Local Descriptor for Robust Place Recognition using LiDAR Intensity
This addresses place recognition for mobile robots in challenging environments with viewpoint and illumination changes, representing an incremental improvement by integrating intensity data with existing geometric methods.
The paper tackled the problem of robust place recognition in mobile robotics by combining LiDAR geometric information with calibrated intensity returns to create a new descriptor, ISHOT, which outperformed geometric-only descriptors by a significant margin in evaluations. They also developed a probabilistic keypoint voting algorithm that achieved sublinear place recognition performance, validated in large-scale built-up and unstructured environments.
Place recognition is a challenging problem in mobile robotics, especially in unstructured environments or under viewpoint and illumination changes. Most LiDAR-based methods rely on geometrical features to overcome such challenges, as generally scene geometry is invariant to these changes, but tend to affect camera-based solutions significantly. Compared to cameras, however, LiDARs lack the strong and descriptive appearance information that imaging can provide. To combine the benefits of geometry and appearance, we propose coupling the conventional geometric information from the LiDAR with its calibrated intensity return. This strategy extracts extremely useful information in the form of a new descriptor design, coined ISHOT, outperforming popular state-of-art geometric-only descriptors by significant margin in our local descriptor evaluation. To complete the framework, we furthermore develop a probabilistic keypoint voting place recognition algorithm, leveraging the new descriptor and yielding sublinear place recognition performance. The efficacy of our approach is validated in challenging global localization experiments in large-scale built-up and unstructured environments.