Abstract
Motion segmentation is aimed at segmenting the feature point trajectories belonging to independently moving objects. Using the affine camera model, the motion segmentation problem can be viewed as a subspace clustering problem—clustering the data points drawn from a union of low-dimensional subspaces. In this paper, we propose a solution for motion segmentation that uses a multi-model fitting technique. We propose a data grouping method and a model selection strategy for obtaining more distinguishable data point permutation preferences, which significantly improves the clustering. We perform extensive testing on the Hopkins 155 dataset, and two real-world datasets. The experimental results illustrate that the proposed method can deal with incomplete trajectories and the perspective effect, comparing favorably with the current state of the art.
Highlights
Motion segmentation is aimed at segmenting objects with different motions in the video and has become an essential issue for many computer vision applications, such as a visual odometer and video segmentation
We propose a motion segmentation method based on the multi-model fitting technique
We propose a data grouping method, which defines the similarity between data points, and introduce the locality-sensitive hashing (LSH) tool in the processing of the similarity to group the data points; We propose a model selection approach that combines energy minimization and the geometric robust information criterion (GRIC) to optimize the model set obtained by the data grouping; No prior knowledge is needed, such as the number of motions, as this can be automatically estimated through the model selection
Summary
Motion segmentation is aimed at segmenting objects with different motions in the video and has become an essential issue for many computer vision applications, such as a visual odometer and video segmentation. The method in [48] is able to estimate the number of motions automatically, which first over-segments motions by the spectral clustering, merges the over-segmented motions It has a high computational cost due to the use of a more complex geometric model in a mixed norm optimization scheme. We propose a data grouping method, which defines the similarity between data points, and introduce the LSH tool in the processing of the similarity to group the data points; We propose a model selection approach that combines energy minimization and the geometric robust information criterion (GRIC) to optimize the model set obtained by the data grouping; No prior knowledge is needed, such as the number of motions, as this can be automatically estimated through the model selection.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
