Highly robust estimator using a case-dependent residual distribution model

Ngo Trung Thanh, Hajime Nagahara, Ryusuke Sagawa, Yasuhiro Mukaigawa, Masahiko Yachida, Yasushi Yagi

Research output: Contribution to journalArticlepeer-review


The latest robust estimators usually take advantage of density estimation, such as kernel density estimation, to improve the robustness of inlier detection. However, the challenging problem for these systems is choosing the suitable smoothing parameter, which can result in the population of inliers being overor under-estimated, and this, in turn, reduces the robustness of the estimation. To solve this problem, we propose a robust estimator that estimates an accurate inlier scale. The proposed method first carries out an analysis to figure out the residual distribution model using the obvious case-dependent constraint, the residual function. Then the proposed inlier scale estimator performs a global search for the scale producing the residual distribution that best fits the residual distribution model. Knowledge about the residual distribution model provides a major advantage that allows us to estimate the inlier scale correctly, thereby improving the estimation robustness. Experiments with various simulations and real data are carried out to validate our algorithm, which shows certain benefits compared with several of the latest robust estimators.

Original languageEnglish
Pages (from-to)260-276
Number of pages17
JournalIPSJ Transactions on Computer Vision and Applications
Publication statusPublished - 2009
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition


Dive into the research topics of 'Highly robust estimator using a case-dependent residual distribution model'. Together they form a unique fingerprint.

Cite this