Indoor Surface Classification for Mobile Robots

<p>In this project, we generated a dataset that contains three different types of indoor floor surfaces: carpet, tile and wood. Then, we used this dataset to train eight CNN-based models, including our proposed model, <em><strong>MobileNetV2-modified</strong></em>.</p> <ul> <li>The dataset comprises a total of 2081 samples, consisting of images captured with cameras in various indoor environments and lighting conditions.</li> <li>These images were taken from different angles in accordance with the overall dimensions of the indoor robots.</li> <li>This dataset includes samples collected from more than 20 different indoor environments.</li> <li>The dataset consists of 870 carpet samples, 638 tile samples and 573 wood surface samples.</li> </ul> <p>&nbsp;</p>