Towards Large-Scale Rendering of Simulated Crops for Synthetic Ground Truth Generation on Modular Supercomputers

TL;DR

This paper proposes a scalable approach to generate synthetic crop images using Unreal Engine and distributed GPU rendering, aiming to improve training data availability for computer vision in agriculture.

Contribution

It introduces a method for large-scale rendering of virtual crop scenes on modular supercomputers, enabling efficient synthetic data generation for training neural networks.

Findings

Scalable rendering of complex crop scenes achieved on supercomputers.

Distributed GPU training reduces time for synthetic data generation.

Enhanced training data availability for crop image analysis.

Abstract

Computer Vision problems deal with the semantic extraction of information from camera images. Especially for field crop images, the underlying problems are hard to label and even harder to learn, and the availability of high-quality training data is low. Deep neural networks do a good job of extracting the necessary models from training examples. However, they rely on an abundance of training data that is not feasible to generate or label by expert annotation. To address this challenge, we make use of the Unreal Engine to render large and complex virtual scenes. We rely on the performance of individual nodes by distributing plant simulations across nodes and both generate scenes as well as train neural networks on GPUs, restricting node communication to parallel learning.