Abstract
Wine is the most important product from the Douro Region, in Portugal. Ampelographs are disappearing, and farmers need new solutions to identify grapevine varieties to ensure high-quality standards. The development of methodology capable of automatically identify grapevine are in need. In the scenario, deep learning based methods are emerging as the state-of-art in grapevines classification tasks. In previous work, we verify the deep learning models would benefit from focus classification patches in leaves images areas. Deep learning segmentation methods can be used to find grapevine leaves areas. This paper presents a methodology to segment grapevines images automatically based on the U-net model. A private dataset was used, composed of 733 grapevines images frames extracted from 236 videos collected in a natural environment. The trained model obtained a Dice of 95.6% and an Intersection over Union of 91.6%, results that fully satisfy the need of localise grapevine leaves.

Abstract

Abstract

Abstract

Abstract

Abstract
Previous works have shown the great potential of Virtual Reality (VR) in the area of Education. This paper studies if users can learn a second language when using a gamified VR application through an English learning test and how learning influences user satisfaction, sense of presence, cybersickness, and quality of experience through questionnaires. For this purpose, the VirtualeaRn game was developed. 20 Portuguese participants were exposed to the application, and the learning test was used before and after using the application. Result analysis shows an increase in learning results after using the VR gamified application, indicating the technology's efficacy in learning a second language. A positive user satisfaction, sense of presence, and quality of experience were also found. Some cases of cybersickness were reported. The outcomes are promising and provide enough information to show the potential of the gamification of VR technology for the area of learning a second language.