High-Resolution UAV Image Generation for Sorghum Panicle Detection

TL;DR

This paper introduces a novel data augmentation method using GAN-generated synthetic UAV images to improve Sorghum panicle detection and counting, addressing the challenge of limited labeled data.

Contribution

It presents a GAN-based approach to generate synthetic high-resolution UAV images with labels, enhancing deep learning performance for plant phenotyping.

Findings

Improved panicle detection accuracy with synthetic data

Enhanced counting performance in UAV image analysis

Demonstrated effectiveness of GAN-based augmentation

Abstract

The number of panicles (or heads) of Sorghum plants is an important phenotypic trait for plant development and grain yield estimation. The use of Unmanned Aerial Vehicles (UAVs) enables the capability of collecting and analyzing Sorghum images on a large scale. Deep learning can provide methods for estimating phenotypic traits from UAV images but requires a large amount of labeled data. The lack of training data due to the labor-intensive ground truthing of UAV images causes a major bottleneck in developing methods for Sorghum panicle detection and counting. In this paper, we present an approach that uses synthetic training images from generative adversarial networks (GANs) for data augmentation to enhance the performance of Sorghum panicle detection and counting. Our method can generate synthetic high-resolution UAV RGB images with panicle labels by using image-to-image translation GANs with a limited ground truth dataset of real UAV RGB images. The results show the improvements in panicle detection and counting using our data augmentation approach.