Automated Agronomy: Evaluation of Fruits Ripeness Using Machine Learning Approach
Lecture Notes in Networks and Systems
First page number:
Last page number:
© 2021, Springer Nature Switzerland AG. Fruit orchards require a lot of tasks, monitoring the current state of fruits and anticipated time of harvest. Precise estimation of harvest time is a key knowledge for the supply chain and timely delivery to grocery stores. The current process relies on human agronomists, who visit orchards often and do the visual evaluation of number of fruits, their ripeness and expected time of harvest. In this paper, we propose a preliminary work for automation of the fruits’ evaluation process, using machine learning algorithms to evaluate pictures of the trees. For our current system we have used pictures – one picture per tree, to constitute the base for evaluation of each tree using multiple pictures and video captured by drones. In this paper, Convolutional Neural Network (CNN) is used for fruit image classification based on ripeness stage of the fruits. Fruits classification was based on appropriate surface color and shape features and CNN was used to extract these features for classification. The model showed 96.43% accuracy. The ultimate goal of this work is to fully automate the process of orchard trees evaluation, including estimation of number of fruits on the tree (including non-visible ones), their ripeness and time of harvest to address the commercial market delivery planning requirements.
Agronomy; Drones; Machine learning; UAV
Computer Engineering | Electrical and Computer Engineering
Automated Agronomy: Evaluation of Fruits Ripeness Using Machine Learning Approach.
Lecture Notes in Networks and Systems, 182