Seed Classification using Synthetic Image Datasets Generated from Low-Altitude UAV Imagery

TL;DR

This paper presents a novel approach for seed classification using synthetic datasets generated from low-altitude UAV imagery, employing domain randomization and ensemble CNN models to achieve high accuracy despite challenging imaging conditions.

Contribution

It introduces a method for creating synthetic training data from limited seed images and develops an ensemble CNN framework for improved seed classification accuracy.

Findings

Achieved 94.6% overall classification accuracy.

Synthetic datasets effectively train CNNs for seed classification.

Ensemble models outperform individual CNNs.

Abstract

Plant breeding programs extensively monitor the evolution of seed kernels for seed certification, wherein lies the need to appropriately label the seed kernels by type and quality. However, the breeding environments are large where the monitoring of seed kernels can be challenging due to the minuscule size of seed kernels. The use of unmanned aerial vehicles aids in seed monitoring and labeling since they can capture images at low altitudes whilst being able to access even the remotest areas in the environment. A key bottleneck in the labeling of seeds using UAV imagery is drone altitude i.e. the classification accuracy decreases as the altitude increases due to lower image detail. Convolutional neural networks are a great tool for multi-class image classification when there is a training dataset that closely represents the different scenarios that the network might encounter during evaluation. The article addresses the challenge of training data creation using Domain Randomization wherein synthetic image datasets are generated from a meager sample of seeds captured by the bottom camera of an autonomously driven Parrot AR Drone 2.0. Besides, the article proposes a seed classification framework as a proof-of-concept using the convolutional neural networks of Microsoft's ResNet-100, Oxford's VGG-16, and VGG-19. To enhance the classification accuracy of the framework, an ensemble model is developed resulting in an overall accuracy of 94.6%.