ForestVO: Enhancing Visual Odometry in Forest Environments Through ForestGlue

Recent advancements in visual odometry systems have improved autonomous navigation, yet challenges persist in complex environments like forests, where dense foliage, variable lighting, and repetitive textures compromise the accuracy of feature correspondences. To address these challenges, we introdu...

Full description

Saved in:
Bibliographic Details
Published in:IEEE robotics and automation letters Vol. 10; no. 6; pp. 5233 - 5240
Main Authors: Pritchard, Thomas, Ijaz, Saifullah, Clark, Ronald, Kocer, Basaran Bahadir
Format: Journal Article
Language:English
Published: Piscataway IEEE 01.06.2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Accuracy
Autonomous navigation
Cameras
Computational modeling
Computer vision for automation
Feature extraction
Foliage
Forestry
Forests
localization
Navigation systems
Pose estimation
Real time
Real-time systems
robotics and automation in agriculture and forestry
Simultaneous localization and mapping
Training
Visual odometry
ISSN:2377-3766, 2377-3766
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recent advancements in visual odometry systems have improved autonomous navigation, yet challenges persist in complex environments like forests, where dense foliage, variable lighting, and repetitive textures compromise the accuracy of feature correspondences. To address these challenges, we introduce ForestGlue. ForestGlue enhances the SuperPoint feature detector through four configurations - grayscale, RGB, RGB-D, and stereo-vision inputs - optimised for various sensing modalities. For feature matching, we employ LightGlue or SuperGlue, both of which have been retrained using synthetic forest data. ForestGlue achieves comparable pose estimation accuracy to baseline LightGlue and SuperGlue models, yet require only 512 keypoints, just 25% of the 2048 keypoints used by baseline models, to achieve an LO-RANSAC AUC score of 0.745 at a 10° threshold. With a 1/4 of the keypoints required, ForestGlue has the potential to reduce computational overhead whilst being effective in dynamic forest environments, making it a promising candidate for real-time deployment on resource-constrained platforms such as drones or mobile robotic platforms. By combining ForestGlue with a novel transformer based pose estimation model, we propose ForestVO, which estimates relative camera poses using the 2D pixel coordinates of matched features between frames. On challenging TartanAir forest sequences, ForestVO achieves an average relative pose error (RPE) of 1.09 m and kitti_score of 2.33%, outperforming direct-based methods such as DSO in dynamic scenes by 40%, while maintaining competitive performance with TartanVO despite being a significantly lighter model trained on only 10% of the dataset. This work establishes an end-to-end deep learning pipeline tailored for visual odometry in forested environments, leveraging forest-specific training data to optimise feature correspondence and pose estimation for improved accuracy and robustness in autonomous navigation systems.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2377-3766
2377-3766
DOI:10.1109/LRA.2025.3557738