3D Segmentation and Damage Analysis from Robotic Scans of Disaster Sites
Chen, Jing Dao Dao
MetadataShow full item record
Disaster relief and response plays an important role in saving lives and reducing economic loss after earthquakes, windstorm events and man-made explosions. Mobile robots represent an effective solution to assist in post-disaster reconnaissance in areas that are dangerous to human agents. These robots need an accurate 3D semantic map of the site in order to carry out disaster relief work such as search and rescue and damage assessment. Thus, there exists a research need to automatically identify building elements and detect structural damage from laser-scanned points clouds acquired by mobile robots. Current methods for point cloud semantic segmentation mostly perform direct class prediction at the point level without considering object-level semantics and generalizability across datasets. Moreover, current segmentation methods are unsuitable for real-time operation because they are designed to work as a post-processing step and do not process points from new scans in an online manner. This research proposes a learnable region growing method to perform class-agnostic point cloud segmentation in a data-driven and generalizable manner. In addition, an anomaly-based crack segmentation method is proposed where a deep feature embedding is used as a basis for separation between inlier and outlier points. Finally, an incremental segmentation scheme is used to process point cloud data in an online fashion and combine semantic information across multiple scans.