Currently, many companies or even cities use surveillance cameras all the time, and due to the COVID-19 pandemic, many places have to limit the number of people in attendance. This paper proposes a method for people counting by gender and age in videos using deep learning techniques. The proposed method is based on a face detection and tracking approach combined with an alignment process to minimize the negative effect of the background information, considering occlusions and avoiding duplicate counting. Then, specialized Deep Neural Networks based on the EfficientNet architecture are employed for age and gender classification. Experimental results show that our method achieves satisfactory performance on people counting by age and gender, demonstrating the effectiveness of the present method.
Soft biometrics traits extracted from a human body, including the type of clothes, hair color, and accessories, are useful information used for people tracking and identification. Semantic segmentation of these traits from images is still a challenge for researchers because of the huge variety of clothing styles, layering, shapes, and colors. To tackle these issues, we proposed EPYNET, a framework for clothing segmentation. EPYNET is based on the Single Shot MultiBox Detector (SSD) and the Feature Pyramid Network (FPN) with the EfficientNet model as the backbone. The framework also integrates data augmentation methods and noise reduction techniques to increase the accuracy of the segmentation. We also propose a new dataset named UTFPR-SBD3, consisting of 4,500 manually annotated images into 18 classes of objects, plus the background. Unlike available public datasets with imbalanced class distributions, the UTFPR-SBD3 has, at least, 100 instances per class to minimize the training difficulty of deep learning models. We introduced a new measure of dataset imbalance, motivated by the difficulty in comparing different datasets for clothing segmentation. With such a measure, it is possible to detect the influence of the background, classes with small items, or classes with a too high or too low number of instances. Experimental results on UTFPR-SBD3 show the effectiveness of EPYNET, outperforming the state-of-art methods for clothing segmentation on public datasets. Based on these results, we believe that the proposed approach can be potentially useful for many real-world applications related to soft biometrics, people surveillance, image description, clothes recommendation, and others.
Automatically understanding and describing the visual content of videos in natural language is a challenging task in computer vision. Existing approaches are often designed to describe single events in a closed-set setting. However, in real-world scenarios, concurrent activities and previously unseen actions may appear in a video. This work presents the OSVidCap, a novel open-set video captioning framework that recognizes and describes, in natural language, concurrent known actions and deal with unknown ones. The OSVidCap is based on the encoder-decoder framework and uses a detection-andtracking-object-based mechanism followed by a background blurring method to focus on specific targets in a video. Additionally, we employ the TI3D Network with the Extreme Value Machine (EVM), which learns representations and recognizes unknown actions. We evaluate the proposed approach on the benchmark ActivityNet Captions dataset. Also, an enhanced version of the LIRIS human activity dataset was proposed by providing descriptions for each action. We also provide spatial, temporal, and caption annotations for existing unlabeled actions in the dataset -considered unknown actions in our experiments. Experimental results showed our method's effectiveness in recognizing and describing concurrent actions in natural language and the strong ability to deal with detected unknown activities. Based on these results, we believe that the proposed approach can be potentially helpful for many real-world applications, including human behavior analysis, safety monitoring, and surveillance.
This work presents an information retrieval architecture developed for the Santa Catarina State Telemedicine System. This architecture employs DICOM Structured Reporting, controlled vocabularies for data catalogization and a specially developed search engine for data indexing and storing. Results of our case study show that searches can be performed much faster with the proposed search mechanism and that the precision of results is acceptable in most cases. In some searches, irrelevant items within the 15 first results were identified. This occurred partially because search terms found in the additional free text observations inserted into the findings reports were treated with the same relevance as formally diagnostically relevant items of the DICOM SR structure and, partially because the semantics of negations associated to search terms in the findings reports were not taken into consideration.
Large-scale telemedicine systems provide extensive amounts of data that can be used to gather epidemiological information. Epidemiologists have been using GIS systems for the easy and quick visualization of data and to perform georeferenced epidemiological analysis. This paper presents GISTelemed, a georeferenced epidemiological analysis tool developed as part of the Santa Catarina State Integrated Telemedicine and Telehealth System (STT/SC), a statewide telemedicine infrastructure in Brazil. The GISTelemed module offers an architecture supporting real-time recovery, information visualization and epidemiological analysis from structured and semi-structured data. The architecture uses controlled vocabularies for data catalogization and a specially developed ETL process that allows sending and receiving data on a large number of protocols, including DICOM SR and SQL. We performed a case study with users that indicates good perceived ease of use and usefulness of GISTelemed by both medical staff and health care managers.
Fundamento: A síndrome de Brugada é um distúrbio arritmogênico hereditário caracterizado pela presença de características eletrocardiográficas específicas com ou sem sintomas. Os pacientes apresentam risco aumentado de morte súbita por fibrilação ventricular. A prevalência desse padrão eletrocardiográfico difere de acordo com a região estudada. Porém, informações epidemiológicas, incluindo a população brasileira, são escassas. Objetivo: Avaliar a prevalência do padrão eletrocardiográfico da síndrome de Brugada e o perfil epidemiológico associado a ela. Métodos: Estudo transversal que incluiu 846.533 registros ECG de 716.973 pacientes do banco de dados de eletrocardiograma (ECG) da Rede de Telemedicina de Santa Catarina por um período de quatro anos. Todos os exames foram ECG de 12 derivações convencionais (sem V1 e V2 em posições altas). Os exames identificados com o diagnóstico de "Síndrome de Brugada" (tipos 1 e 2) foram revisados por um eletrofisiologista. Foram considerados significativos valores de p<0,05. Resultados: Apresentavam padrão potencialmente consistente com ECG do tipo Brugada 83 pacientes. Destes, 33 foram confirmados com padrão de Brugada tipo 1, e 22 com tipo 2, após reavaliação. A prevalência de ECG do tipo 1 de Brugada foi de 4,6 por 100.000 pacientes. O ECG do tipo Brugada 1 foi associado ao sexo masculino (81,8% vs. 41,5%, p<0,001) e menor prevalência de obesidade (9,1% vs. 26,4%, p=0,028).Conclusões: Este estudo mostrou baixa prevalência de ECG do tipo Brugada no sul do Brasil. A presença de ECG com padrão Brugada tipo 1 esteve associada ao sexo masculino e menor prevalência de obesidade que a população geral.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.