Towards Large-Scale Rendering of Simulated Crops for Synthetic Ground Truth Generation on Modular Supercomputers
This addresses the problem of limited expert-annotated training data for crop image analysis, though it is incremental as it applies existing rendering and distributed computing methods to a specific domain.
The paper tackles the challenge of generating high-quality synthetic training data for computer vision tasks in field crop images by using the Unreal Engine to render large virtual scenes on modular supercomputers, distributing plant simulations across nodes to efficiently create scenes and train neural networks on GPUs.
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.