3D free-form object recognition in range images using local surface patches

By Hui Chen, Bir Bhanu. Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004., 2004

523 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/761bb237531765fb92287cc60ac77f6c63a8eade

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

Citations in the corpus

Model globally, match locally: Efficient and robust 3D object recognition (2010, background): “Chen and Bhanu [3] introduced a local surface patch representation that is a histogram of shape index values vs.”
Body Surface Context: A New Robust Feature for Action Recognition From Depth Videos (2014, background): “It is a very effective approach to represent a shape or a surface by describing the context structures for reference points [33], [34].”
Image Matching from Handcrafted to Deep Features: A Survey (2020, background): “Chen and Bhanu (2007) introduced the local surface patch (LSP) method.”
SHOT: Unique signatures of histograms for surface and texture description (2014, background): “This task is accomplished by 3D detectors [5, 6, 7], whose aim is to single out points that are distinctive, to allow for effective description and matching, as well as repeatable with respect to vantage point variations and noise.”
Rotational Projection Statistics for 3D Local Surface Description and Object Recognition (2013, methodology): “While LSP and THRIFT based algorithms were very sensitive to noise.”
A combined texture-shape descriptor for enhanced 3D feature matching (2011, methodology): “Several approaches have been proposed for 3D feature point detection and description [1] [2] [3] [4] [5] [6] [7].”
Performance Evaluation of 3D Keypoint Detectors (2012, methodology): “One example of the approach relying on point-wise saliency measurements is Local Surface Patches (LSP), introduced in Chen and Bhanu (2007).”
3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration (2018, background): “s of the year (bottom) give mostly wrong matches even after RANSAC. Right: 3D point cloud of the same scene remains largely the same and can be matched easily. be broadly categorized into handcrafted [35,5,26,25,13,30,28] and learning approaches [34,8,15,27,6] - i.e. pre- and post- deep learning app”
3D Object Recognition in Cluttered Scenes with Local Surface Features: A Survey (2014, methodology): “Chen and Bhanu [68] proposed " local surface patches " by accumulating the number of points into a 2D histogram.”
Deep Learning Advances in Computer Vision with 3D Data (2017, background): “Indicative examples of ﬁxed-scale detectors are Local Surface Patches (LSPs) [Chen and Bhanu 2007], Intrinsic Shape Signatures (ISSs) [Zhong 2009], and the 3D detector proposed in Mian et al. [2010] termed as “KeyPoint Quality” (KPQ) in Tombari et al. [2013], while a popular adaptive-scale detector…”
Unique shape context for 3d data description (2010, methodology): “After the matching stage, in order to compute a subset of reliable correspondences out of those yielded by the matcher, the Geometric Consistency approach is used, which is a typical object recognition algorithm [4,9].”
Unique Signatures of Histograms for Local Surface Description (2010, background): “Within the same subclass, Local Surface Patches [10] computes histograms of normals and shape indexes [11] of the points belonging to the support.”
Review: deep learning on 3D point clouds (2020, background): “In the past few years, processing of point cloud for visual intelligence has been based on handcrafted features [1, 2, 3, 4, 5, 6].”
A Global Hypotheses Verification Method for 3D Object Recognition (2012, methodology): “Our CG approach, inspired by [16], iteratively groups subsets of correspondences based on checking the geometric consistency of pairs of correspondences.”
Autonomous robotic stone stacking with online next best object target pose planning (2017, methodology): “Then we use an approach, presented in [20], to verify that the matched keypoints are geometrical consistent.”
Tutorial: Point Cloud Library: Three-Dimensional Object Recognition and 6 DOF Pose Estimation (2012, methodology): “In this comparison, we have used an approach similar to that proposed in [18], where an iterative algorithm based on simple geometric consistency of pairs of correspondences was proposed.”
RPM-Net: Robust Point Matching Using Learned Features (2020, background): “Generally, these descriptors accumulate measurements (typically number of points) into histograms according to their spatial coordinates [9, 14, 32], or their geometric attributes such as curvature [4] or normals [28].”
Sliding Shapes for 3D Object Detection in Depth Images (2014, unknown): “Keypoint matching: Just as SIFT keypoints for image matching [50], a popular type of algorithms [51–60] is to detect keypoints on a 3D point cloud or a mesh, generate descriptors for the keypoints (e.”