Ensemble of shape functions for 3D object classification

By Walter Wohlkinger, Markus Vincze. IEEE International Conference on Robotics and Biomimetics, 2011

405 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/1e3464d0f05ab9801bb0f886dd4ce2b53663212f

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

In Computer Vision and Pattern Recognition

In Geology

Citations in the corpus

M2DP: A novel 3D point cloud descriptor and its application in loop closure detection (2016, methodology): “ESF uses a voxel grid to approximate the real surface, iteratively samples three points and computes the shape properties.”
Deep Learning Advances in Computer Vision with 3D Data (2017, background): “Popular global descriptors are Ensemble of Shape Functions (ESF) [Wohlkinger and Vincze 2011] and Viewpoint Feature Histogram (VFH) [Rusu et al. 2010].”
3DmFV: Three-Dimensional Point Cloud Classification in Real-Time Using Convolutional Neural Networks (2018, background): “They can be divided into two main groups: local descriptors [8], [9], [10], [11] and global descriptors [12], [13], [14].”
SegMatch: Segment based place recognition in 3D point clouds (2016, background): “f(2) Ensemble of shape histograms: This feature of dimension 1x640 is made of 10 histograms which encode the shape functions D2, D3 and A3 as described in [6].”
3DNet: Large-scale object class recognition from CAD models (2012, methodology): “The Ensemble of Shape Functions descriptor introduced in [23] is based on the SDVS descriptor and includes multiple shape function as described in Osada [14], such as A3(angles), D2(lengths) and D3(areas) which increases the classiﬁcation performance.”
Scan Context: Egocentric Spatial Descriptor for Place Recognition Within 3D Point Cloud Map (2018, methodology): “The existing methods mainly use the histogram [9, 11, 12] to address the two aforementioned 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Madrid, Spain, October 1-5, 2018”
Sliding Shapes for 3D Object Detection in Depth Images (2014, background): “3D classification: Classification-based approaches [65–68, 51, 69–79] typically consider the whole object at the same time by extracting a holistic feature for the whole object and classifying the feature vector via a classifier.”
Hobbit, a care robot supporting independent living at home: First prototype and lessons learned (2016, positive): “For learning and recognizing objects, 3D shape descriptors [40] are calculated from views of the object, coming in the form of RGB-D data from the Kinect camera in the ‘‘head’’ of the robot.”
Noise-Resistant Deep Learning for Object Classification in Three-Dimensional Point Clouds Using a Point Pair Descriptor (2018, methodology): “In particular, we perform voxelization of the object volume using a voxel grid of dimensions Nx × Ny × Nz to enable fast lookup and occupancy check computations [2].”