Abstract The demand for soybean tends to increase worldwide with population growth. Despite farmers adopting strategies such as crop rotation, soil preparation, and the application of chemical products, the most critical factor to increase productivity is choosing cultivars adapted to the region so that they are resistant to deceases. In addition, seed quality also directly influences crop productivity. To help a farmer select suitable cultivars and analyze the quality of soybean seeds, we present an application that uses the user’s location to identify suitable cultivars based on the edaphoclimatic characteristics of a region. The details of these cultivars are shown in text, images, and video, making it possible to compare the selected varieties. Our app also contains a trained convolution neural network capable of classifying the quality of soybean seeds based on an image captured by the user or stored on a smartphone. The convolutional neural network architecture allowed an excellent performance, with an accuracy of 94.06% in the classification of soybean seeds. All app functionality runs comfortably on mobile devices. Compared to others that have the same purpose, our application has a more significant number of features.

Assessment of video segmentation quality is a problem seldom investigated by the scientific community. Nevertheless, recent studies presented some objective metrics to evaluate algorithms. Such metrics consider different ways in which segmentation errors occur (perceptual factors) and its parameters are adjusted according to the application for which the segmented frames are intended. We demonstrate empirically that the performance of existing metrics changes according to the segmentation algorithm; we applied such metrics to evaluate bilayer segmentation algorithms for compose scenes in Augmented Reality environments. We also contribute with a new objective metric to adjust the parameters of two bilayer segmentation algorithms found in the literature.

Augmented Reality (AR) systems which use optical tracking with fiducial marker for registration have had an important role in popularizing this technology, since only a personal computer with a conventional webcam is required. However, in most these applications, the virtual elements are shown only in the foreground a real element does not occlude a virtual one. The method presented enables AR environments based on fiducial markers to support mutual occlusion between a real element and many virtual ones, according to the elements position (depth) in the environment.