Skip to Main content Skip to Navigation
Theses

Hybrid Machine Learning and Geometric Approaches for Single RGB Camera Relocalization

Abstract : In the last few years, image-based camera relocalization becomes an important issue of computer vision applied to augmented reality, robotics as well as autonomous vehicles. Camera relocalization refers to the problematic of the camera pose estimation including both 3D translation and 3D rotation. In localization systems, camera relocalization component is necessary to retrieve camera pose after tracking lost, rather than restarting the localization from scratch.This thesis aims at improving the performance of camera relocalization in terms of both runtime and accuracy as well as handling challenges of camera relocalization in dynamic environments. We present camera pose estimation based on combining multi-patch pose regression to overcome the uncertainty of end-to-end deep learning methods. To balance between accuracy and computational time of camera relocalization from a single RGB image, we propose a sparse feature hybrid methods. A better prediction in the machine learning part of our methods leads to a rapid inference of camera pose in the geometric part. To tackle the challenge of dynamic environments, we propose an adaptive regression forest algorithm that adapts itself in real time to predictive model. It evolves by part over time without requirement of re-training the whole model from scratch. When applying this algorithm to our real-time and accurate camera relocalization, we can cope with dynamic environments, especially moving objects. The experiments proves the efficiency of our proposed methods. Our method achieves results as accurate as the best state-of-the-art methods on the rigid scenes dataset. Moreover, we also obtain high accuracy even on the dynamic scenes dataset.
Complete list of metadatas

Cited literature [203 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-02879103
Contributor : Abes Star :  Contact
Submitted on : Tuesday, June 23, 2020 - 3:10:21 PM
Last modification on : Monday, October 5, 2020 - 9:44:04 AM
Long-term archiving on: : Thursday, September 24, 2020 - 5:49:53 PM

File

2019_DUONG_archivage.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-02879103, version 1

Citation

Nam-Duong Duong. Hybrid Machine Learning and Geometric Approaches for Single RGB Camera Relocalization. Computer Vision and Pattern Recognition [cs.CV]. CentraleSupélec, 2019. English. ⟨NNT : 2019CSUP0008⟩. ⟨tel-02879103⟩

Share

Metrics

Record views

87

Files downloads

201