HelixTrack: Event-Based Tracking and RPM Estimation of Propeller-like Objects

2026-03-10

AI Summary

This work addresses the challenge of accurately tracking high-speed rotating propeller-like objects and estimating their revolutions per minute (RPM) under microsecond-level latency, a task at which existing frame- or event-based methods struggle due to their reliance on smooth motion assumptions. The authors propose a fully event-driven approach that back-projects image-plane events onto the rotor plane via dynamic homography, integrates a Kalman filter for real-time phase estimation, and introduces a phase–geometry coupled batch iterative optimization framework to jointly achieve high-precision tracking and RPM estimation. Key contributions include the first event-driven method for simultaneous propeller tracking and microsecond-resolution RPM estimation, a novel phase–geometry coupled optimization framework, and the TQE dataset—the first to provide high-resolution event streams, ego-motion, and ground-truth RPM. Experiments demonstrate that the method processes full-rate events on TQE at 11.8× real-time speed, significantly outperforming existing baselines.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: State Estimation
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Safety-critical perception for unmanned aerial vehicles and rotating machinery requires microsecond-latency tracking of fast, periodic motion under egomotion and strong distractors. Frame-based and event-based trackers drift or break on propellers because periodic signatures violate their smooth-motion assumptions. We tackle this gap with HelixTrack, a fully event-driven method that jointly tracks propeller-like objects and estimates their rotations per minute (RPM). Incoming events are back-warped from the image plane into the rotor plane via a homography estimated on the fly. A Kalman Filter maintains instantaneous estimates of phase. Batched iterative updates refine the object pose by coupling phase residuals to geometry. To our knowledge, no public dataset targets joint tracking and RPM estimation of propeller-like objects. We therefore introduce the Timestamped Quadcopter with Egomotion (TQE) dataset with 13 high-resolution event sequences, containing 52 rotating objects in total, captured at distances of 2 m / 4 m, with increasing egomotion and microsecond RPM ground truth. On TQE, HelixTrack processes full-rate events (approx. 11.8x real time) faster than real time and microsecond latency. It consistently outperforms per-event and aggregation-based baselines adapted for RPM estimation.

Problem

• event-based tracking
• propeller-like objects
• RPM estimation
• microsecond latency
• periodic motion

Innovation

• event-based vision
• propeller tracking
• RPM estimation
• Kalman filter
• homography warping