检索结果-内蒙古大学图书馆

IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems

作者： Yi Guo Hao Chu Jinxiu Wu Ze Shen Fei Wang College of Information Science and Engineering Northeastern University Shenyang China Faculty of Robot Science and Engineering Northeastern University Shenyang China

The advent of cost-effective RGB-D sensors has made it more feasible to achieve high-precision 6D pose prediction from RGB-D images. One of the primary research challenges entails extracting distinctive features from the color features presented in RGB images, as well as capturing geometric details from depth data, while effectively harnessing the synergistic potential of these two mutually complementary data sources. In this study, we propose a bidirectional attention context fusion framework for learning 6D pose parameters from RGB-D images. Specifically, we introduce a lightweight attention mechanism to improve the ability of appearance features learning from RGB images. Additionally, we design a features extraction framework of point clouds to fully explore the spatial information of the local distance structure within the neighborhood and more representative global features obtained by hybrid contextual local information. Furthermore, we combine the speed-up robust feature algorithm with the farthest point sampling algorithm, taking full advantage of our appearance and geometric information extraction to predict pose estimation. In the experimental results, we provide compelling evidence that our method surpasses the performance of state-of-the-art methods on two demanding benchmark datasets, LineMOD and YCB-Video.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A robot Grasp Relationship Detection Network Based on the Fusion of Multiple Features 33

A Robot Grasp Relationship Detection Network Based on the Fu...

引用

第33届中国控制与决策会议

作者： Jianning Chi Xingrui Wu Changqing Ma Xiaosheng Yu Chengdong Wu College of Robot Science and Engineering Northeastern University College of Information Science and Engineering Northeastern University

ISBN: (纸本)9781665431293

Grasp is one of the main ways for robots to interact with the real ***,there are many approaches in grasp detection using deep *** can successfully detect one or multi grasp locations from an RGB *** it comes to a scene with multiple objects,they still need the relationships of the objects to instruct robotics in grasping *** this paper,we present a new deep convolutional neural network approach for detecting all potential objects and predicting grasp relation ships of them from an RGB *** each object pair,we firstly generate not only their visual features,but also their spatial masks and semantic embedding vectors from three *** we integrate these features as input to obtain their grasp *** results show that our proposed approach outperforms the state-of-the-art and achieves 73.78% accuracy on the Visual Manipulation Relationship Dataset(VMRD).

关键词： robot Grasp Relationship Convolutional Neural Network Spatial Masks

来源：评论

学校读者我要写书评

暂无评论

A Lightweight and Dynamic Convolutional Network for Real-time Semantic Segmentation

A Lightweight and Dynamic Convolutional Network for Real-tim...

引用

第35届中国控制与决策会议

作者： Chunyu Zhang Fang Xu Chengdong Wu Faculty of Robot Science and Engineering Northeastern University Shenyang Siasun Robot & Automation Company Ltd

Semantic segmentation is a difficult task that satisfies most of the demands of autonomous driving and drone aerial photography in a unified *** neural networks can properly categorize image pixels via end-to-end model ***,achieving the optimal trade-off between segmentation precision and the number of network parameters while maintaining a suitable inference time has become a challenging *** this paper,we propose a lightweight dynamic convolutional semantic segmentation network,LDCNet,which belongs to the asymmetric network ***,we designed a coding module that includes dynamic convolution:*** success of this module is attributed to the use of dynamic convolution,which increases the utilization of local and contextual information of the *** also designed the decoding module containing feature pyramids and hybrid attention:HA-FP,which performs a multi-scale fusion of features accompanied by feature *** the Cityscapes and Camvid datasets,LDCNet obtains 73.5 mIoU and 69.4 mIoU accuracy with 78.4 FPS and91.3 FPS,respectively,without pre-training or *** experimental findings reveal that LDCNet achieves an outstanding balance between segmentation accuracy and network parameters with just 0.96 M.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Joint Segmentation and Grasp Pose Detection with Multi-Modal Feature Fusion Network

Joint Segmentation and Grasp Pose Detection with Multi-Modal...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Xiaozheng Liu Yunzhou Zhang He Cao Dexing Shan Jiaqi Zhao College of Information Science and Engineering Northeastern University Shenyang China Faculty of Robot Science and Engineering Northeastern University Shenyang China

Efficient grasp pose detection is essential for robotic manipulation in cluttered scenes. However, most methods only utilize point clouds or images for prediction, ignoring the advantages of different features. In this paper, we present a multi-modal fusion network for joint segmentation and grasp pose detection. We design a point cloud and image co-guided feature fusion module that can be used to fuse features and adaptively estimate the importance of the point-pixel feature pairs. Moreover, we develop a seed point sampling algorithm that simultaneously considers the distance, semantics and attention scores. For selected seed points, we adopt a local feature aggregation module to fully utilize the local spatial features in the grasp region. Experimental results on the GraspNet-lBillion Dataset show that our network outperforms several state-of-the-art methods. We also conduct real robot grasping experiments to demonstrate the effectiveness of our approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fully Asynchronous Neuromorphic Perception for Mobile robot Dodging with Loihi Chips

arXiv

引用

arXiv 2024年

作者： Jiang, Junjie Kong, Delei Hu, Chenming Fang, Zheng Faculty of Robot Science and Engineering Northeastern University Shenyang China School of Robotics Hunan University Changsha China

Sparse and asynchronous sensing and processing in natural organisms lead to ultra low-latency and energy-efficient perception. Event cameras, known as neuromorphic vision sensors, are designed to mimic these characteristics. However, fully utilizing the sparse and asynchronous event stream remains challenging. Influenced by the mature algorithms of standard cameras, most existing event-based algorithms still rely on the"group of events" processing paradigm (e.g., event frames, 3D voxels) when handling event streams. This paradigm encounters issues such as feature loss, event stacking, and high computational burden, which deviates from the intended purpose of event cameras. To address these issues, we propose a fully asynchronous neuromorphic paradigm that integrates event cameras, spiking networks, and neuromorphic processors (Intel Loihi). This paradigm can faithfully process each event asynchronously as it arrives, mimicking the spike-driven signal processing in biological brains. We compare the proposed paradigm with the existing"group of events" processing paradigm in detail on the real mobile robot dodging task. Experimental results show that our scheme exhibits better robustness than frame-based methods with different time windows and light conditions. Additionally, the energy consumption per inference of our scheme on the embedded Loihi processor is only 4.30% of that of the event spike tensor method on NVIDIA Jetson Orin NX with energy-saving mode, and 1.64% of that of the event frame method on the same neuromorphic processor. As far as we know, this is the first time that a fully asynchronous neuromorphic paradigm has been implemented for solving sequential tasks on real mobile robot. © 2024, CC BY.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Group-Mix SAM: Lightweight Segmentation Solution for Industrial Implementations

Group-Mix SAM: Lightweight Segmentation Solution for Industr...

引用

Cognitive Computing and Complex Data (ICCD), International Conference on the

作者： Liang Wu Puhong Duan Xiaoguang Ma Faculty of Robot Science and Engineering Northeastern University Shenyang China School of Robotics Hunan University Changsha China

ISBN: (数字)9798350352894

ISBN: (纸本)9798350352900

Since its emergence in early 2023, Segment Anything Model(SAM) has garnered significant academic interests and spawned many investigations from various perspectives due to its zero-shot generalization ability. However, the deployment of SAM in scenes that required real-time performance, such as industrial assembly liners, had severe challenges due to its heavy image encoder, whose parameters were as large as 632M. In this study, we proposed a lightweight segmentation solution for industrial assembly line applications, wherein the heavyweight image encoder was replaced with a lightweight one. Specifically, we employed decoupled distillation to train the encoder of MobileSAM in a resource-limited setting. The entire knowledge distillation experiment could be completed in a single day on a single RTX 4090. The resulting lightweight SAM, called Group- Mix SAM, had 37.63% (2.16M) fewer parameters and 42.5% (15614.7M) fewer floating-point operations compared to MobileSAM. Additionally, on our homemade industrial dataset: MALD, its mIoU was only marginally lower than that of MobileSAM, at 0.615. Finally, we conducted comprehensive experiments to demonstrate the superiority of Group-Mix SAM in real industrial scenes.

关键词： Image segmentation Computational modeling Computer architecture Real-time systems Data models Cognitive systems Assembly

来源：评论

学校读者我要写书评

暂无评论

EV-MGDispNet: Motion-Guided Event-Based Stereo Disparity Estimation Network with Left-Right Consistency

arXiv

引用

arXiv 2024年

作者： Jiang, Junjie Zhuang, Hao Huang, Xinjie Kong, Delei Fang, Zheng Faculty of Robot Science and Engineering Northeastern University Shenyang China School of Robotics Hunan University Changsha China

Event cameras have the potential to revolutionize the field of robot vision, particularly in areas like stereo disparity estimation, owing to their high temporal resolution and high dynamic range. Many studies use deep learning for event camera stereo disparity estimation. However, these methods fail to fully exploit the temporal information in the event stream to acquire clear event representations. Additionally, there is room for further reduction in pixel shifts in the feature maps before constructing the cost volume. In this paper, we propose EV-MGDispNet, a novel event-based stereo disparity estimation method. Firstly, we propose an edge-aware aggregation (EAA) module, which fuses event frames and motion confidence maps to generate a novel clear event representation. Then, we propose a motion-guided attention (MGA) module, where motion confidence maps utilize deformable transformer encoders to enhance the feature map with more accurate edges. Finally, we also add a census left-right consistency loss function to enhance the left-right consistency of stereo event representation. Through conducting experiments within challenging real-world driving scenarios, we validate that our method outperforms currently known state-of-the-art methods in terms of mean absolute error (MAE) and root mean square error (RMSE) metrics. Copyright © 2024, The Authors. All rights reserved.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Adaptive Merging and Coordinated Offspring Generation in Multi-Population Evolutionary Multi-Modal Multi-Objective Optimization 5

Adaptive Merging and Coordinated Offspring Generation in Mul...

引用

5th International Conference on Data-Driven Optimization of Complex Systems, DOCS 2023

作者： Wang, Xiangyu Zheng, Tianzi Jin, Yaochu Bielefeld University Faculty of Technology Bielefeld Germany College of Information Science and Engineering Northeastern University Shenyang China

ISBN: (纸本)9798350393521

Multi-modal multi-objective optimization problems (MMOPs) have attracted increased attention in recent years, where solutions share the same Pareto front in the objective space but distribute differently in the decision space. However, most existing multi-modal multi-objective evolutionary algorithms fail to or have a low convergence speed to solve high-dimensional MMOPs with sparse Pareto optimal solutions, which have found a wide range of applications in many areas, such as neural architecture search and feature selection. To find a suitable number of Pareto optimal sets quickly, we propose an adaptive merging method in multi-population, in which subpopulations satisfying a certain criterion are merged into one subpopulation in this work. In addition, a coordinated offspring generation strategy that takes into account the sparsity ratio of the current subpopulations is introduced to generate more promising off-spring solutions, where dimensions with high sparsity should have a higher chance of being mutated. Comparative experimental results comparing four state-of-the-art peer algorithms on eight widely used benchmark problems verify the effectiveness of the proposed method. © 2023 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Collecting and analyzing key-value data under shuffled differential privacy

引用

Frontiers of Computer science 2023年第2期17卷 241-243页

作者： Ning WANG Wei ZHENG Zhigang WANG Zhiqiang WEI Yu GU Peng TANG Ge YU Faculty of Information Science and Engineering Ocean University of ChinaQingdao 266100China School of Computer Science and Engineering Northeastern UniversityShenyang 110819China Key Lab of Cryptologic Technology and Information Security Ministry of EducationShandong UniversityQingdao 266200China School of Cyber Science and Technology Shandong UniversityQingdao 266200China

1 Introduction Key-value data,as NoSQL data widely used in recent years,has been frequently collected and used for analysis in major websites and mobile *** frequency distribution estimation on the key domain,as well as the mean estimation of values associated with the same key,are crucial and worth billion dollars in the ***,in real applications,the key-value records are submitted by terminal devices of different *** collecting the information from users may pose serious risks on personal *** the other hand,the emerging shuffled differential privacy(SDP)model[1]is proposed to collect sensitive data from users.

关键词： NoSQL app value

来源：评论

学校读者我要写书评

暂无评论

HAG: Hierarchical Attention with Graph Network for Dialogue Act Classification in Conversation 48

HAG: Hierarchical Attention with Graph Network for Dialogue ...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Fu, Changzeng Chen, Zhenghan Shi, Jiaqi Wu, Bowen Liu, Chaoran Ishi, Carlos Toshinori Ishiguro, Hiroshi Northeastern University Sstc China Osaka University Graduate School of Engineering Science Japan Riken Interactive Robot Research Team Guardian Robot Project Japan Peking University School of Software and Microelectronics China

ISBN: (纸本)9781728163277

The prediction of dialogue acts (DA) labels on utterance-level in conversations can be treated as a sequence labeling problem, which requires context- and speaker-aware semantic comprehension, especially for Japanese. In this study, we pro-posed a hierarchical attention with the graph neural network (HAG) to consider the contextual interconnections as well as the semantics carried by the sentence itself. Concretely, the model use long-short term memory networks (LSTMs) to perform a context-aware encoding within a dialogue window. Then, we construct the context graph by aggregating the neighboring utterances. Subsequently, a speaker feature transformation is executed with a graph attention network (GAT) to calculate the interconnections, while a context-level feature selection is performed with a gated graph convolutional network (GatedGCN) to select the salient utterances that contribute to the DA classification. Finally, we merge the representations of different levels and conduct a classification with two dense layers. We evaluate the proposed model on Japanese dialogue act dataset (JPS-DA). The experimental results show that our method outperforms the baselines. © 2023 IEEE.

关键词： Graph neural networks

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：