithm demonstrates excellent performance in further improving the anti-interference capability and positioning accuracy. Copyright © 2025, 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

Deep Residual Learning Based Localization of Near-Field Sources in Unknown Spatially Colored Noise Fields

Deep Residual Learning Based Localization of Near-Field Sour...

引用

European Signal Processing Conference (EUSIPCO)

作者： Zhuoqian Jiang Jingmin Xin Weiliang Zuo Nanning Zheng Akira Sano Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China National Engineering Laboratory for Visual Information Processing and Applications Xi'an Jiaotong University Xi'an China Shunan Academy of Artificial Intelligence Zhejiang China Department of System Design Engineering Keio University Yokohama Japan

ISBN: (数字)9789082797091

ISBN: (纸本)9781665467995

In this paper, we explore the problem of near-field source localization in an unknown spatially colored noise environment using an end-to-end neural network which is based on deep residual learning. Specifically, the proposed approach uses the multi-dimensional information of the array covariance as input, and finally directly outputs the location information of the near-field sources through the regression structure. The architecture of deep neural network is well designed taking into account the trade-off between the expression ability and compu-tational complexity. In addition, benefiting from the method of generating training data that combines the degree of separation to traverse the spatial location, the proposed approach has a robust performance for different location parameter separation. The simulation results demonstrate that the proposed approach outperforms the existing model-driven methods under various conditions, especially for the adverse scenes with low SNRs, small number of snapshots, or correlated sources.

关键词： Location awareness Deep learning Simulation Neural networks Training data Signal processing algorithms Position measurement

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Learning of 3D Scene Flow with 3D Odometry Assistance

arXiv

引用

arXiv 2022年

作者： Wang, Guangming Feng, Zhiheng Jiang, Chaokang Wang, Hesheng Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai200240 China Engineering Research Center of Intelligent Control for Underground Space Ministry of Education School of Information and Control Engineering Advanced Robotics Research Center China University of Mining and Technology Xuzhou221116 China

Scene flow represents the 3D motion of each point in the scene, which explicitly describes the distance and the direction of each point’s movement. Scene flow estimation is used in various applications such as autonomous driving fields, activity recognition, and virtual reality fields. As it is challenging to annotate scene flow with ground truth for real-world data, this leaves no real-world dataset available to provide a large amount of data with ground truth for scene flow estimation. Therefore, many works use synthesized data to pre-train their network and real-world LiDAR data to finetune. Unlike the previous unsupervised learning of scene flow in point clouds, we propose to use odometry information to assist the unsupervised learning of scene flow and use real-world LiDAR data to train our network. Supervised odometry provides more accurate shared cost volume for scene flow. In addition, the proposed network has mask-weighted warp layers to get a more accurate predicted point cloud. The warp operation means applying an estimated pose transformation or scene flow to a source point cloud to obtain a predicted point cloud and is the key to refining scene flow from coarse to fine. When performing warp operations, the points in different states use different weights for the pose transformation and scene flow transformation. We classify the states of points as static, dynamic, and occluded, where the static masks are used to divide static and dynamic points, and the occlusion masks are used to divide occluded points. The mask-weighted warp layer indicates that static masks and occlusion masks are used as weights when performing warp operations. Our designs are proved to be effective in ablation experiments. The experiment results show the promising prospect of an odometry-assisted unsupervised learning method for 3D scene flow in real-world data. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Design of grayscale digital light processing 3D printing block by machine learning and evolutionary algorithm

引用

Composites Communications 2022年 36卷

作者： Zhao, Baowen Zhang, Mengjie Dong, Le Wang, Dong Robotics Institute School of Mechanical Engineering Shanghai Jiao Tong University Shanghai 200240 China State Key Laboratory of Mechanical System and Vibration Shanghai Jiao Tong University Shanghai 200240 China Meta Robotics Institute Shanghai Jiao Tong University Shanghai 200240 China

Grayscale digital light processing (DLP) 3D printing method, using grayscale light patterns to adjust the microscale material properties, is a revolutionary technology for future advanced manufacturing. However, the design and optimization method of the grayscale distribution remains elusive. In this paper, we propose an optimization method for grayscale DLP printed rectangular blocks based on a machine learning and evolutionary algorithm. We use an automated finite element model-based evaluation to predict the deformation shapes with arbitrary grayscale distribution, considering the nonlinear mechanical performances. A machine learning model based on recurrent neural networks is trained using the database formed by the finite element method model to enable fast and precise prediction of the deformed shapes. Optimal designs of the deformed shapes are efficiently realized via integrating the machine learning model and evolution algorithm method. Grayscale distributions are optimized to form desired deformations and validated by experiments. This work paves the way for designing and optimizing grayscale digital light processing 3D printed structures. © 2022 Elsevier Ltd

关键词：

来源：评论

学校读者我要写书评

暂无评论

Digital Modeling of Massage Techniques and Reproduction by Robotic Arms

arXiv

引用

arXiv 2024年

作者： Xu, Yuan Huang, Kui Guo, Weichao Du, Leyi The SJTU Paris Elite Institute of Technology Shanghai Jiao Tong University Shanghai200240 China The State Key Laboratory of Mechanical System and Vibration School of Mechanical Engineering Shanghai Jiao Tong University Shanghai200240 China Meta Robotics Institute Shanghai Jiao Tong University Shanghai200240 China School of Gongli Hospital Medical Technology University of Shanghai for Science and Technology China

This paper explores the digital modeling and robotic reproduction of traditional Chinese medicine (TCM) massage techniques. We adopt an adaptive admittance control algorithm to optimize force and position control, ensuring safety and comfort. The paper analyzes key TCM techniques from kinematic and dynamic perspectives, and designs robotic systems to reproduce these massage techniques. The results demonstrate that the robot successfully mimics the characteristics of TCM massage, providing a foundation for integrating traditional therapy with modern robotics and expanding assistive therapy applications. Copyright © 2024, The Authors. All rights reserved.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

Constant Direct Current Triboelectric Nanogenerator Based on Soft-Contact Mode for Self-Powered Cathodic Protection

SSRN

引用

SSRN 2022年

作者： Li, Ming Jiang, Tianyi Ren, Yukun Jiang, Hongyuan School of Mechatronics Engineering Harbin Institute of Technology West Da-zhi Street 92 Harbin150001 China State Key Laboratory of Robotics and System Harbin Institute of Technology West Da-zhi Street 92 Heilongjiang Harbin150001 China

Triboelectric nanogenerator (TENG) has been proved to be a promising technology for harvesting decentralized energy. However, the application fields of the traditional TENGs are limited by the high crest factor. Here a constant direct current TENG (CDC-TENG) with low crest factor is proposed by connecting three rotating TENGs with specific phase difference (Δ θ ) in parallel. Excellent wear resistance and humidity resistance are demonstrated owing to the soft-contact mode and 3D encapsulated design. For the CDC-TENG (3P6E), the crest factor surprisingly decreases to 1.05 while that of the TENGs without Δ θ is up to 1.31. Meanwhile, the current density up to 3021 μA·m -2 is achieved at the rotation speed of 500 r·min -1 . Then, owing to the excellent output of constant direct current (DC), a commercial timer is directly driven by the CDC-TENG without using capacitor. Finally, the CDC-TENG is used as the power source of cathodic protection (CP) system, which exhibits an excellent corrosion protection effect. In general, this work provides a meaningful template for TENGs to broaden the marine industrial applications of constant DC demand. © 2022, The Authors. All rights reserved.

关键词： Nanogenerators

来源：评论

学校读者我要写书评

暂无评论

Design, Analysis, and Experiment of a Coupled-Adaptive Underactuated Prosthetic Handbased on Linkage Mechanisms

SSRN

引用

SSRN 2022年

作者： Fan, Shaowei Dai, Jinghui Zhang, Ning Zhang, Ting Cheng, Ming Liu, Bingchen Jiang, Li State Key Laboratory of Robotics and System Harbin Institute of Technology Heilongjiang Harbin150080 China National Research Center for Rehabilitation Technical Aids Beijing100176 China College of Mechanical and Electrical Engineering Soochow University Jiangsu Suzhou215021 China

To reproduce the characteristics of human hand motion, this paper proposes a novel four-degree-of-freedom prosthetic hand that combines the advantages of coupled motion and self-adaptive motion. A coupled-adaptive underactuated finger was developed using a cross-coupled four-link mechanism and an adaptive five-link mechanism. The finger can perform both power and precision grasping excellently. Based on the seesaw mechanism, a differential mechanism among the middle finger, ring finger, and little finger was developed to further reduce the size and weight of the prosthetic hand. To avoid the ejection phenomenon, the stability of the finger is systematically analyzed in this paper using the grasp-state space analysis technique. The stability analysis results indicate that ejection does not occur in the entire workspace of the proposed finger. The grasping experiments indicate that the proposed prosthetic hand possesses excellent stability and adaptability. © 2022, The Authors. All rights reserved.

关键词： Prosthetics

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：