RESUMO
Action recognition plays an important role in various applications such as video monitoring, automatic video indexing, crowd analysis, human-machine interaction, smart homes and personal assistive robotics. In this paper, we propose improvements to some methods for human action recognition from videos that work with data represented in the form of skeleton poses. These methods are based on the most widely used techniques for this problem-Graph Convolutional Networks (GCNs), Temporal Convolutional Networks (TCNs) and Recurrent Neural Networks (RNNs). Initially, the paper explores and compares different ways to extract the most relevant spatial and temporal characteristics for a sequence of frames describing an action. Based on this comparative analysis, we show how a TCN type unit can be extended to work even on the characteristics extracted from the spatial domain. To validate our approach, we test it against a benchmark often used for human action recognition problems and we show that our solution obtains comparable results to the state-of-the-art, but with a significant increase in the inference speed.
RESUMO
Robust action recognition methods lie at the cornerstone of Ambient Assisted Living (AAL) systems employing optical devices. Using 3D skeleton joints extracted from depth images taken with time-of-flight (ToF) cameras has been a popular solution for accomplishing these tasks. Though seemingly scarce in terms of information availability compared to its RGB or depth image counterparts, the skeletal representation has proven to be effective in the task of action recognition. This paper explores different interpretations of both the spatial and the temporal dimensions of a sequence of frames describing an action. We show that rather intuitive approaches, often borrowed from other computer vision tasks, can improve accuracy. We report results based on these modifications and propose an architecture that uses temporal convolutions with results comparable to the state of the art.
Assuntos
Osso e Ossos/anatomia & histologia , Imageamento Tridimensional , Articulações/anatomia & histologia , Movimento , Reconhecimento Automatizado de Padrão , Algoritmos , Bases de Dados como Assunto , Humanos , Redes Neurais de Computação , Fatores de TempoRESUMO
Mycobacteria identification is crucial to diagnose tuberculosis. Since the bacillus is very small, finding it in Ziehl-Neelsen (ZN)-stained slides is a long task requiring significant pathologist's effort. We developed an automated (AI-based) method of identification of mycobacteria. We prepared a training dataset of over 260,000 positive and over 700,000,000 negative patches annotated on scans of 510 whole slide images (WSI) of ZN-stained slides (110 positive and 400 negative). Several image augmentation techniques coupled with different custom computer vision architectures were used. WSIs automatic analysis was followed by a report indicating areas more likely to present mycobacteria. Our model performs AI-based diagnosis (the final decision of the diagnosis of WSI belongs to the pathologist). The results were validated internally on a dataset of 286,000 patches and tested in pathology laboratory settings on 60 ZN slides (23 positive and 37 negative). We compared the pathologists' results obtained by separately evaluating slides and WSIs with the results given by a pathologist aided by automatic analysis of WSIs. Our architecture showed 0.977 area under the receiver operating characteristic curve. The clinical test presented 98.33% accuracy, 95.65% sensitivity, and 100% specificity for the AI-assisted method, outperforming any other AI-based proposed methods for AFB detection.