A method to segment maps from different modalities using free space layout -- MAORIS : MAp Of RIpples Segmentation
This addresses the need for robust map segmentation in human-robot interaction and semantic mapping, offering improved performance over existing methods, though it is incremental as it builds on prior segmentation techniques.
The paper tackles the problem of segmenting maps from different modalities, such as robot-built and hand-drawn sketch maps, into semantic representations like rooms and corridors, achieving a Matthews correlation coefficient (MCC) of 0.98 on a public dataset compared to 0.65 and 0.70 for state-of-the-art methods, and 0.56 on a new sketch dataset against 0.28 and 0.30.
How to divide floor plans or navigation maps into semantic representations, such as rooms and corridors, is an important research question in fields such as human-robot interaction, place categorization, or semantic mapping. While most works focus on segmenting robot built maps, those are not the only types of map a robot, or its user, can use. We present a method for segmenting maps from different modalities, focusing on robot built maps and hand-drawn sketch maps, and show better results than state of the art for both types. Our method segments the map by doing a convolution between the distance image of the map and a circular kernel, and grouping pixels of the same value. Segmentation is done by detecting ripple-like patterns where pixel values varies quickly, and merging neighboring regions with similar values. We identify a flaw in the segmentation evaluation metric used in recent works and propose a metric based on Matthews correlation coefficient (MCC). We compare our results to ground-truth segmentations of maps from a publicly available dataset, on which we obtain a better MCC than the state of the art with 0.98 compared to 0.65 for a recent Voronoi-based segmentation method and 0.70 for the DuDe segmentation method. We also provide a dataset of sketches of an indoor environment, with two possible sets of ground truth segmentations, on which our method obtains an MCC of 0.56 against 0.28 for the Voronoi-based segmentation method and 0.30 for DuDe.