01905naa a2200385 a 450000100080000000500110000800800410001902200140006002400540007410000180012824501710014626000090031752006040032665300240093065300250095465300240097965300260100365300180102965300260104765300240107365300410109765300290113865300260116765300270119365300280122065300390124865300330128765300260132070000230134670000210136970000210139070000190141170000150143077300740144521658892024-07-22       2024    bl uuuu     u00u1 u    #d  a0168-16997 ahttps://doi.org/10.1016/j.compag.2024.1091992DOI1 aSANTOS, T. T.  aMultiple orange detection and tracking with 3-D fruit relocalization and neural-net based yield regression in commercial sweet orange orchards.h[electronic resource]  c2024  aHere, we propose a non-invasive alternative that utilizes fruit counting from videos, implemented as a pipeline. Firstly, we employ convolutional neural networks for the detection of visible fruits. Inter-frame association techniques are then applied to track the fruits across frames. To handle occluded and re-appeared fruit, we introduce a relocalization component that employs 3-D estimation of fruit locations. Finally, a neural network regressor is utilized to estimate the total number of fruits, integrating image-based fruit counting with other tree data such as crop variety and tree size.  aAgricultura digital  aAprendizado profundo  aContagem de laranja  aCrop yield estimation  aDeep learning  aDetecção de laranja  aDigital agriculture  aEstimativa do rendimento da colheita  aMultiple-object tracking  aOrange fruit counting  aOrange fruit detection  aPomares de laranja doce  aRastreamento de múltiplos objetos  aRealocação de frutas em 3D  aSweet orange orchards1 aSOUZA, K. X. S. de1 aCAMARGO NETO, J.1 aKOENIGKAN, L. V.1 aMOREIRA, A. S.1 aTERNES, S.  tComputers and Electronics in Agriculturegv. 224, 109199, Sept. 2024.