发布求助
文献互助 智能选刊 最新文献

Proceedings of the 2021 4th International Conference on Sensors, Signal and Image Processing最新文献

筛选
英文 中文
DeepLab Network for Meteorological Trough Line Recognition 气象槽线识别的DeepLab网络
Proceedings of the 2021 4th International Conference on Sensors, Signal and Image Processing Pub Date : 2021-10-15 DOI: 10.1145/3502814.3502820
Yali Cai, Qian Li
{"title":"DeepLab Network for Meteorological Trough Line Recognition","authors":"Yali Cai, Qian Li","doi":"10.1145/3502814.3502820","DOIUrl":"https://doi.org/10.1145/3502814.3502820","url":null,"abstract":"A meteorological trough line recognition method is proposed in this paper, in which a DeepLab network that adopts an encoder-decoder architecture is utilized to classify each point in the meteorological grid data into two categories: trough point or not, and then the trough area with the strongest horizontal convergence in the low-pressure area will be identified. The meteorological elements data related to the formation of trough includes the air pressure, the wind velocity and the temperature on 500hp, while the labels are marked with trough lines manually, they are used to train the network model. The proposed method first uses the Deeplab model to recognize the trough area from the meteorological elements data and then extracts the trough line from the trough area by skeleton line extraction algorithm. To evaluate our proposed method, the quantitative experiments were conducted and the results show us that the precission rate of proposed method performances better than the traditional method.","PeriodicalId":115172,"journal":{"name":"Proceedings of the 2021 4th International Conference on Sensors, Signal and Image Processing","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122956584","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
Generic Demosaicking Method for Multispectral Filter Arrays Based on Adaptive Frequency Domain Filtering 基于自适应频域滤波的多谱滤波阵列通用去马赛克方法
Proceedings of the 2021 4th International Conference on Sensors, Signal and Image Processing Pub Date : 2021-10-15 DOI: 10.1145/3502814.3502825
Zechen Wang, Geng Zhang, Bing-liang Hu
{"title":"Generic Demosaicking Method for Multispectral Filter Arrays Based on Adaptive Frequency Domain Filtering","authors":"Zechen Wang, Geng Zhang, Bing-liang Hu","doi":"10.1145/3502814.3502825","DOIUrl":"https://doi.org/10.1145/3502814.3502825","url":null,"abstract":"Multispectral filter arrays (MSFAs) are widely applied to achieve snapshot multispectral imaging on a single image sensor, which causes incomplete data of each channel in the original captured image, and thus a process of estimating missing data named “demosaicking” is needed for high spatial resolution imaging. In a multispectral imaging system equipped with MSFA, as the number of spectral channels increases, the lack of data in the original captured image becomes severer, which brings great challenges to the demosaicking process, and thus classical demosaicking methods for MSFAs often fail to satisfy both reconstructed image quality and computational efficiency. In this paper, we propose a generic demosaicking method for MSFAs based on adaptive frequency domain filtering (AFDF) which achieves high quality of reconstructed images with little computational cost. Experimental results demonstrate that our proposed demosaicking method outperforms the state-of-the-art methods in terms of both quality of reconstructed images and processing time.","PeriodicalId":115172,"journal":{"name":"Proceedings of the 2021 4th International Conference on Sensors, Signal and Image Processing","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128441696","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
Multi-task Command and Control System based on Cloud Architecture 基于云架构的多任务指挥控制系统
Proceedings of the 2021 4th International Conference on Sensors, Signal and Image Processing Pub Date : 2021-10-15 DOI: 10.1145/3502814.3502821
Guangfang Hu, Mingmei Zhang, Ming-Chuan Ni, Wanzeng Cai, Junjie Wang
{"title":"Multi-task Command and Control System based on Cloud Architecture","authors":"Guangfang Hu, Mingmei Zhang, Ming-Chuan Ni, Wanzeng Cai, Junjie Wang","doi":"10.1145/3502814.3502821","DOIUrl":"https://doi.org/10.1145/3502814.3502821","url":null,"abstract":"This paper designs a multi-task command and control system based on cloud architecture. It can greatly facilitate the deployment of multiple command and control tasks. The cloud architecture in this system includes virtualized cloud, container cloud, and desktop cloud. The management nodes in the container cloud and the underlying virtual machines in the desktop cloud are deployed on the virtualized cloud. In order to make full use of and ensure the reliability of data, the data of virtualized cloud, container cloud, and desktop cloud are all stored on distributed storage systems. The system can greatly reduce the operational complexity of operation and maintenance personnel through introducing unified cloud management and comprehensive operation and maintenance.","PeriodicalId":115172,"journal":{"name":"Proceedings of the 2021 4th International Conference on Sensors, Signal and Image Processing","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125669486","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
From Level Line Tree to Iso-Tree 从水平线树到等值线树
Proceedings of the 2021 4th International Conference on Sensors, Signal and Image Processing Pub Date : 2021-10-15 DOI: 10.1145/3502814.3502815
Yuqing Song, Rui Tao
{"title":"From Level Line Tree to Iso-Tree","authors":"Yuqing Song, Rui Tao","doi":"10.1145/3502814.3502815","DOIUrl":"https://doi.org/10.1145/3502814.3502815","url":null,"abstract":"Many applications need a hierarchical image representation as a tool for unifying formalism. The level line tree model is such a tool, using a two-tree (the positive and negative level line trees) scheme to represent an image. The two trees differ only at the level lines meeting the image border, implying the two-tree scheme not a concise representation. In this paper, we propose an iso-tree model to solve the redundancy problem. Our algorithm re-organizes a level line tree such that all level lines not meeting the image border are grouped into a rooted tree, called the closed level line tree; the other level lines are stripped of intersections with the image border, and the remaining segments are grouped into a free tree, called the open iso-tree. The closed level line tree and the open iso-tree together make a concise representation of an image. The representation offers a facility analyzing the objects across the image border. Experiments demonstrated the execution efficiency of the new model as compared with the existing methods.","PeriodicalId":115172,"journal":{"name":"Proceedings of the 2021 4th International Conference on Sensors, Signal and Image Processing","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125971217","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 Image Dimensionality Reduction Algorithms 图像降维算法研究
Proceedings of the 2021 4th International Conference on Sensors, Signal and Image Processing Pub Date : 2021-10-15 DOI: 10.1145/3502814.3502819
Zulun He, Jingjun Zhang
{"title":"Research on Image Dimensionality Reduction Algorithms","authors":"Zulun He, Jingjun Zhang","doi":"10.1145/3502814.3502819","DOIUrl":"https://doi.org/10.1145/3502814.3502819","url":null,"abstract":"This paper summarizes the principle of the Scale Invariant Feature (SIFT), Principal Component Analysis (PCA), and PCANet. Also, the paper uses IPython to realize the similarity comparison using SIFT and handwriting recognization using PCANet, then calculate the precision and recall of the result. The main thing of the SIFT is to find the key point descriptor through the Scale-space, Gaussian Pyramid, and Difference of Gaussian Pyramid (DoG), while the primary purpose of PCA is to find the eigenvalue and eigenvector through calculating the covariance. The combination of the PCA and neuro network, PCANet is divided into three stages.","PeriodicalId":115172,"journal":{"name":"Proceedings of the 2021 4th International Conference on Sensors, Signal and Image Processing","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116153504","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
Implementation and Evaluation of Image Transmission Protocol in Wireless Multimedia Sensor Networks 无线多媒体传感器网络中图像传输协议的实现与评价
Proceedings of the 2021 4th International Conference on Sensors, Signal and Image Processing Pub Date : 2021-10-15 DOI: 10.1145/3502814.3502823
V. Ta, H. Oh
{"title":"Implementation and Evaluation of Image Transmission Protocol in Wireless Multimedia Sensor Networks","authors":"V. Ta, H. Oh","doi":"10.1145/3502814.3502823","DOIUrl":"https://doi.org/10.1145/3502814.3502823","url":null,"abstract":"In wireless multimedia sensor networks (WMSNs), a multimedia sensor node captures an image and sends it to a server via multiple wireless hops. In this process, an image transmission protocol has some stringent requirements such as reliability in data transmission, energy consumption of nodes, and end-to-end delay. This paper implements an image transmission protocol called the pipelined cooperative transmission (PCT) protocol on WMSNs and evaluates its suitability in the viewpoint of the requirements. According to experiments, the protocol could deliver an image of 34 Kbytes within less than 0.4 seconds without any loss of packet and also about 94% of totally generated images, even with a long-distance multi-hop topology and the high interference of WiFi signals.","PeriodicalId":115172,"journal":{"name":"Proceedings of the 2021 4th International Conference on Sensors, Signal and Image Processing","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115165513","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
Estimation of The Surface Quality Of Galvanazed Steel: The Method Of Decomposing The Image Into Layers 镀锌钢表面质量的评价:图像分层分解方法
Proceedings of the 2021 4th International Conference on Sensors, Signal and Image Processing Pub Date : 2021-10-15 DOI: 10.1145/3502814.3502818
A. Nikolaev, O. Logunova, Evgeny Garbar, M. Arkulis, P. Kalandarov
{"title":"Estimation of The Surface Quality Of Galvanazed Steel: The Method Of Decomposing The Image Into Layers","authors":"A. Nikolaev, O. Logunova, Evgeny Garbar, M. Arkulis, P. Kalandarov","doi":"10.1145/3502814.3502818","DOIUrl":"https://doi.org/10.1145/3502814.3502818","url":null,"abstract":"The aim of the study is to increase the reliability of information on the surface quality of galvanized coiled steel in the automated assessment system. The paper presents examples of images of a surface with defects that are visually close but have a different classification. The authors decompose the image into layers and begin to classify the surface defects of materials on the brightness histogram for each layer and image with defects. The research was carried out for the conditions of a large metallurgical enterprise of the Russian Federation. As a result of the study, it was proved that for the bar charts of brightness by image layers, the data used to identify the type of defect are presented.","PeriodicalId":115172,"journal":{"name":"Proceedings of the 2021 4th International Conference on Sensors, Signal and Image Processing","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121706449","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: 6
An Optical Tracking System with Defaced Marker Detection 带有污损标记检测的光学跟踪系统
Proceedings of the 2021 4th International Conference on Sensors, Signal and Image Processing Pub Date : 2021-10-15 DOI: 10.1145/3502814.3502824
Yu Qiu, Zhao Zheng, R. Ou, X. Hu, Jingfan Fan, Jian Yang
{"title":"An Optical Tracking System with Defaced Marker Detection","authors":"Yu Qiu, Zhao Zheng, R. Ou, X. Hu, Jingfan Fan, Jian Yang","doi":"10.1145/3502814.3502824","DOIUrl":"https://doi.org/10.1145/3502814.3502824","url":null,"abstract":"Optical tracking systems (OTSs) have been widely used in clinical practice to fulfill the high precision needs of contemporary surgery. The markers that are defaced in the production or surgery reduce the accuracy and tracking range of OTS. This effect was not considered in current products from either industry or academia. In this paper, we propose an OTS which can detect the defaced markers automatically. A stereo camera module is set to track surgical instruments by locating the markers affixed to them. An adaptive threshold approach is suggested to locate the markers. The typical fiducial localization error of our OTS reaches 0.28 mm, which is totally comparable to commercial devices. A defaced marker detection method based on the luminous energy model of OTS is proposed and can be used to recognize the defaced markers regardless of their relative positions to the OTS.","PeriodicalId":115172,"journal":{"name":"Proceedings of the 2021 4th International Conference on Sensors, Signal and Image Processing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123564989","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
IoT Based License Plate Recognition System Using Deep Learning and OpenVINO 基于物联网的车牌识别系统，使用深度学习和OpenVINO
Proceedings of the 2021 4th International Conference on Sensors, Signal and Image Processing Pub Date : 2021-10-15 DOI: 10.1145/3502814.3502816
Mau-Luen Tham, Weimin Tan
{"title":"IoT Based License Plate Recognition System Using Deep Learning and OpenVINO","authors":"Mau-Luen Tham, Weimin Tan","doi":"10.1145/3502814.3502816","DOIUrl":"https://doi.org/10.1145/3502814.3502816","url":null,"abstract":"Recent advances in artificial intelligence (AI) and computer vision have transformed automatic license plate recognition (ALPR) into an important application for intelligent transportation systems. However, existing algorithms are not directly applicable in the Internet of Things (IoT) environment due to the hardware constraints of processing power. In this paper, we propose a lightweight and accurate IoT-based ALPR solution using deep learning. First, a newly trained YOLOv4-tiny model based on Malaysian car plate is attained via transfer learning. Second, OpenVINO is adopted to optimize the trained model for faster inference time. Third, centroid tracking and geofencing are utilized to collect multiple image instances of the same car plate. Fourth, OpenCV image processing is invoked to segment the characters of each image instance before feeding them into the Tesseract optical character recognition (OCR) engine for character recognition. Fifth, a weighted selection algorithm is designed to choose the best car plate number among the pooled samples. Lastly, the entire solution is deployed in the Up Squared board and powered by the popular IoT Node-Red. Results reveal that the proposed solution has a frame per second (FPS) of 2.6 using Intel Movidius Myriad X, detection accuracy of 99.02 %, and license plate optical character recognition (OCR) accuracy of 78.23%.","PeriodicalId":115172,"journal":{"name":"Proceedings of the 2021 4th International Conference on Sensors, Signal and Image Processing","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115362623","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: 3
Crack-SegNet: Surface Crack Detection in Complex Background Using Encoder-Decoder Architecture 裂纹-分段网:基于编码器-解码器结构的复杂背景表面裂纹检测
Proceedings of the 2021 4th International Conference on Sensors, Signal and Image Processing Pub Date : 2021-10-15 DOI: 10.1145/3502814.3502817
Rong Ran, Xin-yu Xu, S. Qiu, Xiaopeng Cui, Fuhui Wu
{"title":"Crack-SegNet: Surface Crack Detection in Complex Background Using Encoder-Decoder Architecture","authors":"Rong Ran, Xin-yu Xu, S. Qiu, Xiaopeng Cui, Fuhui Wu","doi":"10.1145/3502814.3502817","DOIUrl":"https://doi.org/10.1145/3502814.3502817","url":null,"abstract":"Timely and accurate detection of the initiation and expansion of crack is of great significance for improving safe operation of civil infrastructures. Image-based visual surface inspection has been an indispensable way for long-time infrastructure monitoring. However, existing crack detection methods generally suffer from the interference of complex background, leading to obvious performance drops. To tackle this, an improved encoder-decoder architecture based on SegNet is proposed in this paper, namely crack-SegNet. The encoder network hierarchically learns visual features from the original image, and the decoder network gradually up-samples and maps the encoded features to the input size for the pixel-level classification. In order to enhance the feature capacity of cracks in complex background, a channel attention mechanism is integrated into the encoder, as well as a spatial attention module in the decoder to improve the feature representation of cracks. Meanwhile, a spatial pyramid pooling is also attached to the last convolutional layer of the encoder to capture crack with different scales. To better validate the proposed method, a challenging metal surface crack dataset with much more complex background is collected. Experimental results on the datasets show that the proposed crack-SegNet outperforms other state-of-the-art crack detection methods, especially in complex background.","PeriodicalId":115172,"journal":{"name":"Proceedings of the 2021 4th International Conference on Sensors, Signal and Image Processing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129442439","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
下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信