Point feature extraction on 3D range scans taking into account object boundaries

By Bastian Steder, Radu Bogdan Rusu, Kurt Konolige, Wolfram Burgard. IEEE International Conference on Robotics and Automation, 2011

305 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Geology

View Paper: https://www.semanticscholar.org/paper/bc89fc6d6333e358e3b65c8e956567621cb60a3d

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

1. Vladlen Koltun
2. Yulan Guo
3. Min Lu
4. Qian-Yi Zhou
5. Ferdous Sohel
6. Jianwei Wan
7. Federico Tombari
8. Mohammed Bennamoun

In Computer Vision and Pattern Recognition

1. Vladlen Koltun
2. Yulan Guo
3. Mohammed Bennamoun
4. Ferdous Sohel
5. Federico Tombari
6. Min Lu
7. Luigi Di Stefano
8. Jianwei Wan

In Geology

1. Vladlen Koltun
2. Qian-Yi Zhou
3. Yulan Guo
4. Federico Tombari
5. Min Lu
6. Luigi Di Stefano
7. Mohammed Bennamoun
8. Ferdous Sohel

Citations in the corpus

• 3D is here: Point Cloud Library (PCL) (2011, methodology): “An example of the PCL implementation pipeline for Fast Point Feature Histogram (FPFH) [4] estimation. pling, outlier removal, indices extraction, projections, etc; • libpcl features: implements many 3D features such as surface normals and curvatures, boundary point estimation , moment invariants, pr”
• Robust reconstruction of indoor scenes (2015, background): “In the past decade researchers have studied local shape descriptors that can be used for pruning and correspondence [20, 52, 55, 24], and proposed different types of constellations [2, 16, 43].”
• Performance of histogram descriptors for the classification of 3D laser range data in urban environments (2012, background): “Over the last years, a variety of descriptors for matching of point clouds [8], [13], object recognition [9], [14] and classification [15], [5], [4] representing properties of the surrounding surface of one point were proposed.”
• Learning to Detect Good 3D Keypoints (2017, methodology): “13, the relative ordering of hand-crafted detectors does change: on the one hand, the baseline uniform sampling approach performs better than KPQ, ISS, and Harris3D; on the other hand, NARF, whose performance was quite unsatisfactory on previous datasets, turns out the best hand-crafted detector onK”
• 3D Object Recognition in Cluttered Scenes with Local Surface Features: A Survey (2014, background): “[105], [106] first aligned the local patch around the keypoint p with the normal of p .”