Instance Segmentation in Mobile Computing Environments for Identification of Specific Characteristics in Endangered Species

The segmentation of instances is a key topic in image processing and computer vision. There are numerous applications such as medical image analysis, video surveillance, image compression among others, in which its algorithms show significant results. Due to the COVID-19 pandemic, most countries have been affected mainly by their economy. In the food production sector, including fishing and aquaculture, it was no different. In this context, this research has as main objective to contribute to the 2030 Agenda for Sustainable Development suggested by the United Nations (UN), through a fish detection and segmentation model based on the framework Detectron2, optimizing the time of professionals in identifying specific characteristics of a particular species. To achieve this objective, this research seeks to facilitate the recognition of patterns of parts of the fish from the segmentation of instances and to stimulate scientific research in the area through the morphological information collection of certain species. The results present an accuracy, based on the Intersection over Union (IoU) indicator, of 88.4%, providing an effective solution for the collection of these characteristics.