Motion segmentation by subspace separation and model selection

By K. Kanatani. Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001, 2001

413 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/f6822438b2ebf4ff3cbb03e77d34c955021cb836

How researchers see this paper

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

In Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

Sparse Subspace Clustering: Algorithm, Theory, and Applications (2012, background): “…the data not only increases the computational time and memory requirements of algorithms, but also adversely affects their performance due to the noise effect and insufficient number of samples with respect to the ambient space dimension, commonly referred to as the “curse of dimensionality” [1].”
Multi-Scale Fusion Subspace Clustering Using Similarity Constraint (2020, background): “In recent years, subspace clustering [33] has aroused widespread research interests in unsupervised learning and is successfully exploited to various applications, such as image segmentation [22, 36], motion segmentation [14, 4], image clustering [40, 5, 37, 38, 11], genes expression microarray clus”
Sparse subspace clustering (2009, methodology): “Factorization-based methods [6] [12] [16] find an initial segmentation by thresholding the entries of a similarity matrix built from the factorization of the matrix of data points.”
Subspace Clustering (2011, methodology): “Since d is related to the variance of the noise, one can use statistics on the data to determine d (see [22] and [33] for possible methods).”
Spectral Curvature Clustering (SCC) (2009, methodology): “Some of them emphasize modeling of the underlying flats and then use the models to infer the clusters (see e.g., Independent Component Analysis (Hyvärinen and Oja 2000), Subspace Separation (Kanatani 2001, 2002), Generalized Principal Component Analysis (GPCA) (Vidal et al. 2005; Ma et al. 2008)).”
Figure-ground segmentation improves handled object recognition in egocentric video (2010, background): “Sparse features are easier to track or match, and feature tracks are often used in motion segmentation (e.g. [9] [24] [28]).”
Video Pop-up: Monocular 3D Reconstruction of Dynamic Scenes (2014, methodology): “Motion segmentation has also been cast as a motion subspace clustering problem, first applied to the affine camera case [9], [19] and later extended to the case of perspective scenes [22].”
A Closed-Form Solution to Non-Rigid Shape and Motion Recovery (2004, methodology): “The factorization technique has been extended to the non-rigid cases (Costeira and Kanade, 1998; Han and Kanade, 2000; Wolf and Shashua, 2001; Kanatani, 2001; Wolf and Shashua, 2002; Vidal and Soatto, 2002; Zelnik-Manor and Irani, 2003; Sugaya and Kanatani, 2004; Vidal and Hartley, 2004).”
Sparse Subspace Clustering: Algorithm, Theory, and Applications (2013, methodology): “Factorization-based algebraic approaches such as [8], [9], [15] find an initial segmentation by thresholding the entries of a similarity matrix built from the factorization of the data matrix.”
Motion Segmentation in the Presence of Outlying, Incomplete, or Corrupted Trajectories (2010, background): “Factorization-based approaches [5], [12], [16], [17] attempt to directly factor Y according to (4).”
A Geometric Analysis of Subspace Clustering with Outliers (2011, methodology): “In the presence of noise, or when the independence assumption is violated, various methods have been proposed to “clean up” the aﬃnity matrix and put it into block diagonal form [10, 23, 20, 46, 24, 22].”
A Continuous Occlusion Model for Road Scene Understanding (2016, methodology): “For moving objects, this is within the purview of motion segmentation, which has been approached through algebraic factorization methods [4, 27, 26], statistical methods [11, 9, 20] and clustering methods [31, 8].”
A Benchmark for the Comparison of 3-D Motion Segmentation Algorithms (2007, methodology): “However, this process is very sensitive to noise [5, 10, 19].”
Robust and Efficient Subspace Segmentation via Least Squares Regression (2012, neutral): “image representation [1], cl ustering [2] and motion segmentation [3] [4].”
A General Framework for Motion Segmentation: Independent, Articulated, Rigid, Non-rigid, Degenerate and Non-degenerate (2006, methodology): “[2][10][11][12], use the dot product of the trajectories or some normalized form as the affinity measurement for clustering.”
Visual SLAM and Structure from Motion in Dynamic Environments (2018, methodology): “Based on the limitation of previous works, Kanatani [71, 72] proposed Geometric Information Criterion (G-AIC, or in some literature called GIC) by taking into account the number of observations and the dimension of the model; it has the following form: GIC = (−2)loд(L) + 2(DN + K ), (3) where N is t”
Deep Subspace Clustering Networks (2017, methodology): “The resulting methods can then be roughly divided into three categories [42]: factorization methods [7, 17, 44, 29, 16], higher-order model based methods [49, 6, 33, 37], and self-expressiveness based methods [9, 24, 26, 46, 15, 12, 22, 52].”
Subspace Clustering by Block Diagonal Representation (2018, methodology): “Subspace clustering has many applications in computer vision [16],”
Multiframe Motion Segmentation with Missing Data Using PowerFactorization and GPCA (2008, neutral): “Kanatani scales the entries of Q using the geometric Akaike’s information criterion for linear (Kanatani 2001) and affine (Kanatani and Matsunaga 2002) subspaces.”