In-field mango fruit sizing is useful for estimation of fruit maturation and size distribution,\ninforming the decision to harvest, harvest resourcing (e.g., tray insert sizes), and marketing. In-field\nmachine vision imaging has been used for fruit count, but assessment of fruit size from images\nalso requires estimation of camera-to-fruit distance. Low cost examples of three technologies for\nassessment of camera to fruit distance were assessed: a RGB-D (depth) camera, a stereo vision camera\nand a Time of Flight (ToF) laser rangefinder. The RGB-D camera was recommended on cost and\nperformance, although it functioned poorly in direct sunlight. The RGB-D camera was calibrated,\nand depth information matched to the RGB image. To detect fruit, a cascade detection with histogram\nof oriented gradients (HOG) feature was used, then Otsu�s method, followed by color thresholding\nwas applied in the CIE L*a*b* color space to remove background objects (leaves, branches etc.).\nA one-dimensional (1D) filter was developed to remove the fruit pedicles, and an ellipse fitting\nmethod employed to identify well-separated fruit. Finally, fruit lineal dimensions were calculated\nusing the RGB-D depth information, fruit image size and the thin lens formula. A Root Mean Square\nError (RMSE) = 4.9 and 4.3 mm was achieved for estimated fruit length and width, respectively,\nrelative to manual measurement, for which repeated human measures were characterized by a\nstandard deviation of 1.2 mm. In conclusion, the RGB-D method for rapid in-field mango fruit size\nestimation is practical in terms of cost and ease of use, but cannot be used in direct intense sunshine.\nWe believe this work represents the first practical implementation of machine vision fruit sizing in\nfield, with practicality gauged in terms of cost and simplicity of operation.
Loading....