2022 International Symposium on Intelligent Robotics and Systems (ISoIRS)最新文献_第3页

A complementary object detection method via integrating CNN with Vision Transformer(ViT) 一种CNN与视觉变压器(Vision Transformer, ViT)相结合的互补目标检测方法

2022 International Symposium on Intelligent Robotics and Systems (ISoIRS) Pub Date : 2022-10-01 DOI: 10.1109/isoirs57349.2022.00009

Yibo Gao, NiangWang Wang

{"title":"A complementary object detection method via integrating CNN with Vision Transformer(ViT)","authors":"Yibo Gao, NiangWang Wang","doi":"10.1109/isoirs57349.2022.00009","DOIUrl":"https://doi.org/10.1109/isoirs57349.2022.00009","url":null,"abstract":"The object detection method based on CNN is the mainstream method in the field of object detection because of its special structure of hierarchical and gradual extraction of local features, which can simultaneously consider low-level geometric features and high-level semantic features. However, this structure does not make full use of the global information of the image, resulting in classification errors when the features are limited or fuzzy. To solve the above problems, this paper explores a complementary feature extraction backbone via integrating CNN with Vision Transformer(ViT), and designs a shallow ViT structure to interact features of the proposals in a two-stage object detector with the image background feature to realize global modeling and feature alignment. In addition, according to the particularity of the supplementary structure, a segmented training strategy is designed. This strategy ensures that the model can extract the features together, and maximize the independence of their respective structures, giving full play to the advantages brought by different feature extraction methods. The model is verified on the COCO and PASCAL VOC Datasets. Through the experimental results and feature visualization analysis, it can be concluded that the mAP values are higher than CNN-based and ViT based detectors on the premise of adding limited parameters, which proves the effectiveness of the method.","PeriodicalId":405065,"journal":{"name":"2022 International Symposium on Intelligent Robotics and Systems (ISoIRS)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117203779","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Analysis of Swarm Robotics Cooperative Control Strategy from the Patent Perspective 基于专利视角的群体机器人协同控制策略分析

2022 International Symposium on Intelligent Robotics and Systems (ISoIRS) Pub Date : 2022-10-01 DOI: 10.1109/ISoIRS57349.2022.00039

Xiaofen Fang, Haoran Xu, Bei Chen, Kunli Fang, Guohua Li, Zhijun Mao, Lei Zheng, Jianfu Jiang

引用次数: 0

Research on Computer Information System Based on Neural Network Linear Regression Model 基于神经网络线性回归模型的计算机信息系统研究

2022 International Symposium on Intelligent Robotics and Systems (ISoIRS) Pub Date : 2022-10-01 DOI: 10.1109/ISoIRS57349.2022.00023

Changjian Huang, Liuchun Zhan, Xianfeng Zeng

引用次数: 0

Lightweight super-resolution networks with global and local residual characteristics 具有全局和局部残差特征的轻量级超分辨网络

2022 International Symposium on Intelligent Robotics and Systems (ISoIRS) Pub Date : 2022-10-01 DOI: 10.1109/ISoIRS57349.2022.00012

Yunlong Wang, Lei Xiong, Fengsui Wang, Yue Xu

{"title":"Lightweight super-resolution networks with global and local residual characteristics","authors":"Yunlong Wang, Lei Xiong, Fengsui Wang, Yue Xu","doi":"10.1109/ISoIRS57349.2022.00012","DOIUrl":"https://doi.org/10.1109/ISoIRS57349.2022.00012","url":null,"abstract":"At present, there is a problem of complexity and calculation of the image super-resolution algorithm network. To improve this problem, we propose a lightweight super-resolution network that blends global and local features. First, shallow image features are extracted using a convolutional block, and secondly, deep features are extracted by multiple cascading residual feature distillation blocks GLRB, where in order to achieve a good trade-off between model performance and network parameter quantity, local features are learned by enhancing the feature selection module ESA and the balanced dual-attention module to improve model performance. Then, the extracted residual features are fused, and the reconstructed image is obtained by sub-pixel convolution sampling. The experimental results under multiple standard test data sets show that the reconstructed image performance PSNR is improved by 0.25 dB to 32.23, and the number of model parameters is 470.21 K. Compared with DRCN, CARN, IMDN, RFDN and other algorithms, the proposed algorithm has better model lightweight and image reconstruction quality.","PeriodicalId":405065,"journal":{"name":"2022 International Symposium on Intelligent Robotics and Systems (ISoIRS)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128637140","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Research on Temporal and Spatial Short-Term Traffic Flow Forecasting Model based on Multi-Sensing Data 基于多传感数据的时空短期交通流预测模型研究

2022 International Symposium on Intelligent Robotics and Systems (ISoIRS) Pub Date : 2022-10-01 DOI: 10.1109/isoirs57349.2022.00028

Yantao Shao, Zhihao Wen, Chenzhuo Jin, Caipeng Gu, Lina Wang

{"title":"Research on Temporal and Spatial Short-Term Traffic Flow Forecasting Model based on Multi-Sensing Data","authors":"Yantao Shao, Zhihao Wen, Chenzhuo Jin, Caipeng Gu, Lina Wang","doi":"10.1109/isoirs57349.2022.00028","DOIUrl":"https://doi.org/10.1109/isoirs57349.2022.00028","url":null,"abstract":"The intelligent transportation system mainly includes freeway ramp control, active shift limit and active accident management system. Traffic flow prediction is the key input of active traffic control systems. Accurately predicting road traffic flow is the basic guarantee for the realization of intelligent transportation. In order to improve the prediction accuracy of road traffic flow, this paper proposes a short-term traffic flow prediction method based on the space-time fusion framework. This method uses traffic flow rate, occupancy rate and weather factors to make short-term predictions of traffic flow. Under the framework of space-time fusion, four traffic flow prediction methods are studied: deep neural networks, distributed random forests, gradient propulsion machines and the related performance of generalized linear models. The experiment uses traffic data from Shangtang Elevated Road in Hangzhou City for calibration and evaluation. The results show that under the framework of space-time fusion, the results obtained by the above four prediction models are very similar and can accurately predict road traffic flow. Among them, the accuracy of the distributed random forest model is better than the other three methods.","PeriodicalId":405065,"journal":{"name":"2022 International Symposium on Intelligent Robotics and Systems (ISoIRS)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124488678","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Battlefield Reconnaissance and Monitoring WSN Transport Protocol based on Network Coding 基于网络编码的战场侦察与监控WSN传输协议

2022 International Symposium on Intelligent Robotics and Systems (ISoIRS) Pub Date : 2022-10-01 DOI: 10.1109/ISoIRS57349.2022.00040

Gang Qi, Wei Xia, Ronggen Zhao, Jiangbo Zhao

引用次数: 0

Solving Ascent Trajectory Optimization Problems by Radua Pseudospectral Method 用Radua伪谱法求解上升弹道优化问题

2022 International Symposium on Intelligent Robotics and Systems (ISoIRS) Pub Date : 2022-10-01 DOI: 10.1109/ISoIRS57349.2022.00029

Liaochao Deng, Cheng Xu, Weishuai You

{"title":"Solving Ascent Trajectory Optimization Problems by Radua Pseudospectral Method","authors":"Liaochao Deng, Cheng Xu, Weishuai You","doi":"10.1109/ISoIRS57349.2022.00029","DOIUrl":"https://doi.org/10.1109/ISoIRS57349.2022.00029","url":null,"abstract":"Ascent trajectory optimization problem of air-breathing hypersonic vehicles is a highly nonlinear and nonconvex problems. Most of the early works focus on the traditional indirect method, which needs to derive the complete first-order necessary conditions of the trajectory optimization problem. The derivation process is too complicated and error-prone. Additionally, indirect method has a high demand on the initial guess, and it needs to give the initial guess of covariant variables without physical significance. In this paper, we solve the ascent trajectory optimization problem directly using Radau Pseudospectral Method (RPM). Firstly, the complex three-dimensional ascent trajectory optimization problem is established in detail. Conmmon inequality path constraints including those on dynamic pressure and aerodynamic bending moment are taken into account. The performance index is given as maximizing the final mass considering minimizing the fuel consumption. Subsequently, the ascent trajectory optimization problem is transformed into a nonlinear programming problem (NLP) by RPM. Finally, the ascent trajectory optimization for Generic Hypersonic Aerodynamic Model Example (GHAME) is solved by RPM and the optimal results demonstrate the rapidity, effectiveness and high precision of RPM. The comparison between optimal trajectories with and without path constraints shows that path constraints increase fuel consumption.","PeriodicalId":405065,"journal":{"name":"2022 International Symposium on Intelligent Robotics and Systems (ISoIRS)","volume":"189 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122471894","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Research on Face Recognition System Based on Deep Convolutional Machine Learning Model 基于深度卷积机器学习模型的人脸识别系统研究

2022 International Symposium on Intelligent Robotics and Systems (ISoIRS) Pub Date : 2022-10-01 DOI: 10.1109/ISoIRS57349.2022.00015

Changjian Huang, Liuchun Zhan, Xianfeng Zeng

引用次数: 0

Darknet Detection: A Darknet Traffic Detection Method Based on Improved Between-class Learning 暗网检测:一种基于改进类间学习的暗网流量检测方法

2022 International Symposium on Intelligent Robotics and Systems (ISoIRS) Pub Date : 2022-10-01 DOI: 10.1109/isoirs57349.2022.00024

Binjie Song, Yuanhang Wang, Jixiang Chen, Minxi Liao, Yufei Chang

{"title":"Darknet Detection: A Darknet Traffic Detection Method Based on Improved Between-class Learning","authors":"Binjie Song, Yuanhang Wang, Jixiang Chen, Minxi Liao, Yufei Chang","doi":"10.1109/isoirs57349.2022.00024","DOIUrl":"https://doi.org/10.1109/isoirs57349.2022.00024","url":null,"abstract":"With the development of the Internet, people have paid more attention to privacy protection, and privacy protection technology is widely used. However, it also breeds the darknet, which has become a tool that criminals can exploit, especially in the fields of economic crime and military intelligence. The darknet detection is becoming increasingly important, however, the darknet traffic is seriously unbalanced. The detection is difficult and the accuracy of the detection methods needs to be improved. To overcome these problems, in this paper, we first propose a novel learning method. The method is a Chebyshev distance based Between-class learning (CDBC), which can learn the spatial distribution of the darknet dataset, and generate \"gap data\". The gap data can be used to optimize the distribution boundaries of the dataset. Secondly, a novel darknet traffic detection scheme is proposed. We test the proposed method on the ISCXTor 2016 dataset and the CIC-Darknet 2020 dataset, and the results show that CDBC can help more than 10 existing methods improve accuracy, even up to 99.99%. Compared with other sampling methods, CDBC can also help the classifiers achieve higher recall.","PeriodicalId":405065,"journal":{"name":"2022 International Symposium on Intelligent Robotics and Systems (ISoIRS)","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133317697","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Research on Landscape Design of Coastal Resort from the Perspective of Space Experience and Cognitive and Affective Computing 空间体验与认知情感计算视角下的滨海度假区景观设计研究

2022 International Symposium on Intelligent Robotics and Systems (ISoIRS) Pub Date : 2022-10-01 DOI: 10.1109/ISoIRS57349.2022.00027

Jingwen Yuan, Longlong Zhang, C. Kim

引用次数: 0