01630nam a2200265 a 450000100080000000500110000800800410001902000220006002200140008210000180009624501210011426001030023530000120033850000610035052007630041165000110117465000200118565000110120565300350121665300340125165300260128565300200131165300180133170000150134921366672023-12-13       2021    bl uuuu     u00u1 u    #d  a978-65-00-34526-1  a2177-97241 aSANTOS, T. T.  aA methodology for detection and localization of fruits in apples orchards from aerial images.h[electronic resource]  aIn: CONGRESSO BRASILEIRO DE AGROINFORMÁTICA, 13., 2021, Bagé. Anais [...]. Bagé: Unipampac2021  ap. 1-9.  aOrganizado por Ana Paula Lüdtke Ferreira. SBIAgro 2021.  aAbstract. Computer vision methods based on convolutional neural networks (CNNs) have presented promising results on image-based fruit detection at ground-level for different crops. However, the integration of the detections found in different images, allowing accurate fruit counting and yield prediction, have received less attention. This work presents a methodology for automated fruit counting employing aerial-images. It includes algorithms based on multiple view geometry to perform fruits tracking, not just avoiding double counting but also locating the fruits in the 3-D space. Preliminary assessments show correlations above 0.8 between fruit counting and true yield for apples. The annotated dataset employed on CNN training is publicly available.  aApples  aNeural networks  aMaçã  aContagem automática de frutas  aConvolutional neural networks  aDetecção de maçãs  aFruit detection  aRedes neurais1 aGEBLER, L.