Automatic visual detection of human behavior: a review from 2000 to 2014

Due to advances in information technology (e.g., digital video cameras, ubiquitous sensors), the automatic detection of human behaviors from video is a very recent research topic. In this paper, we perform a systematic and recent literature review on this topic, from 2000 to 2014, covering a selection of 193 papers that were searched from six major scientific publishers. The selected papers were classified into three main subjects: detection techniques, datasets and applications. The detection techniques were divided into four categories (initialization, tracking, pose estimation and recognition). The list of datasets includes eight examples (e.g., Hollywood action). Finally, several application areas were identified, including human detection, abnormal activity detection, action recognition, player modeling and pedestrian detection. Our analysis provides a road map to guide future research for designing automatic visual human behavior detection systems.

An integrated system for human action recognition from video using hidden Markov model

In this paper, we present an integrated system for real-time automatic detection of human actions from video. The proposed approach uses the boundary of humans as the main feature for recognizing actions. Background subtraction is performed using Gaussian mixture model. Then, features are extracted from silhouettes and Vector Quantization is used to map features into symbols (bag of words approach). Finally, actions are detected using the Hidden Markov Model. The proposed system was validated using a newly collected real- world dataset. The obtained results show that the system is capable of achieving robust human detection, in both indoor and outdoor environments. Moreover, promising classification results were achieved when detecting two basic human actions: walking and sitting.

In vitro chondrogenic commitment of human Wharton's jelly stem cells by co-culture with human articular chondrocytes.

Wharton's jelly stem cells (WJSCs) are a potential source of transplantable stem cells in cartilage-regenerative strategies, due to their highly proliferative and multilineage differentiation capacity. We hypothesized that a non-direct co-culture system with human articular chondrocytes (hACs) could enhance the potential chondrogenic phenotype of hWJSCs during the expansion phase compared to those expanded in monoculture conditions. Primary hWJSCs were cultured in the bottom of a multiwell plate separated by a porous transwell membrane insert seeded with hACs. No statistically significant differences in hWJSCs duplication number were observed under either of the culture conditions during the expansion phase. hWJSCs under co-culture conditions show upregulations of collagen type I and II, COMP, TGFβ1 and aggrecan, as well as of the main cartilage transcription factor, SOX9, when compared to those cultured in the absence of chondrocytes. Chondrogenic differentiation of hWJSCs, previously expanded in co-culture and monoculture conditions, was evaluated for each cellular passage using the micromass culture model. Cells expanded in co-culture showed higher accumulation of glycosaminoglycans (GAGs) compared to cells in monoculture, and immunohistochemistry for localization of collagen type I revealed a strong detection signal when hWJSCs were expanded under monoculture conditions. In contrast, type II collagen was detected when cells were expanded under co-culture conditions, where numerous round-shaped cell clusters were observed. Using a micromass differentiation model, hWJSCs, previously exposed to soluble factors secreted by hACs, were able to express higher levels of chondrogenic genes with deposition of cartilage extracellular matrix components, suggesting their use as an alternative cell source for treating degenerated cartilage.

Hand gesture recognition for human computer interaction : a comparative study of different image features

Hand gesture recognition for human computer interaction, being a natural way of human computer interaction, is an area of active research in computer vision and machine learning. This is an area with many different possible applications, giving users a simpler and more natural way to communicate with robots/systems interfaces, without the need for extra devices. So, the primary goal of gesture recognition research is to create systems, which can identify specific human gestures and use them to convey information or for device control. For that, vision-based hand gesture interfaces require fast and extremely robust hand detection, and gesture recognition in real time. In this study we try to identify hand features that, isolated, respond better in various situations in human-computer interaction. The extracted features are used to train a set of classifiers with the help of RapidMiner in order to find the best learner. A dataset with our own gesture vocabulary consisted of 10 gestures, recorded from 20 users was created for later processing. Experimental results show that the radial signature and the centroid distance are the features that when used separately obtain better results, with an accuracy of 91% and 90,1% respectively obtained with a Neural Network classifier. These to methods have also the advantage of being simple in terms of computational complexity, which make them good candidates for real-time hand gesture recognition.

Human papillomavirus (HPV) screening and cervical cancer burden. A Brazilian perspective

This review tackles the issues related to disease burden caused by cervical cancer (CC) and its precursor (CIN) lesions in Brazil. A special focus is given to new technologies with potential to interfere with the development of CC by reducing the high-risk human papillomavirus (hr-HPV)-induced lesions that remain a major public health burden in all developing countries where organized screening programs do not exist. Globally, 85 % of all incident CC and 50 % of CC deaths occur in the developing countries. Unfortunately, most regions of Brazil still demonstrate high mortality rates, ranking CC as the second most common cancer among Brazilian women. Recently, CC screening programs have been tailored in the country to enable early detection of CC precursor lesions and thereby reduce cancer mortality. A combination of HPV testing with liquid-based cytology (LBC) seems to be a promising new approach in CC screening, with high expectation to offer an adequate control of CC burden in this country.

Forecasting human entrances at a commercial store using facial recognition data

Dissertação de mestrado integrado em Engenharia e Gestão de Sistemas de Informação

Hand gesture recognition system based in computer vision and machine learning: Applications on human-machine interaction

Tese de Doutoramento em Engenharia de Eletrónica e de Computadores

Development of a novel aptamer-based multi-sensor device for the detection of osteopontin

Doctoral Dissertation for PhD degree in Chemical and Biological Engineering