Asynchronous Event Stream Noise Filtering for High-frequency Structure Deformation Measurement

2025-12-16

AI Summary

To address challenges in high-frequency structural deformation measurement—including severe illumination interference, high cost of conventional high-speed cameras, and substantial noise in LED-marker event streams—this paper proposes a monocular measurement method based on event cameras. The approach innovatively integrates LED blinking priors with a motion–blinking event decoupling mechanism to construct a spatiotemporal correlation model for event streams, enabling asynchronous noise suppression and separation of motion-induced and blinking-related events. Combined with monocular geometric calibration and deformation inversion algorithms, it achieves robust LED marker extraction and sub-millisecond deformation reconstruction. Experimental results demonstrate a localization accuracy of ±0.3 pixels under strong ambient illumination and successful planar deformation measurement up to 500 Hz. Compared to traditional high-speed camera solutions, the proposed method reduces hardware cost by 90% while maintaining measurement fidelity and temporal resolution.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Hardware-aware ML

Application Category

• Security and Privacy: Large-scale security measurements
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization

Abstract

Large-scale structures suffer high-frequency deformations due to complex loads. However, harsh lighting conditions and high equipment costs limit measurement methods based on traditional high-speed cameras. This paper proposes a method to measure high-frequency deformations by exploiting an event camera and LED markers. Firstly, observation noise is filtered based on the characteristics of the event stream generated by LED markers blinking and spatiotemporal correlation. Then, LED markers are extracted from the event stream after differentiating between motion-induced events and events from LED blinking, which enables the extraction of high-speed moving LED markers. Ultimately, high-frequency planar deformations are measured by a monocular event camera. Experimental results confirm the accuracy of our method in measuring high-frequency planar deformations.

Problem

• Filters noise from event streams for structural deformation measurement
• Extracts LED markers from event streams to track high-speed motion
• Measures high-frequency planar deformations using a monocular event camera

Innovation

• Event camera filters noise via spatiotemporal correlation
• Differentiates motion and LED events for marker extraction
• Monocular event camera measures high-frequency planar deformations