Early Identification and Localization Algorithm for Weak Seedlings Based on Phenotype Detection and Machine Learning

• Published in: Agriculture (Basel) Vol. 13; no. 1; p. 212
• Main Authors: Xu, Shengyong, Zhang, Yi, Dong, Wanjing, Bie, Zhilong, Peng, Chengli, Huang, Yuan
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.01.2023
• Subjects: Accuracy; Agricultural production; agriculture; Algorithms; Cameras; Classification; Culling; Data collection; Decision trees; Factories; Genotype & phenotype; Germination; grow prediction; Growth models; image analysis; Image processing; Image segmentation; Leaf area; Learning algorithms; Leaves; Localization; Machine learning; Morphology; Neural networks; Nurseries; phenotype; phenotype measurement; Phenotypes; Physiology; Plant growth; plant height; Plants; prediction; Recurrent neural networks; Replenishment; Seedlings; Seeds; strong seedling model; Technical services; Vision systems; Water melons; watermelons; China
• ISSN: 2077-0472; 2077-0472
• DOI: 10.3390/agriculture13010212

It is important to propose the correct decision for culling and replenishing seedlings in factory seedling nurseries to improve the quality of seedlings and save resources. To solve the problems of inefficiency and subjectivity of the existing traditional manual culling and replenishment of seeds, this paper proposes an automatic method to discriminate the early growth condition of seedlings. Taking watermelon plug seedlings as an example, Azure Kinect was used to collect data of its top view three times a day, at 9:00, 14:00, and 19:00. The data were collected from the time of germination to the time of main leaf growth, and the seedlings were manually determined to be strong or weak on the last day of collection. Pre-processing, image segmentation, and point cloud processing methods were performed on the collected data to obtain the plant height and leaf area of each seedling. The plant height and leaf area on the sixth day were predicted using an LSTM recurrent neural network for the first three days. The R squared for plant height and leaf area prediction were 0.932 and 0.901, respectively. The dichotomous classification of normal and abnormal seedlings was performed using six machine learning classification methods, such as random forest, SVM, and XGBoost, for day six data. The experimental results proved that random forest had the highest classification accuracy of 84%. Finally, the appropriate culling and replenishment decisions are given based on the classification results. This method can provide some technical support and a theoretical basis for factory seedling nurseries and transplanting robots.