Dynamic Measurement of Portos Tomato Seedling Growth Using the Kinect 2.0 Sensor

Abstract

Traditionally farmers monitor their crops employing their senses and experience. However, the human sensory system is inconsistent due to stress, health, and age. In this paper, we propose an agronomic application for monitoring the growth of Portos tomato seedlings using Kinect 2.0 to build a more accurate, cost-effective, and portable system. The proposed methodology classifies the tomato seedlings into four categories: The first corresponds to the seedling with normal growth at the time of germination; the second corresponds to germination that occurred days after; the third category entails exceedingly late germination where its growth will be outside of the estimated harvest time; the fourth category corresponds to seedlings that did not germinate. Typically, an expert performs this classification by analyzing ten percent of the randomly selected seedlings. In this work, we studied different methods of segmentation and classification where the Gaussian Mixture Model (GMM) and Decision Tree Classifier (DTC) showed the best performance in segmenting and classifying Portos tomato seedlings.

How to make sense of 3D representations for plant phenotyping: a compendium of processing and analysis techniques

“…Using Kinect for acquiring a 3D point cloud data can be found in several studies including Wang et al [44] on lettuce, González et al [45] on tomato seedling, Zhang et al [46] on pumpkin roots, and Zhang et al [47] on maize plants.…”

“…Apple tree/orchard [110,341] Calathea makoyana [111] Cyclamen [40] Epipremnum aureum [111] Hedera nepalensis [111] Hydrangea [40] Lettuce [44] Maize (Corn) [13,38,47] Monstera deliciosa [111] Orchidaceae [40] Paprika [109] Pelargonium [40] Pepper [155] Pumpkin [46] Rapeseed [33] Rosebush [110] Sorghum [39] Soybean [43] Sugar beet [13,36] Sunflower [13] Tomato [45] Wheat [36] Yucca [110] ToF cameras use time between emitted light and reflected light from thousands of points to conduct 3D images.…”

Feature extraction of 3D Chinese rose model based on color and shape features

“… Bi (2022) successfully applied the shape distribution retrieval method to the analysis of the perspective distance-angle shape distribution of the garden landscape, which effectively improved the classification ability. Gonzalez-Barbosa ( Gonzalez-Barbosa et al., 2022 ) used Kinect 2.0 to collect 3D point clouds of tomato seedlings to obtain their morphological characteristics to monitor the growth of tomato seedlings. Jayakumari ( Jayakumari et al., 2021 ) designed the CropPointNet CNN model to segment crops semantically from a three-dimensional perspective, and applied high-resolution laser radar to classify cabbage, tomato, and eggplant based on objects.…”