# A Comparative Study of Physically Accurate Synthetic Shadow Datasets in Agricultural Settings with Human Activity

## TL;DR

This paper evaluates a synthetic shadow dataset for agriculture, showing it performs well for training models, especially in similar domains.

## Contribution

The study introduces a photorealistic synthetic shadow dataset tailored for agriculture with human activity.

## Key findings

- AgroSegNet shows competitive performance in shadow segmentation tasks.
- The synthetic dataset is effective for transfer learning in agricultural domains.
- Annotation quality and image domain significantly influence model training outcomes.

## Abstract

Shadow, a natural phenomenon resulting from the absence of light, plays a pivotal role in agriculture, particularly in processes such as photosynthesis in plants. Despite the availability of generic shadow datasets, many suffer from annotation errors and lack detailed representations of agricultural shadows with possible human activity inside, excluding those derived from satellite or drone views. In this paper, we present an evaluation of a synthetically generated top-down shadow segmentation dataset characterized by photorealistic rendering and accurate shadow masks. We aim to determine its efficacy compared to real-world datasets and assess how factors such as annotation quality and image domain influence neural network model training. To establish a baseline, we trained numerous baseline architectures and subsequently explored transfer learning using various freely available shadow datasets. We further evaluated the out-of-domain performance compared to the training set of other shadow datasets. Our findings suggest that AgroSegNet demonstrates competitive performance and is effective for transfer learning, particularly in domains similar to agriculture.