Accurate Sparse Feature Regression Forest Learning for Real-Time Camera Relocalization

Abstract : Camera relocalization is needed in several applications such as augmented reality or robot navigation. However, it is still challenging to have a both real-time and accurate method. In this paper, we present our hybrid method combing machine learning approach and geometric approach for real-time camera relocalization from a single RGB image. We introduce our sparse feature regression forest to improve the machine learning part. In our regression forest, we propose a novel split function, that uses a whole feature vector instead of classical binary test function to improve the accuracy of 2D-3D point correspondences. Moreover, we use sparse feature extraction (SURF features) to reduce time processing. The results indicate that our method is the only real-time hybrid method (50ms per frame). We also achieve results as accurate as the best state-of-the-art methods (hybrid methods) and outperform machine learning based and sparse feature based methods.
Document type :
Conference papers
Complete list of metadatas

https://hal-univ-rennes1.archives-ouvertes.fr/hal-01971931
Contributor : Laurent Jonchère <>
Submitted on : Monday, January 7, 2019 - 2:02:11 PM
Last modification on : Thursday, July 25, 2019 - 9:50:38 AM

Identifiers

Citation

Nam-Duong Duong, Amine Kacete, Catherine Soladie, Pierre-Yves Richard, Jérôme Royan. Accurate Sparse Feature Regression Forest Learning for Real-Time Camera Relocalization. 6th International Conference on 3D Vision (3DV), Sep 2018, Verona, Italy. ⟨10.1109/3DV.2018.00079⟩. ⟨hal-01971931⟩

Share

Metrics

Record views

300