Geometry-Aware Visual Odometry for Bronchoscopic Navigation via High-Gain Observer Fusion

2026-07-06

AI Summary

This work addresses the challenge of visual odometry failure and drift in bronchoscopic navigation, caused by texture-poor airways, specular reflections, and vanishing point singularities inherent to tubular structures. The authors propose a geometry-aware visual odometry framework that uniquely integrates airway geometric priors with a high-gain observer. Specifically, the method leverages the tubular vanishing point to yield a stable forward heading, estimates ego-motion velocity using looming cues, and fuses noisy visual odometry outputs through a high-gain observer to suppress drift. Notably, the approach operates without CT scans or external sensors and maintains robust localization even under minimal parallax. Experiments on ex vivo human lungs demonstrate that the proposed method reduces absolute trajectory error by over 50% compared to state-of-the-art approaches such as ORB-SLAM2, LoFTR-VO, and DPVO, while achieving the lowest relative pose error across all tested sequences.

Abstract

Navigational bronchoscopy is critical for pulmonary interventions, yet current platforms depend heavily on pre-operative CT or external sensors, limiting their use in critical care and resource-constrained settings. Vision-only navigation offers a scalable alternative, but conventional visual odometry (VO) struggles with texture-poor airway images, specularities, and the vanishing-point singularities of tubular anatomy, leading to frequent tracking failures and drift. We present a geometry-aware VO framework that explicitly leverages vanishing-point cues from airway lumens. Detected lumens are back-projected to 3D rays, whose weighted fusion yields a stable forward heading even when parallax cues are absent. This heading, together with looming-based velocity estimates, is fused with noisy VO outputs using a bespoke high-gain observer that enforces airway-following priors and rejects drift. We validate the method on ex-vivo mechanically ventilated human lungs with electromagnetic tracking ground truth. Compared to state-of-the-art pipelines (ORB-SLAM2, LoFTR-VO, DPVO), our approach reduces absolute trajectory error by more than 50% and achieves the lowest relative pose error across all test sequences.

Problem

• visual odometry
• bronchoscopic navigation
• texture-poor images
• vanishing-point singularities
• tracking failure

Innovation

• geometry-aware visual odometry
• vanishing-point cues
• high-gain observer
• bronchoscopic navigation
• airway lumen