发布求助

文献互助智能选刊最新文献

Anais Estendidos da XXXIV Conference on Graphics, Patterns and Images (SIBRAPI Estendido 2021)最新文献

筛选

英文中文

KutralNext: An Efficient Multi-label Fire and Smoke Image Recognition Model KutralNext:一种高效的多标签火灾和烟雾图像识别模型

Anais Estendidos da XXXIV Conference on Graphics, Patterns and Images (SIBRAPI Estendido 2021) Pub Date : 2021-10-18 DOI: 10.5753/sibgrapi.est.2021.20007

Angel Ayala, David Macêdo, C. Zanchettin, Francisco Cruz, Bruno Fernandes

{"title":"KutralNext: An Efficient Multi-label Fire and Smoke Image Recognition Model","authors":"Angel Ayala, David Macêdo, C. Zanchettin, Francisco Cruz, Bruno Fernandes","doi":"10.5753/sibgrapi.est.2021.20007","DOIUrl":"https://doi.org/10.5753/sibgrapi.est.2021.20007","url":null,"abstract":"Early alert fire and smoke detection systems are crucial for management decision making as daily and security operations. One of the new approaches to the problem is the use of images to perform the detection. Fire and smoke recognition from visual scenes is a demanding task due to the high variance of color and texture. In recent years, several fire-recognition approaches based on deep learning methods have been proposed to overcome this problem. Nevertheless, many developments have been focused on surpassing previous state-of-the-art model's accuracy, regardless of the computational resources needed to execute the model. In this work, is studied the trade-off between accuracy and complexity of the inverted residual block and the octave convolution techniques, which reduces the model's size and computation requirements. The literature suggests that those techniques work well by themselves, and in this research was demonstrated that combined, it achieves a better trade-off. We proposed the KutralNext architecture, an efficient model with reduced number of layers and computacional resources for singleand multi-label fire and smoke recognition tasks. Additionally, a more efficient KutralNext+ model improved with novel techniques, achieved an 84.36% average test accuracy in FireNet, FiSmo, and FiSmoA fire datasets. For the KutralSmoke and FiSmo fire and smoke datasets attained an 81.53% average test accuracy. Furthermore, state-of-the-art fire and smoke recognition model considered, FireDetection, KutralNext uses 59% fewer parameters, and KutralNext+ requires 97% fewer flops and is 4x faster.","PeriodicalId":110864,"journal":{"name":"Anais Estendidos da XXXIV Conference on Graphics, Patterns and Images (SIBRAPI Estendido 2021)","volume":"207 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122990570","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

Coffee Leaf Diseases Identification and Severity Classification using Deep Learning 基于深度学习的咖啡叶病害识别与严重程度分类

Anais Estendidos da XXXIV Conference on Graphics, Patterns and Images (SIBRAPI Estendido 2021) Pub Date : 2021-10-18 DOI: 10.5753/sibgrapi.est.2021.20039

E. Lisboa, Givanildo Lima, Fabiane Queiroz

引用次数: 2

Methods for segmentation of spinal cord and esophagus in radiotherapy planning computed tomography 放射治疗计划中脊髓和食管分割的计算机断层扫描方法

Anais Estendidos da XXXIV Conference on Graphics, Patterns and Images (SIBRAPI Estendido 2021) Pub Date : 2021-10-18 DOI: 10.5753/sibgrapi.est.2021.20009

J. O. Diniz, A. Silva, A. Paiva

引用次数: 0

On periodic tilings with regular polygons 在正则多边形的周期性平铺上

Anais Estendidos da XXXIV Conference on Graphics, Patterns and Images (SIBRAPI Estendido 2021) Pub Date : 2021-10-18 DOI: 10.5753/sibgrapi.est.2021.20025

José Ezequiel Soto Sánchez, Asla Medeiros e Sá, L. H. Figueiredo

引用次数: 2

Avaliação de Modelos de Detecção de Objetos para Detectar Glomérulos em Imagens Histológicas 组织学图像中肾小球检测对象检测模型的评价

Anais Estendidos da XXXIV Conference on Graphics, Patterns and Images (SIBRAPI Estendido 2021) Pub Date : 2021-10-18 DOI: 10.5753/sibgrapi.est.2021.20028

Abel Ramalho Galvão, Jonathan M. C. Rehem, W. L. C. D. Santos, Luciano Rebouças de Oliveira, A. A. Duarte, M. F. Angelo

引用次数: 0

Virtual lines for offside situations analysis in football 用于足球越位分析的虚拟线

Anais Estendidos da XXXIV Conference on Graphics, Patterns and Images (SIBRAPI Estendido 2021) Pub Date : 2021-10-18 DOI: 10.5753/sibgrapi.est.2021.20037

Karim Ferreira Lima, R. M. D. Figueiredo, Eduardo Augusto Martins, Jean Schmith

{"title":"Virtual lines for offside situations analysis in football","authors":"Karim Ferreira Lima, R. M. D. Figueiredo, Eduardo Augusto Martins, Jean Schmith","doi":"10.5753/sibgrapi.est.2021.20037","DOIUrl":"https://doi.org/10.5753/sibgrapi.est.2021.20037","url":null,"abstract":"Offside is one of the situations that is analyzed by the Video Assistant Referee (VAR). However, it has caused some controversy due to the delay in the analysis and definition of the irregularity. This work proposes a method that helps in the analysis of offside situations and also makes it available for nonprofessional matches. Here, image processing algorithms were used to determine offside situations in football matches from TV videos, of course, in accordance with the game regulation. The method includes the image vanishing point identification, camera calibration and the virtual offside line drawing. The method presented good results from 10 videos selected for analysis, with five from the right side of the field and five on from the left side. Among the videos, one was chosen as the basis for explaining the development of the method and demonstrate a situation with a virtual line drawn automatically, therefore determining an offside situation. As a result, the virtual line is identified by the color red when the manually selected player is in offside and green when he is not.","PeriodicalId":110864,"journal":{"name":"Anais Estendidos da XXXIV Conference on Graphics, Patterns and Images (SIBRAPI Estendido 2021)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121487921","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

Segmentation and graph generation of muzzle images for cattle identification 用于牛识别的口吻图像分割与图形生成

Anais Estendidos da XXXIV Conference on Graphics, Patterns and Images (SIBRAPI Estendido 2021) Pub Date : 2021-10-18 DOI: 10.5753/sibgrapi.est.2021.20033

Lucas Wojcik, J. Junior, D. Menotti, J. Hill

{"title":"Segmentation and graph generation of muzzle images for cattle identification","authors":"Lucas Wojcik, J. Junior, D. Menotti, J. Hill","doi":"10.5753/sibgrapi.est.2021.20033","DOIUrl":"https://doi.org/10.5753/sibgrapi.est.2021.20033","url":null,"abstract":"The current methods for the organizing the records (i.e., cataloguing) of cattle are known to be archaic and inefficient, and often harmful to the animal. Such methods include the use of metal tags attached to the animal's ears like earrings and of branding irons on their necks. Previous research on new methods of livestock branding based on computer vision techniques utilized a mixture of texture features such as Gabor Filters and Local Binary Pattern as a means of extracting identifying features for each animal. The presented approach proposes a new technique using the muzzle image as an individual identifier as a novel technique, assuming that the muzzle RoI taken as input for the model pipeline is already extracted and cropped. This task is performed in three steps. First, the muzzle image is segmented via a convolutional neural network, resulting in a bitmap from which a graph structure is extracted in the second phase. The final phase consists of matching the resulting graph with the ones previously extracted and stored in the database for an optimal match. The results for the segmentation quality show a fidelity of around seventy percent, while the extracted graph perfectly represents the extracted bitmap. The matching algorithm is currently in progress.","PeriodicalId":110864,"journal":{"name":"Anais Estendidos da XXXIV Conference on Graphics, Patterns and Images (SIBRAPI Estendido 2021)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134507297","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

A Comparative Study of Text Document Representation Approaches Using Point Placement-based Visualizations 基于点放置的可视化文本文档表示方法的比较研究

Anais Estendidos da XXXIV Conference on Graphics, Patterns and Images (SIBRAPI Estendido 2021) Pub Date : 2021-10-18 DOI: 10.5753/sibgrapi.est.2021.20035

Hevelyn Sthefany Lima de Carvalho, Vinícius R. P. Borges

{"title":"A Comparative Study of Text Document Representation Approaches Using Point Placement-based Visualizations","authors":"Hevelyn Sthefany Lima de Carvalho, Vinícius R. P. Borges","doi":"10.5753/sibgrapi.est.2021.20035","DOIUrl":"https://doi.org/10.5753/sibgrapi.est.2021.20035","url":null,"abstract":"In natural language processing, text representation plays an important role which can affect the performance of language models and machine learning algorithms. Basic vector space models, such as the term frequency-inverse document frequency, became popular approaches to represent text documents. In the last years, approaches based on word embeddings have been proposed to preserve the meaning and semantic relations of words, phrases and texts. In this paper, we focus on studying the influences of different text representations to the quality of the 2D visual spaces (layouts) generated by state-of-art visualizations based on point placement. For that purpose, a visualizationassisted approach is proposed to support users when exploring such representations in classification tasks. Experimental results using two public labeled corpora were conducted to assess the quality of the layouts and to discuss possible relations to the classification performances. The results are promising, indicating that the proposed approach can guide users to understand the relevant patterns of a corpus in each representation.","PeriodicalId":110864,"journal":{"name":"Anais Estendidos da XXXIV Conference on Graphics, Patterns and Images (SIBRAPI Estendido 2021)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133647794","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

A Novel Human-Machine Hybrid Framework for Person Re-Identification from Full Frame Videos 基于人机混合框架的全帧视频人物再识别

Anais Estendidos da XXXIV Conference on Graphics, Patterns and Images (SIBRAPI Estendido 2021) Pub Date : 2021-10-18 DOI: 10.5753/sibgrapi.est.2021.20013

Felix Olivier Sumari Huayta, E. Clua, Joris Guérin

{"title":"A Novel Human-Machine Hybrid Framework for Person Re-Identification from Full Frame Videos","authors":"Felix Olivier Sumari Huayta, E. Clua, Joris Guérin","doi":"10.5753/sibgrapi.est.2021.20013","DOIUrl":"https://doi.org/10.5753/sibgrapi.est.2021.20013","url":null,"abstract":"With the major adoption of automation for cities security, person re-identification (Re-ID) has been extensively studied. In this dissertation, we argue that the current way of studying person re-identification, i.e. by trying to re-identify a person within already detected and pre-cropped images of people, is not sufficient to implement practical security applications, where the inputs to the system are the full frames of the video streams. To support this claim, we introduce the Full Frame Person Re-ID setting (FF-PRID) and define specific metrics to evaluate FF-PRID implementations. To improve robustness, we also formalize the hybrid human-machine collaboration framework, which is inherent to any Re-ID security applications. To demonstrate the importance of considering the FF-PRID setting, we build an experiment showing that combining a good people detection network with a good Re-ID model does not necessarily produce good results for the final application. This underlines a failure of the current formulation in assessing the quality of a Re-ID model and justifies the use of different metrics. We hope that this work will motivate the research community to consider the full problem in order to develop algorithms that are better suited to real-world scenarios.","PeriodicalId":110864,"journal":{"name":"Anais Estendidos da XXXIV Conference on Graphics, Patterns and Images (SIBRAPI Estendido 2021)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133558248","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

Detecção de Fissuras Utilizando Redes Neurais Convolucionais 利用卷积神经网络进行裂缝检测

Anais Estendidos da XXXIV Conference on Graphics, Patterns and Images (SIBRAPI Estendido 2021) Pub Date : 2021-10-18 DOI: 10.5753/sibgrapi.est.2021.20041

R. P. C. D. Oliveira, C. Mauricio, V. N. D. Santos, F. F. F. Peres

引用次数: 0

1
2

下一页尾页

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

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