Inside Out: Transforming Images of Lab-Grown Plants for Machine Learning Applications in Agriculture

Abstract

Machine learning tasks often require a significant amount of training data for the resultant network to perform suitably for a given problem in any domain. In agriculture, dataset sizes are further limited by phenotypical differences between two plants of the same genotype, often as a result of differing growing conditions. Synthetically-augmented datasets have shown promise in improving existing models when real data is not available. In this paper, we employ a contrastive unpaired translation (CUT) generative adversarial network (GAN) and simple image processing techniques to translate indoor plant images to appear as field images. While we train our network to translate an image containing only a single plant, we show that our method is easily extendable to produce multiple-plant field images. Furthermore, we use our synthetic multiplant images to train several YoloV5 nano object detection models to perform the task of plant detection and measure the accuracy of the model on real field data images. Including training data generated by the CUT-GAN leads to better plant detection performance compared to a network trained solely on real data.

WG-YOLOv5: improved YOLOv5 based on wavelet transform and GSConv for real-time wildfire detection

“…In this paper, Precision, Recall, Mean Average Precision (mAP), Number of Parameters, GFLOPS (Giga Floating Point Operations Per Second), and Inference Speed (FPS) are used to evaluate the model's performance [16].…”

Field Plant Identification Through Indoor Imagery Using Image Augmentation and Object Detection Algorithms

“…The blue background can be removed in this space by setting a threshold, which results in keyed-out plants. Figure 4.4 shows picture of a single indoor canola and its corresponding mask that can be used to remove the blue background [61].…”