Hough Transform and 3D SURF for Robust Three Dimensional Classification

By Jan Knopp, Mukta Prasad, Geert Willems, Radu Timofte, Luc Van Gool. 2010

388 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computational Mechanics, Computer Vision and Pattern Recognition, 3D Vision & Pose

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 Computational Mechanics

In Computer Vision and Pattern Recognition

In 3D Vision & Pose

Citations in the corpus

Volumetric and Multi-view CNNs for Object Classification on 3D Data (2016, methodology): “Alternatives include models based on distances, angles, triangle areas, or tetrahedra volumes [23], local shape diameters measured at densely-sampled surface points [3], Heat kernel signatures [1, 17], or extensions of SIFT and SURF feature descriptors to 3D voxel grids [16].”
Multi-view Convolutional Neural Networks for 3D Shape Recognition (2015, background): “For example, shapes can be represented with histograms or bag-of-features models constructed out of surface normals and curvatures [15], distances, angles, triangle areas or tetrahedra volumes gathered at sampled surface points [25], properties of spherical functions defined in volumetric grids [16]”
Multi-View Silhouette and Depth Decomposition for High Resolution 3D Object Representation (2018, background): “Other representations aim to use orientation [36], rotational invariance [15] or 3D-SURF features [16].”
Taskonomy: Disentangling Task Transfer Learning (2018, background): “They are often invariant to informative (but possibly distracting) features such as textures [50, 39, 25, 47, 16].”
Pairwise Decomposition of Image Sequences for Active Multi-view Recognition (2016, background): “Shape descriptors include distributions of local surface properties [14, 32], spherical harmonic functions over voxel grids [24], and 3D local invariant features [25].”
Trajectory-Based Modeling of Human Actions with Motion Reference Points (2012, background): “The first category extracts/learns spatial-temporal local features where many efforts have been devoted to the design of good detectors/descriptors [1,7,8,9,10,11] or feature learning algorithms [12,13,14].”
GVCNN: Group-View Convolutional Neural Networks for 3D Shape Recognition (2018, methodology): “The shape-based descriptor was designed based on the native 3D representations of objects, such as voxel grid [26], polygon mesh [2, 10], local shape diameters measured at densely sampled surface points [3], or extensions of the SIFT and SURF descriptors to 3D voxel grids [13].”
Sliding Shapes for 3D Object Detection in Depth Images (2014, methodology): “We perform dictionary coding on top each of them [20].”
Performance Evaluation of 3D Keypoint Detectors (2012, methodology): “Unlike previous proposals, 3D SURF (Knopp et al. 2010) builds a scale-space out of a voxelized version of the original mesh.”
Learning a Hierarchical Latent-Variable Model of 3D Shapes (2017, background): “Early efforts [28, 23, 34] often combined simple image classification methods with handcrafted shape descriptors, requiring intensive effort on the side of the human data annotator.”
M2DP: A novel 3D point cloud descriptor and its application in loop closure detection (2016, methodology): “The 3D SURF [19] extends the popular 2D SURF descriptor to 3D data by voxelizing the 3D mesh and defining the saliency of each voxel by the Haar wavelet response.”
Learning to Rank 3D Features (2014, background): “[17] proposed to weight the 3D features based on how often they vote for the correct shape center on a training set.”
High-level event recognition in unconstrained videos (2012, methodology): “[62] extended SURF to efficiently compute 3D spatio-temporal key-points.”
ImVoteNet: Boosting 3D Object Detection in Point Clouds With Image Votes (2020, methodology): “Most relevant to our work are PointRCNN [41] and Deep Hough Voting (VOTENET) [33] (related to earlier Hough voting ideas [47, 50, 16, 15]) which demonstrated state-ofthe-art 3D object detection in outdoor and indoor scenes, respectively.”
3D-Div: A novel local surface descriptor for feature matching and pairwise range image registration (2013, methodology): “[3] proposed 3D SURF descriptors for shape retrieval and classification.”
3D Object Classification via Spherical Projections (2017, background): “While early works focus on leveraging handcrafted features for classification [14, 1, 12, 8, 15, 9], recent methods seek to leverage the power of deep neural networks [27, 25].”
3D Object Recognition in Cluttered Scenes with Local Surface Features: A Survey (2014, methodology): “Local extrema over the space sðv v; sÞ were used to detect the " 3D SURF " keypoints and their corresponding scales.”