Enhancing Visual Odometry Estimation Performance Using Image Enhancement Models

Hajira Saleem, Hajira Saleem, Reza Malekian, Reza Malekian, Hussan Munir, Hussan Munir

2024

Abstract

Visual odometry is a key component of autonomous vehicle navigation due to its cost-effectiveness and efficiency. However, it faces challenges in low-light conditions because it relies solely on visual features. To mitigate this issue, various methods have been proposed, including sensor fusion with LiDAR, multi-camera systems, and deep learning models based on optical flow and geometric bundle adjustment. While these approaches show potential, they are often computationally intensive, perform inconsistently under different lighting conditions, and require extensive parameter tuning. This paper evaluates the impact of image enhancement models on visual odometry estimation in low-light scenarios. We assess odometry performance on images processed with gamma transformation and four deep learning models: RetinexFormer, MAXIM, MIRNet, and KinD++. These enhanced images were tested using two odometry estimation techniques: TartanVO and Selective VIO. Our findings highlight the importance of models that enhance odometry-specific features rather than merely increasing image brightness. Additionally, the results suggest that improving odometry accuracy requires image-processing models tailored to the specific needs of odometry estimation. Furthermore, since different odometry models operate on distinct principles, the same image-processing technique may yield varying results across different models.

Paper Citation

in Harvard Style

Saleem H., Malekian R. and Munir H. (2024). Enhancing Visual Odometry Estimation Performance Using Image Enhancement Models. In Proceedings of the 21st International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO; ISBN 978-989-758-717-7, SciTePress, pages 293-300. DOI: 10.5220/0012932600003822

in Bibtex Style

@conference{icinco24,
author={Hajira Saleem and Reza Malekian and Hussan Munir},
title={Enhancing Visual Odometry Estimation Performance Using Image Enhancement Models},
booktitle={Proceedings of the 21st International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO},
year={2024},
pages={293-300},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012932600003822},
isbn={978-989-758-717-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 21st International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO
TI - Enhancing Visual Odometry Estimation Performance Using Image Enhancement Models
SN - 978-989-758-717-7
AU - Saleem H.
AU - Malekian R.
AU - Munir H.
PY - 2024
SP - 293
EP - 300
DO - 10.5220/0012932600003822
PB - SciTePress