Finding Outliers in a Haystack: Anomaly Detection for Large Pointcloud Scenes
By: Ryan Faulkner , Luke Haub , Simon Ratcliffe and more
Potential Business Impact:
Helps robots see new things in outdoor scenes.
LiDAR scanning in outdoor scenes acquires accurate distance measurements over wide areas, producing large-scale point clouds. Application examples for this data include robotics, automotive vehicles, and land surveillance. During such applications, outlier objects from outside the training data will inevitably appear. Our research contributes a novel approach to open-set segmentation, leveraging the learnings of object defect-detection research. We also draw on the Mamba architecture's strong performance in utilising long-range dependencies and scalability to large data. Combining both, we create a reconstruction based approach for the task of outdoor scene open-set segmentation. We show that our approach improves performance not only when applied to our our own open-set segmentation method, but also when applied to existing methods. Furthermore we contribute a Mamba based architecture which is competitive with existing voxel-convolution based methods on challenging, large-scale pointclouds.
Similar Papers
Finding Outliers in a Haystack: Anomaly Detection for Large Pointcloud Scenes
CV and Pattern Recognition
Helps robots see new things in outdoor scenes.
Robust 3D Object Detection using Probabilistic Point Clouds from Single-Photon LiDARs
CV and Pattern Recognition
Improves robot vision in dark or far away.
Self-Supervised Moving Object Segmentation of Sparse and Noisy Radar Point Clouds
CV and Pattern Recognition
Helps self-driving cars see moving things faster.