Edged USLAM: Edge-Aware Event-Based SLAM with Learning-Based Depth Priors
Şebnem Sarıözkan, HÃ1⁄4rkan Şahin, Olaya Ãlvarez-TuñÃ3n, Erdal Kayacan
AI summary
Problem
Standard visual SLAM degrades under rapid motion, low light, or high dynamic range conditions, while event cameras alone struggle with sparse data integration and feature extraction for reliable mapping.
Approach
The system enhances motion-compensated event frames using edge-aware filtering and grid-based ORB tracking, while fusing coarse, learning-based depth estimates as soft constraints to stabilize scale and motion compensation.
Key results
- Novel edge-aware front-end boosts feature tracking in low-contrast and high-speed scenarios
- Lightweight depth module integration reduces scale drift and improves geometric consistency
- Achieves lowest average position RMSE (0.14 m) on the Event-Camera Dataset versus competing methods
- Demonstrates real-time, robust UAV navigation in cluttered, GPS-denied indoor environments
Why it matters
Enables reliable aerial navigation in hazardous or GPS-denied settings where conventional cameras fail, advancing safe autonomous drone operations.
Abstract
Conventional visual simultaneous localization and mapping (SLAM) algorithms often fail under rapid motion, low illumination, or abrupt lighting transitions due to motion blur and limited dynamic range. Event cameras mitigate these issues with high temporal resolution and high dynamic range (HDR), but their sparse, asynchronous outputs complicate feature extraction and integration with other sensors, e.g., inertial measurement units (IMUs) and standard cameras. We present Edged USLAM, a hybrid visual–inertial system that extends Ultimate SLAM (USLAM) with an edge-aware front-end and a lightweight depth module. The front-end enhances event frames for robust feature tracking and nonlinear motion compensation, while the depth module provides coarse, region-of-interest (ROI)-based scene depth to improve motion compensation and scale consistency. Evaluations across public benchmarks and real-world unmanned air vehicle (UAV) flights demonstrate that performance varies significantly by scenario. For instance, event-only methods like point–line event-based visual–inertial odometry (PL-EVIO) or learning-based pipelines such as deep event-based visual odometry (DEVO) excel in highly aggressive or extreme HDR conditions. In contrast, Edged USLAM provides superior stability and minimal drift in slow or structured trajectories, ensuring consistently accurate localization on real flights under challenging illumination. These findings highlight the complementary strengths of event-only, learning-based, and hybrid approaches, while positioning Edged USLAM as a robust solution for diverse aerial navigation tasks.