Use of synthetic images for training a deep learning model for weed detection and biomass estimation in cotton.
Academic Article
Overview
Research
Identity
Additional Document Info
Other
View All
Overview
abstract
Site-specific treatment of weeds in agricultural landscapes has been gaining importance in recent years due to economic savings and minimal impact on the environment. Different detection methods have been developed and tested for precision weed management systems, but recent developments in neural networks have offered great prospects. However, a major limitation with the neural network models is the requirement of high volumes of data for training. The current study aims at exploring an alternative approach to the use of real images to address this issue. In this study, synthetic images were generated with various strategies using plant instances clipped from UAV-borne real images. In addition, the Generative Adversarial Networks (GAN) technique was used to generate fake plant instances which were used in generating synthetic images. These images were used to train a powerful convolutional neural network (CNN) known as "Mask R-CNN" for weed detection and segmentation in a transfer learning mode. The study was conducted on morningglories (MG) and grass weeds (Grass) infested in cotton. The biomass for individual weeds was also collected in the field for biomass modeling using detection and segmentation results derived from model inference. Results showed acomparable performance between the real plant-based syntheticimage (mean average precision for mask-mAPm: 0.60; mean average precision for bounding box-mAPb: 0.64) and real imagedatasets (mAPm: 0.80; mAPb: 0.81). However, themixed dataset(real image+ real plant instance-based synthetic image dataset)resulted inno performance gain for segmentation mask whereas avery small performance gain for bounding box (mAPm: 0.80; mAPb: 0.83). Around 40-50 plant instances were sufficient for generating synthetic images that resulted in optimal performance. Row orientation of cotton in the synthetic images was beneficial compared to random-orientation. Synthetic images generated with automatically-clipped plant instances performed similarly to the ones generated with manually-clipped instances. Generative Adversarial Networks-derived fake plant instances-based synthetic images did not perform as effectively as real plant instance-based synthetic images. The canopy mask area predicted weed biomass better than bounding box area with R2 values of 0.66 and 0.46 for MG and Grass, respectively. The findings of this study offer valuable insights for guiding future endeavors oriented towards using synthetic images for weed detection and segmentation, and biomass estimation in row crops.
