检索结果-内蒙古大学图书馆

GraspDiff: Grasping Generation for Hand-Object Interaction With Multimodal Guided Diffusion

IEEE Transactions on Visualization and Computer Graphics 2024年 PP卷 PP-PP页

作者： Zuo, Binghui Zhao, Zimeng Sun, Wenqian Yuan, Xiaohan Yu, Zhipeng Wang, Yangang Southeast University School of Automation Nanjing210096 China Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China

Grasping generation holds significant importance in both robotics and AI-generated content. While pure network paradigms based on VAEs or GANs ensure diversity in outcomes, they often fall short of achieving plausibility. Additionally, although those two-step paradigms that first predict contact and then optimize distance yield plausible results, they are always known to be time-consuming. This paper introduces a novel paradigm powered by DDPM, accommodating diverse modalities with varying interaction granularities as its generating conditions, including 3D object, contact affordance, and image content. Our key idea is that the iterative steps inherent to diffusion models can supplant the iterative optimization routines in existing optimization methods, thereby endowing the generated results from our method with both diversity and plausibility. Using the same training data, our paradigm achieves superior generation performance and competitive generation speed compared to optimization-based paradigms. Extensive experiments on both in-domain and out-of-domain objects demonstrate that our method receives significant improvement over the SOTA method. We will release the code for research purposes. © 1995-2012 IEEE.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

Mining Better Samples and Semantic Consistency for Contrast Learning in Forest Semantic Segmentation 41

Mining Better Samples and Semantic Consistency for Contrast ...

引用

第41届中国控制会议

作者： Chongjin Chen Yichao Cao Qingfei Tang Xiaobo Lu School of Software Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Southeast University Nanjing Enbo Technology Co. Ltd.

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Image segmentation has impressive progress in the past several *** good segmentation usually follows pixelwise well-annotated labels which is ***,the robustness would not be guaranteed due to lack-ofdiversity *** work usually focuses on pixels individually and pay less attention to the neighbor *** local context would be scarce and the global context is not utilized following these *** proposal a method,named Forest Semantic Segmentation Network(FSSNet) to address these *** organizes original version and augmented version of images,as two inputs into student branch and teacher branch,and force the two outputs being consistent to strengthen the robustness of our ***,we not only consider pixel itself and also the neighbor pixels because the context of neighbor pixels helps understanding the *** utilizes contrastive loss with memory bank to involve global context in training which will make pixels closer to others in same category and far away from pixels of different categories.A bank filter is suggested to improve the quality of features in the memory *** also proposal a new sample strategy to improve the effect of contrastive loss and reduce the *** method can improve accuracy and strengthen the robustness with affordable extra computation during training process,and no additional computation during inference toward *** to benchmark,the proposed approach can improve the mIoU by 3.1% on our challenging dataset.

关键词： Semantic segmentation Contrastive learning Deep learning

来源：评论

学校读者我要写书评

暂无评论

Sensorless control of SPMSM Based on Generalized Super-twisting Observer and Non-smooth controller

Sensorless Control of SPMSM Based on Generalized Super-twist...

引用

第42届中国控制会议

作者： Dejin Chen Ke Yu Shihong Ding Xiangyu Wang Shihua Li School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education

To enhance the estimation accuracy and dynamic performance of sensorless surface-mounted permanent magnet synchronous motor(SPMSM) drives,a sensorless control scheme based on generalized super-twisting observer(GSTO) and nonsmooth controller is ***,a GSTO for back electromotive force(back-EMF) estimation is *** with the conventional super-twisting observer,the GSTO has a faster convergence rate and stronger robustness due to the additional *** a linear extended state observer(LESO) is adopted to estimate the position,speed,and lumped disturbance at the same ***,a non-smooth composite speed controller is designed by combining the disturbance feed-forward *** with the conventional PI speed controller,the non-smooth controller has a shorter settling time and a better disturbance rejection ***,the effectiveness of the proposed method is verified by simulation results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fall-LSTM:A Fall Detection Network Based on Spatio-Temporal Location Module

Fall-LSTM:A Fall Detection Network Based on Spatio-Temporal ...

引用

第42届中国控制会议

作者： Dapeng Xu Xiaobo Lu Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Southeast University

Fall events have unique dynamic features,which are not fully utilized by existing fall detection *** on video understanding,we propose Fall-LSTM to learn such features pertinently without additional ***-LSTM is composed of CNN-LSTM framework and two excitation modules i.e.,Spatial Attention Module(SAM) and Temporal Location Module(TLM).SAM provides spatial constraints on motion for feature layers through foreground extraction and spatial *** emphasizes frames with high probability of fall events to LSTM by inferring the rate and trend of motion in *** results show that our proposed modules significantly improve the performance of LSTM model,outperforming the state-of-theart methods on two public Fall Detection Datasets i.e.,Le2 i and UR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hmdo: Markerless Multi-View Hand Manipulation Capture with Deformable Objects

SSRN

引用

SSRN 2023年

作者： Xie, Wei Yu, Zhipeng Zhao, Zimeng Zuo, Binghui Wang, Yangang Southeast University The Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China

We construct the first markerless deformable interaction dataset recording interactive motions of the hands and deformable objects, called HMDO (Hand Manipulation with Deformable Objects). Our motivation is the current lack of hand and deformable object interaction datasets, as 3D hand and deformable object reconstruction is challenging. Mainly due to mutual occlusion, the interaction area is difficult to observe, and the visual features between hands and objects are entangled. To tackle this challenge, we propose a method to annotate our captured data. Our key idea is to collaborate with estimated hand features to guide the object pose estimation, and then optimize the deformation process of the object by analyzing the relationship between the hand and the object. Through comprehensive evaluation, the proposed method can reconstruct interactive motions of hands and deformable objects with high quality. In the future, this dataset could boost the research of learning-based reconstruction of deformable interaction scenes. © 2023, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

General Simultaneous Localization and Mapping Scheme for mmWave Communication systems

引用

IEEE Internet of Things Journal 2024年第12期11卷 22521-22536页

作者： Du, Tao Yang, Jie Wen, Chao-Kai Xia, Shuqiang Jin, Shi Southeast University National Mobile Communications Research Laboratory Nanjing210096 China Southeast University Key Laboratory Of Measurement And Control Of Complex Systems Of Engineering Ministry Of Education The Frontiers Science Center For Mobile Information Communication And Security Nanjing210096 China Institute Of Communications Engineering National Sun Yat-sen University Kaohsiung80424 Taiwan Zte Corporation The State Key Laboratory Of Mobile Network And Mobile Multimedia Technology Shenzhen518055 China Southeast University National Mobile Communications Research Laboratory The Frontiers Science Center For Mobile Information Communication And Security Nanjing210096 China

Utilizing high-resolution antenna arrays and wide bandwidth of the millimeter-wave (mmWave) spectrum in 5G new radio (NR) mmWave communication systems holds the potential for high-throughput data transmission while enabling user localization and environmental mapping. However, the majority of existing simultaneous localization and mapping (SLAM) algorithms rely on methods akin to the extended Kalman filter for generating initial map features. These methods prove ineffective when the measurement dimension is insufficient. Furthermore, there is a notable absence of research exploring mmWave prototype systems to evaluate and compare the performance and viability of various SLAM algorithms. To address these challenges, we propose an innovative probability hypothesis density (PHD) generation scheme for birth events and have developed a prototype system. Our approach, referred to as PHD-SLAM, exhibits remarkable effectiveness even in scenarios where the measurement dimension falls short of map features. This means it can function seamlessly with only delay or angle information available. Additionally, we have designed a 28GHz mmWave beam scanning prototype system that leverages the 5G NR frame for accomplishing SLAM algorithms. Following this, we conducted extensive simulations and experimental evaluations to gauge the performance of several leading-edge SLAM algorithms under diverse mmWave circumstances, encompassing PHD-based and belief propagation (BP) SLAM algorithms. Our analysis reveals that both PHD and BP SLAM can achieve agent localization precision within a decimeter and mapping precision within a meter, capitalizing on the angle parameters of mmWave signals. While BP SLAM showcases reduced computational demand, its estimation precision is marginally inferior to that of PHD-SLAM. © 2014 IEEE.

关键词： Belief propagation

来源：评论

学校读者我要写书评

暂无评论

Non-smooth Speed control of Switched Reluctance Motor Based on Generalized Proportional Integral Observer

Non-smooth Speed Control of Switched Reluctance Motor Based ...

引用

第42届中国控制会议

作者： Qingzhao Yin Zheng Tian Shihua Li School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education

This paper investigates the speed regulation control of switched reluctance motor(SRM) *** improve the antidisturbance performance of SRM,a composite non-smooth control strategy is ***,the structure of SRM is analyzed,and a simplified nonlinear model is obtained based on a segmented representation of the varying phase inductance.A virtual control function is introduced to represent the nonlinear part of the torque equation,whose inverse function is cascaded to linearized the nonlinear ***,a generalized proportional integral observer(GPIO) is constructed to estimate the lumped disturbance of the system,which is used for feedforward compensation ***,a composite speed controller is designed based on a combination of finite time proportional feedback and feed-forward compensation based on GPIO(FTP+GPIO).The speed error closed-loop system can be regarded as a first-order finite time control system with bounded *** analysis shows that the proposed scheme can improve the anti-disturbance performance of the closed-loop *** effectiveness of the proposed method is verified by simulation ***,it is compared with proportional feedback combining feed-forward compensation(P+GPIO) method and proportional integral(PI) control method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pylon Reconstruction Based on NeRF

Pylon Reconstruction Based on NeRF

引用

International Conference on Electronics Information and Emergency Communication

作者： Zijian Hu Chenxing Wang School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing China

ISBN: (数字)9798350361896

ISBN: (纸本)9798350361902

In this paper, we propose a pylon reconstruction method based on Neural Radiance Fields (NeRF) technology. The advantage of this method lies in its ability to reconstruct pylons from images, with a multi-view model maintaining good performance even under complex lighting and occlusion conditions. We demonstrate the process of using NeRF to reconstruct electric power towers through experiments. During the experimental process, we collect images of electric power towers from different environments and angles, then apply NeRF to process these images, using deep learning to learn and generate a network model capable of expressing the scene. The experimental results show that our method can complete the reconstruction of scenes with only image inputs, and the reconstructed models have a certain accuracy in terms of geometric details and textures.

关键词： Surface reconstruction Image segmentation Image resolution Shape Poles and towers Lighting Reconstruction algorithms

来源：评论

学校读者我要写书评

暂无评论

Traffic Signal control for Large-Scale Road Networks Based on Deep Reinforcement with PSR

Traffic Signal Control for Large-Scale Road Networks Based o...

引用

Fully Actuated System Theory and Applications (CFASTA), Conference on

作者： Zhicheng Zhou Hui Zhang Ya Zhang School of Automation Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China

ISBN: (数字)9798350373691

ISBN: (纸本)9798350373707

This paper investigates the problem of Traffic Signal control (TSC) in large-scale road networks. In extensive road networks, it is customary to define each intersection as an agent, however, the issue of partial observability is particularly prominent. In this paper, Predictive State Representation (PSR) is employed to address the challenge of partial observability in large-scale multi-agent systems. A Multi-agent Deep Reinforcement Learning (DRL) model based on PSR called PSR-XLight is proposed in Large-Scale TSC systems. Multi-agent PSR is conducted with centralized training and independent filtering which overcome the challenge of prohibitive computations when the number of agents is large. Parameters sharing is adopted between each agent’s PSR model to enhance learning efficiency and facilitate utilization in large-scale multi-agent environments. Each agent undergoes independent DRL training and execution while parameters sharing is adopted. Experiments are conducted on real-world road networks and a large-scale road network comprising 1000 intersections.

关键词： Training Filtering Roads Computational modeling Deep reinforcement learning control systems Observability

来源：评论

学校读者我要写书评

暂无评论

Anomaly-Aware Semantic Self-Alignment Framework for Video-Based Person Re-Identification

Anomaly-Aware Semantic Self-Alignment Framework for Video-Ba...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zhidan Ran Xiaobo Lu Wei Liu School of Automation Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China

Video-based person re-identification (Re-ID) aims at matching the video snippets of the same person across multiple cameras. The ubiquitous appearance misalignment is a critical challenge in video person re-identification. Existing alignment-based methods rely on off-the-shelf human parsing models and cannot handle anomalous appearance information (e.g., obstacles and pedestrian interference) in video sequences. In this paper, we propose Anomaly-Aware Semantic Self-Alignment (ASSA), a novel video-based person Re-ID framework that seeks out body parts without prior human topology information and learns part-based feature representations against anomalous information. The proposed ASSA performs part classifier training and part-aligned representation learning alternately. For the classifier training, we design a Salient Region Extraction module to segment the entire foreground from the background in each input frame. Furthermore, a novel Anomaly-Aware Refinement module is proposed to suppress the influence of anomalous interference. Extensive experiments on three prevalent benchmarks demonstrate the effectiveness and superiority of the proposed framework.

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：