Customized HouseExpo dataset

This dataset was prepared for our research on global map completion in robotics. It is designed for tasks involving <b>sequential and incremental map data collection</b> during robot exploration.The dataset is based on the <b>HouseExpo</b> environment and was generated using <b>Gazebo</b> and <b>ROS</b> to simulate exploration sequences with enhanced <b>frontier detection</b>.The dataset includes:<b>3,384 images</b> for training<b>376 images</b> for validation<b>940 images</b> for testingAll images are in <b>PNG format</b>, converted from the original PGM format to ensure ease of use.Additional implementation details, code, and usage instructions can be found on the accompanying GitHub repository:<br>👉 https://github.com/f0120050/houseexpo_based_custom_dataset_with_gazebo