Abstract
We focus on the problem of class-agnostic instance segmentation of LiDAR point clouds. We propose an approach that combines graph-theoretic search with data-driven learning: it searches over a set of candidate segmentations and returns one where individual segments score well according to a data-driven point-based model of “objectness”. We prove that if we score a segmentation by the worst objectness among its individual segments, there is an efficient algorithm that finds the optimal worst-case segmentation among an exponentially large number of candidate segmentations. We also present an efficient algorithm for the average-case. For evaluation, we repurpose KITTI 3D detection as a segmentation benchmark and empirically demonstrate that our algorithms significantly outperform past bottom-up segmentation approaches and top-down object-based algorithms on segmenting point clouds.
Highlights
P ERCEPTION for autonomous robots presents a collection of compelling challenges for computer vision
Approach: Our approach searches over an exponentially-large space of candidate segmentations and returns one where individual segments score well according to a data-driven point-based model of “objectness” [3]
We introduce efficient algorithms that search over this space of tree-consistent segmentations (Figure 2) and return the one that maximizes a global segmentation score that is computed by aggregating local objectness scores of individual segments
Summary
P ERCEPTION for autonomous robots presents a collection of compelling challenges for computer vision. We focus on the application of autonomous vehicles. This domain has three notable properties that tend not to surface in traditional vision applications: (1) 3D sensing in the form of LiDAR technology, which exhibits different properties than traditional 3D vision captured through stereo or structured light. Autonomous systems require the ability to recognize all possible obstacles and movers - e.g., a piece of road debris must be avoided regardless of what name it has. Such understanding is crucial from a safety perspective. This has been formulated as a perceptual grouping or bottom-up segmentation task, which is typically addressed with different
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
