S18 - Session O1 - Detection of ripening stage of tomato by means of 3D fruit point cloud

Authors: Kowshik Kumar Saha *, Nikos Tsoulias, Manuela Zude-Sasse

Ripening process of tomatoes ( Solanum lycopersicum ) captures physiochemical processes resulting in visually appearing change in colour. In this study, a new technique is proposed utilizing 3D point cloud-based intensity analysis obtained by light detection and ranging (LiDAR) laser scanner to determine the ripening stage of tomato. Tomato fruit (n = 100) of six ripening stages (mature green, breaker, turning, pink, light red, and red) according to USDA standard, were analysed using a linear conveyor mounted LiDAR scanner system in the laboratory. Each fruit was scanned from 1 m distance with the LiDAR system emitting at 650 nm band. Fruit point clouds were pre-processed including calibration of intensity values using standard black and white colour coated boards. Geometric correction for calibrated intensity was performed to correct for the curvature according to the shape of each tomato. Histogram of pre-processed data were used for building intensity classes related to the colour of the fruit. To test the performance of the proposed method, cross validation was performed. The results showed that the average accuracy of detection of six ripening stages of tomato samples achieved 85 %.