Automatically Generating Image Segmentation Datasets for Video Games

David LeBlanc, Greg Lee

2023

Abstract

Image segmentation is applied to images fed as input to deep reinforcement learning agents as a way of highlighting key-features and removing non-key features. If a segmented image is of lower resolution than its source, the problem is further simplified. However, the process of creating a dataset for the training of an image segmenting network is long and costly if done manually. This paper proposes a methodology for automatically generating an arbitrarily large image segmentation dataset with a specifiable segmentation resolution. A convolutional neural network trained for image segmentation using this automatically generated dataset had higher accuracy than a network using a manually labelled training set. Furthermore, an image segmenting network trained on a dataset generated in this manner gave superior performance to an autoencoder in reducing dimensionality while preserving key features. The method proposed was tested on Super Mario Bros. for the Nintendo Entertainment System (NES), but the techniques could apply to any image segmentation problem where it is possible to simulate the placement of key objects.

Paper Citation

in Harvard Style

LeBlanc D. and Lee G. (2023). Automatically Generating Image Segmentation Datasets for Video Games. In Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART, ISBN 978-989-758-623-1, pages 509-516. DOI: 10.5220/0011693800003393

in Bibtex Style

@conference{icaart23,
author={David LeBlanc and Greg Lee},
title={Automatically Generating Image Segmentation Datasets for Video Games},
booktitle={Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART,},
year={2023},
pages={509-516},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011693800003393},
isbn={978-989-758-623-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART,
TI - Automatically Generating Image Segmentation Datasets for Video Games
SN - 978-989-758-623-1
AU - LeBlanc D.
AU - Lee G.
PY - 2023
SP - 509
EP - 516
DO - 10.5220/0011693800003393