This work presents a machine vision system for the localization of strawberries and environment perception in a strawberry-harvesting robot for use in table-top strawberry production. A deep convolutional neural network for segmentation is utilized to detect the strawberries. Segmented strawberries are localized through coordinate transformation, density base point clustering and the proposed location approximation method. To avoid collisions between the gripper and fixed obstacles, the safe manipulation region is limited to the space in front of the table and underneath the strap. Therefore, a safe region classification algorithm, based on Hough Transform algorithm, is proposed to segment the strap masks into a belt region in order to identify the pickable strawberries located underneath the strap. Similarly, a safe region classification algorithm is proposed for the table, to calculate its points in 3D and fit the points onto a 3D plane based on the 3D point cloud, so that pickable strawberries in front of the table can be identified. Experimental tests showed that the algorithm could accurately classify ripe and unripe strawberries and could identify whether the strawberries are within the safe region for harvesting. Furthermore, harvester robot's optimized localization method could accurately locate the strawberry targets with a picking accuracy rate of 74.1% in modified situations. INDEX TERMS Robotics and automation, strawberry harvester, machine vision, environment perception.

No abstract

No abstract

No abstract

A dengue e uma doença endêmica que ocorre principalmente em áreas tropicais, devido à sua transmissão através de mosquitos. Usando mecanismos de pré-processamento e de aprendizado de máquina, esse trabalho objetiva desenvolver um modelo de previsão que estabeleça uma relação existente entre as condicões de uma cidade e a proliferação de epidemia de dengue, como parte da competição 'DengAI - predicting disease spread', fornecida pela plataforma DrivenData. Dentre os modelos implementados, o metodo Ensemble entre o Random Forest e Redes Neurais obtiveram a melhor performance, com melhora de 4,5% em relação ao Benchmark.