AUTHOR=Meng Yao , Xu Mingle , Yoon Sook , Jeong Yongchae , Park Dong Sun 

TITLE=Flexible and high quality plant growth prediction with limited data

JOURNAL=Frontiers in Plant Science

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2022.989304

DOI=10.3389/fpls.2022.989304

ISSN=1664-462X

ABSTRACT=Predicting plant growth is a fundamental challenge that can be employed to analyze plants and further make decisions to have healthy plants with high yields. Deep learning has recently been showing its potential to address this challenge in recent years, however, there are still two issues. First, image-based plant growth prediction is currently taken as either from time-series or image generation viewpoints, resulting in either unclear images or inflexible framework. Second, deep learning-based algorithms are notorious to require a large-scale dataset to obtain a competing performance but collecting enough data is time-consuming and expensive. To address the issues, we consider the plant growth prediction from both viewpoints with two new time-series data augmentation algorithms. To be more specific, we raise a new framework with a length-changeable time-series processing unit to generate images in a flexible way. To obtain high-quality images, generative adversarial loss is utilized to optimize our framework. Furthermore, we first recognize three key points to perform time-series data augmentation and then put forward T-Mixup and T-Copy-Paste. T-Mixup fuses images from different time in pixel-wise while T-Copy-Paste makes new time-series images with a different background by reusing individual leaf extracted from existing dataset. We perform our method in a public dataset and achieve decent results, such as the generated RGB images and instance masks securing PSNR 27.58 and 27.61, respectively.