Segmentation by continuous latent semantic analysis for multi-structure model fitting
Abstract
In this paper, we propose a novel continuous latent semantic analysis fitting method, to efficiently and effectively estimate the parameters of model instances in data, based on latent semantic analysis and continuous preference analysis. Specifically, we construct a new latent semantic space (LSS): where inliers of different model instances are mapped into several independent directions, while gross outliers are distributed close to the origin of LSS. After that, we analyze the data distribution to effectively remove gross outliers in LSS, and propose an improved clustering algorithm to segment the remaining data points. On the one hand, the proposed fitting method is able to achieve excellent fitting results; due to the effective continuous preference analysis in LSS. On the other hand, the proposed method can efficiently obtain final fitting results due to the dimensionality reduction in LSS. Experimental results on both synthetic data and real images demonstrate that the proposed method achieves significant superiority over several state-of-the-art model fitting methods on both fitting accuracy and computational speed.
RAS ID
35652
Document Type
Journal Article
Date of Publication
2021
Funding Information
This work was supported by the National Natural Science Foundation of China under Grants 62072223, 61872307, and by the Natural Science Foundation of Fujian Province under Grants 2020J01829.
School
School of Science
Copyright
subscription content
Publisher
Springer
Comments
Xiao, G., Wang, H., Ma, J., & Suter, D. (2021). Segmentation by continuous latent semantic analysis for multi-structure model fitting. International Journal of Computer Vision,129(7), 2034-2056. https://doi.org/10.1007/s11263-021-01468-6