Smart Autonomous Gardening Rover with Plant Recognition Using Neural Networks

Abstract

Modernization of our environment (pruning trees for constructing tall buildings) results in climatic changes and ecological imbalance. To mitigate the effect, gardening (to plant trees and shrubs) becomes more and more important than just a hobby. Besides, maintenance of a garden is a tedious process and also time-consuming. Often the gardener lacks in knowledge about the requirements of plant (nutrient and the amount of water to be sprayed) to enhance its growth. In this regard, it is necessary to build an autonomous gardening robotic vehicle which automatically identifies and classifies the plant species using feature extraction algorithms (Scale Invariant Feature Transform (SIFT), Speeded-Up Robust Features (SURF), Oriented FAST and Rotated BRIEF (ORB)) and neural networks, respectively. It also measures the key parameters for gardening such as temperature, humidity, heat level, wind speed, wind direction and soil moisture. The data acquired from the on-board sensors of the gardening rover are sent to the cloud storage platform on a regular basis. Based on the acquired data and history, future predictions are made to maintain the garden more effectively and efficiently. A website and an android application are developed for monitoring and controlling the rover from a remote area. This system is a combination of new technologies involving an interdisciplinary approach to carry out precision gardening using Internet of Things (IoT).