检索结果-内蒙古大学图书馆

Chinese Control and Decision Conference, CCDC

作者： Tiansheng Sun Jianning Chi Chengdong Wu Faculty of Robot Science and Engineering Northeastern University Shenyang China

ISBN: (纸本)9781665478977

The main goal of Group Activity Recognition(GAR) is to analyze the group behavior in a multi-actors scene. It is a challenging task that integrates group activity features from individual actors who frequently interact with each other. However, existing state-of-the-art methods do not consider temporal information and take full advantage of spatial relations. Moreover, existing methods utilize max-pooling operation to generate group activity features, which introduces noise into group activity features and leads to bad performance. To tackle these problems, a temporal enhance and spatial gated network is proposed. To fully utilize the rich temporal features and spatial features, two branches are set up to extract temporal features and actor interactive relations, respectively. Then, a feature aggregation module is used to generate group activity features, which can decrease the noise introduced by the max-pooling operation. We conduct a series of experiments on two stand datasets. Experimental results on these benchmarks demonstrate that the proposed approach achieves state-of-the-art performance. Compared with previous work, the recognition accuracy increases by 0.5%~1.0%.

关键词： Logic gates Benchmark testing Activity recognition Feature extraction Behavioral sciences Task analysis

来源：评论

学校读者我要写书评

暂无评论

Joint Semantic and Instance Segmentation in 3D Point Cloud Based on Transformer

Joint Semantic and Instance Segmentation in 3D Point Cloud B...

引用

Chinese Control and Decision Conference, CCDC

作者： Suyi Liu Chengdong Wu Fang Xu Junxiang Wang Jianning Chi Xiaosheng Yu Faculty of Robot Science and Engineering Northeastern University Shenyang China Academia Sinica Shenyang Siasun Robot Automation Co. Ltd Shenyang China

Semantic and instance segmentation in 3D point cloud have made tremendous progress in recent years. In most current methods, semantic and instance segmentation are studied separately, but fall to integrate them. In addition, the irregular domain and lack of ordering make it challenging to design deep neural networks for point cloud learning. In this paper, we propose a joint segmentation method based on Transformer that able to make the two tasks take advantage of each other, leading to a win-win situation. The novel Transformer architecture is used to capture long-short contexts and demonstrates higher segmentation performance. Specifically, for each query point, we use two different key sampling strategies: nearby dense points sampling and distant sparse points sampling. Then, matrix multiplication with query results in two different attention maps, which enables the model to enlarge the effective receptive field. Also, to make the two tasks take advantage of each other, we first combine the semantic perception abstracted from the high-dimensional semantic features with the instance features to enhance instance segmentation performance. Meanwhile, the k-nearest neighbor (KNN) clustering method is used in the instance embedding to find a fixed number of adjacent points for each point in the instance clustering space. The points of the same class are close to each other, the points of different classes are far away from each other, so as to realize the semantic segmentation model of instance embedding. Extensive experiments demonstrate the effectiveness and superiority of our method on S3DIS and ShapeNet datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Vision Based Multi-robot Cooperative Semantic SLAM Algorithm

A Vision Based Multi-robot Cooperative Semantic SLAM Algorit...

引用

Chinese Control and Decision Conference, CCDC

作者： Ji Peng Li Xiaoqiang Gao Wei Li Ming Faculty of Robot Science and Engineering Northeastern University Shenyang China

ISBN: (纸本)9781665478977

The large-scale environmental SLAM which is based on visual information, is an important technical field of mobile robot application. However, a single robot is difficult to achieve the semantic SLAM tasks because of the limited sensing range and the low computing efficiency. This problem can be effectively solved by multi-robot cooperation that is using their collected visual information to model together. In this paper, a vision based multi-robot cooperative semantic SLAM algorithm is proposed. Moreover, to achieve the distributed map splicing that is constructed by several heterogeneous robot, a cloud computing method is also proposed detailedly. Besides, to satisfy the demand of low bandwidth and data transmission between robots and cloud, a high density information representation and a transmission strategy against spatiotemporal delay are designed. On this basis, the LEDNET model is used to obtain the semantic information of environmental feature points. Then, the centroid of map points is obtained to calculate the position information of objects in the environment, the attitude information of objects in the environment is determined by principal component analysis, and a multi map stitching method based on key frame is established to realize the collaborative slam of multi robots. Through the map mosaic test of three robots on KITTI data set, the multi-robot cooperative SLAM algorithm proposed in this paper can quickly and accurately construct the semantic map of large-scale environment.

关键词： Point cloud compression Visualization Cloud computing Simultaneous localization and mapping Computational modeling Splicing Semantics

来源：评论

学校读者我要写书评

暂无评论

Synchronization Control of Delayed Inertial Neural Networks with Semi-Markovian Jumping

Synchronization Control of Delayed Inertial Neural Networks ...

引用

第42届中国控制会议

作者： Junyi Cui Huixia Cui Yingxin Zhang Junyi Wang Min Lei College of Information Science and Engineering Northeastern University Faculty of Robot Science and Engineering Northeastern University NO.710 R&D Institute CSIC

This article deals with the synchronization issue of the time-varying delayed inertial neural networks(INNs) with semi-Markovian jumping(SMJ).The synchronization criteria of the system can be obtained by using the Lyapunov-Krasovskii functional(LKF) and a general free-matrix-based integral *** addition,the mode-dependent control gain matrices are obtained based on synchronization *** last,an example is proposed to show the validity of the theoretical results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

robot Grasping Detection in Object Overlapping Scenes Based on Multi-Stage ROI Extraction

Robot Grasping Detection in Object Overlapping Scenes Based ...

引用

Chinese Control and Decision Conference, CCDC

作者： Jintao Xia Jianning Chi Chengdong Wu Fengyu Zhao Faculty of Robot Science and Engineering Northeastern University Shenyang China

ISBN: (纸本)9781665478977

In multi-object stacking scenes, it is difficult for robots to detect and grasp objects. We propose a new robot grasp detection algorithm Multi-Stage ROI Grasp Detection(MSROI-GD). MSROI-GD uses multi-stage extracted ROI features to detect objects and grasp. Our algorithm can effectively filter and utilize ROI. Experimental results show that the improved MSROI-GD improves the accuracy of the original ROI-GD algorithm by 4.3%, and exceeds the current state-of-the-art algorithm by 0.5% in the overlapping scenes of objects in the VMRD dataset. At the same time, using our grasp detection algorithm on the Cornell grasp dataset still has good results. robot experiments show that MSROI-GD can help robots grasp object in multi-object scenes with a success rate of 85%.

关键词： Stacking Grasping Filtering algorithms Feature extraction Detection algorithms robots

来源：评论

学校读者我要写书评

暂无评论

Neural network equivalent model for highly efficient massive data classification

引用

science China(Information sciences) 2023年第3期66卷 287-288页

作者： Siquan YU Zhi HAN Yandong TANG Chengdong WU School of Information Science and Engineering Northeastern University Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Faculty of Robot Science and Engineering Northeastern University

Dear editor, Recently, neural networks(NNs) have been successfully applied to massive data classification tasks [1, 2]. However,there is an inconsistent problem in neural network structure and convergence [3]. On one hand, under the overparameterize assumption, it requires to design a complex network to guarantee the convergence [4].

关键词：

来源：评论

学校读者我要写书评

暂无评论

Vision-Based Indoor Positioning System for Connected Vehicles in Small-scale Testbed Environments

Vision-Based Indoor Positioning System for Connected Vehicle...

引用

IEEE Symposium on Intelligent Vehicle

作者： Mahmoud S. Hamza Omar M. Shehata Elsayed I. Morgan Catherine M. Elias Multi-Robot Systems (MRS) Research Group Cairo Egypt Mechatronics Department Faculty of Engineering and Materials Science German University Cairo Egypt Mechatronics Department Faculty of Engineering Ain Shams University Cairo Egypt Science Department Faculty of Media Engineering and Technology German University Cairo Egypt

ISBN: (数字)9798350348811

ISBN: (纸本)9798350348828

In this paper, we present an innovative indoor positioning system designed for computing the position and orientation of multiple model-scale vehicles. Our system, equipped with four cameras, utilizes a novel image-stitching technique to stitch the images from these cameras into a single output image. We explore diverse methodologies for detecting and estimating the position and orientation of the model-scale vehicles, demonstrating robust detection within the plane. Through rigorous testing with vehicles of varying dimensions, our system achieves an accuracy ranging from approximately 0.5cm to 3cm on both axes. This establishes the system’s potential applicability in scenarios involving model-scale autonomous vehicles, where precise knowledge of each vehicle’s position is critical.

关键词： Connected vehicles Accuracy Computational modeling Cameras Distance measurement Indoor positioning systems Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Multi-object Grasping Detection in Cluttered Scenes Based on Deep Learning 11

Multi-object Grasping Detection in Cluttered Scenes Based on...

引用

11th IEEE Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2021

作者： Wu, Xiangrui Xu, Fang Du, Zhenjun Song, Jilai Liu, Mingmin Liu, Hongyan Du, Kun Guo, Mingce Northeastern University Faculty of Robot Science and Engineering Shenyang110169 China SIASUN Robot Automation Co. Ltd Shenyang110168 China

ISBN: (纸本)9781665425278

In this paper, we mainly improved the grasp detection network based on the grasp pose detection (GPD) algorithm. Three Network in Network (NIN) structure blocks are used as feature extraction modules, and a fully connected layer is used for classification. And trained the network on our own dataset which these 3D models are all from GraspNetAPI, and the accuracy rate on the test set is 2% higher than the original network. And the amount of its parameters has dropped by 38%. In addition, we combine the Mask R-CNN semantic segmentation network to perform target detection and pixel-level instance segmentation on target objects, which can grasp objects of interest. Finally, we carried out grasping experiments on real robots, and the total grasping success rate was over 70%. © 2021 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Optic Disc Detection Based on Fully Convolutional Network and Weighted Matrix Recovery Model

SSRN

引用

SSRN 2023年

作者： Wang, Siqi Yu, Xiaosheng Chi, Jianning Lv, Pengfei Wang, Junxiang Wu, Chengdong Faculty of Robot Science and Engineering Northeastern University NO. 195 Chuangxin Road Liaoning Shenyang110170 China

Accurate detection of the optic disc contour is one of the important steps in diagnosing eye diseases. Considering that the optic disc is usually a saliency region in fundus images, we propose a weakly-supervised optic disc detection method based on the fully convolution neural network (FCN) combined with the weighted low-rank matrix recovery model (WLRR). Firstly, we extract the low-level features of the fundus image and cluster the pixels using the Simple Linear Iterative Clustering (SLIC) algorithm to generate the feature matrix. Secondly, the top-down semantic prior information provided by FCN and bottom-up background prior information of the optic disc region are used to jointly construct the prior information weighting matrix, which more accurately guides the decomposition of the feature matrix into a sparse matrix representing the optic disc and a low-rank matrix representing the background. Experimental results show that our method can segment the optic disc region accurately. © 2023, 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

Emotional EEG Prediction Based on Spatial-Temporal Graph Convolutional Neural Network

Emotional EEG Prediction Based on Spatial-Temporal Graph Con...

引用

Rehabilitation engineering and Assistive Technology (i-CREATe), International Convention on

作者： Jinying Bi Fei Wang Fangzhou Hu Hao Li Gangguo Qu Shuai Han Faculty of Robot Science and Engineering Northeastern University Shenyang China College of Information Science and Engineering Northeastern University Shenyang China Department of Neurosurgery Shengjing Hospital of China Medical University Shenyang China

ISBN: (数字)9798350355154

ISBN: (纸本)9798350355161

Background and Objective: Emotions are an integral part of our daily lives and have a significant impact on brain neural activities. However, most traditional studies on electroencephalogram (EEG) emotions have focused on identification and classification, without effectively predicting future EEG based on existing emotional EEG signals. This paper introduces a spatial-temporal graph convolutional neural network (STGCNN) to integrate temporal and spatial features of EEG, capturing more emotional information. Methods: After calculating the brain functional network operating Pearson correlation, it is utilized as the input information of the model together with the frequency domain differential entropy (DE). Information prediction in the spatiotemporal domain is mainly achieved through two cross structures of two temporal convolutions and one spatial convolution. Meanwhile, an ablation experiment is designed to illustrate the practicality of the model. Results and Conclusion: The performance of the model is evaluated on the SEED dataset for mixed and single emotions across three sessions and three frequency bands by metrics: Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Weighted Mean Absolute Percentage Error (WMAPE). All performance metrics confirm the predictability of EEG-based emotions, demonstrating the effectiveness of STGCNN for the prediction of EEG. Significance: Accurately emotional EEG prediction is crucial for brain neural rehabilitation training and forecasting.

关键词： Training Measurement Convolution Frequency-domain analysis Neural activity Brain modeling Electroencephalography Spatiotemporal phenomena Convolutional neural networks Root mean square

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：