Superpixels and Graph Convolutional Neural Networks for Efficient Detection of Nutrient Deficiency Stress from Aerial Imagery

TL;DR

This paper introduces a lightweight graph-based approach using superpixels and Graph Convolutional Neural Networks for rapid detection of nutrient deficiency in agricultural fields from aerial imagery, reducing computational costs significantly.

Contribution

The paper presents a novel, efficient method combining superpixels and GCNs for nutrient deficiency detection, outperforming traditional pixel-based deep learning models in speed and parameter count.

Findings

Model trains in minutes, significantly faster than traditional methods.

Uses 4 orders of magnitude fewer parameters than CNNs.

Achieves effective detection of nutrient deficient areas.

Abstract

Advances in remote sensing technology have led to the capture of massive amounts of data. Increased image resolution, more frequent revisit times, and additional spectral channels have created an explosion in the amount of data that is available to provide analyses and intelligence across domains, including agriculture. However, the processing of this data comes with a cost in terms of computation time and money, both of which must be considered when the goal of an algorithm is to provide real-time intelligence to improve efficiencies. Specifically, we seek to identify nutrient deficient areas from remotely sensed data to alert farmers to regions that require attention; detection of nutrient deficient areas is a key task in precision agriculture as farmers must quickly respond to struggling areas to protect their harvests. Past methods have focused on pixel-level classification (i.e. semantic segmentation) of the field to achieve these tasks, often using deep learning models with tens-of-millions of parameters. In contrast, we propose a much lighter graph-based method to perform node-based classification. We first use Simple Linear Iterative Cluster (SLIC) to produce superpixels across the field. Then, to perform segmentation across the non-Euclidean domain of superpixels, we leverage a Graph Convolutional Neural Network (GCN). This model has 4-orders-of-magnitude fewer parameters than a CNN model and trains in a matter of minutes.