Agricultural applications such as yield prediction, precision agriculture and automated harvesting need systems able to infer the cultural state from low-cost sensing devices. Proximal sensing using affordable cameras combined with computer vision have seen a promising alternative, strengthened after the advent of convolutional neural networks (CNNs) as an alternative for challenging pattern recognition problems in natural images. Considering fruit growing monitoring and automation, a fundamental problem is the detection, segmentation and counting of individual fruits in orchards. Here we show that for wine grapes, a crop presenting large variability in shape, color, size and compactness, grape clusters can be successfully detected, segmented and tracked using state-of-theart CNNs. In a dataset containing 408 grape clusters from images taken on field, we have reached a F 1 -score up to 0.91 for instance segmentation, a fine separation of each cluster from other structures in the image that allows a more accurate assessment of fruit size and shape. We have also shown as clusters can be identified and tracked along video sequences recording orchard rows. We also present a public dataset containing grape clusters properly annotated in 300 images and a novel annotation methodology for segmentation of complex objects in natural images. The presented pipeline for annotation, training, evaluation and tracking of agricultural patterns in images can be replicated for different crops and production systems. It can be employed in the development of sensing components for several agricultural and environmental applications.

Unmanned aerial vehicles (UAVs) are being increasingly viewed as valuable tools to aid the management of farms. This kind of technology can be particularly useful in the context of extensive cattle farming, as production areas tend to be expansive and animals tend to be more loosely monitored. With the advent of deep learning, and convolutional neural networks (CNNs) in particular, extracting relevant information from aerial images has become more effective. Despite the technological advancements in drone, imaging and machine learning technologies, the application of UAVs for cattle monitoring is far from being thoroughly studied, with many research gaps still remaining. In this context, the objectives of this study were threefold: (1) to determine the highest possible accuracy that could be achieved in the detection of animals of the Canchim breed, which is visually similar to the Nelore breed (Bos taurus indicus); (2) to determine the ideal ground sample distance (GSD) for animal detection; (3) to determine the most accurate CNN architecture for this specific problem. The experiments involved 1853 images containing 8629 samples of animals, and 15 different CNN architectures were tested. A total of 900 models were trained (15 CNN architectures × 3 spacial resolutions × 2 datasets × 10-fold cross validation), allowing for a deep analysis of the several aspects that impact the detection of cattle using aerial images captured using UAVs. Results revealed that many CNN architectures are robust enough to reliably detect animals in aerial images even under far from ideal conditions, indicating the viability of using UAVs for cattle monitoring.

No abstract

No abstract

Resumo Este estudo verificou a efetividade da promoção de atividade física realizada por agentes comunitários de saúde (ACS) em visitas domiciliares. Trata-se de um ensaio controlado não randomizado com duração de seis meses, com um grupo de ACS que passou por um processo educativo para promover atividade física nas visitas domiciliares para intervir em usuários do Sistema Único de Saúde (SUS) e um grupo controle. Foram avaliados a prática de atividade física e os estágios de mudança de comportamento em 176 adultos (n = 90 do grupo intervenção e n = 86 do grupo controle) atendidos pelos ACS. Foram realizadas análises de associação, razões de prevalência e equações de estimativas generalizadas para verificar diferenças entre os grupos. Não foram observadas evidências de diferenças nos níveis de atividade física e nos estágios de mudança de comportamento entre os usuários dos dois grupos. Os ACS do grupo intervenção realizaram mais visitas domiciliares para promover atividade física aos idosos, pessoas com baixa escolaridade, que não trabalhavam e que tinham doenças crônicas. É importante que os modos de trabalho e prioridades dos ACS sejam repensados para ampliar a promoção da atividade física no SUS.