Selected work

Representative Papers

Autobiasing Event Cameras for Flickering Mitigation

Nov 04, 2025

Event cameras suffer from flicker-induced performance degradation under strobed illumination (25–500 Hz), where rapid intensity variations cause spurious event generation. To address this, we propose a real-time flicker suppression method that autonomously adapts the camera’s internal bias parameters—leveraging the event camera’s native programmable bias configuration without requiring additional hardware or post-processing filters. A lightweight CNN processes event streams online to identify spatial flicker patterns and dynamically optimize bias settings. Evaluated on YOLO-based face detection, our method significantly improves detection confidence and frame rate: edge gradient error decreases by 38.2% under bright illumination and by 53.6% in low-light conditions. These results demonstrate robustness and effectiveness across diverse lighting scenarios.

0 citationsRead paper

Contactless Cardiac Pulse Monitoring Using Event Cameras

May 14, 2025

This study addresses the limitations of conventional frame-based cameras—namely, restricted dynamic range and temporal resolution—in non-contact facial heart rate (HR) estimation. To overcome these constraints, we propose an event-camera-based approach that asynchronously maps sparse event streams into multi-rate 2D frames (30/60/120 FPS) and employs a supervised convolutional neural network (CNN) for end-to-end photoplethysmographic (PPG) signal regression. This work constitutes the first empirical validation that high-fidelity physiological information is intrinsically encoded in event data. Experimental results demonstrate that the 60 FPS and 120 FPS event-frame models achieve root-mean-square errors (RMSE) of 2.54 and 2.13 bpm, respectively—significantly outperforming the 30 FPS frame-camera baseline (2.92 bpm). The method further offers low latency and low power consumption, enabling robust, remote, and high-accuracy non-contact physiological monitoring.

0 citationsRead paper

Recent publications

Latest Papers

Autobiasing Event Cameras for Flickering Mitigation

Nov 04, 2025

Event cameras suffer from flicker-induced performance degradation under strobed illumination (25–500 Hz), where rapid intensity variations cause spurious event generation. To address this, we propose a real-time flicker suppression method that autonomously adapts the camera’s internal bias parameters—leveraging the event camera’s native programmable bias configuration without requiring additional hardware or post-processing filters. A lightweight CNN processes event streams online to identify spatial flicker patterns and dynamically optimize bias settings. Evaluated on YOLO-based face detection, our method significantly improves detection confidence and frame rate: edge gradient error decreases by 38.2% under bright illumination and by 53.6% in low-light conditions. These results demonstrate robustness and effectiveness across diverse lighting scenarios.

0 citationsRead paper

Contactless Cardiac Pulse Monitoring Using Event Cameras

May 14, 2025

This study addresses the limitations of conventional frame-based cameras—namely, restricted dynamic range and temporal resolution—in non-contact facial heart rate (HR) estimation. To overcome these constraints, we propose an event-camera-based approach that asynchronously maps sparse event streams into multi-rate 2D frames (30/60/120 FPS) and employs a supervised convolutional neural network (CNN) for end-to-end photoplethysmographic (PPG) signal regression. This work constitutes the first empirical validation that high-fidelity physiological information is intrinsically encoded in event data. Experimental results demonstrate that the 60 FPS and 120 FPS event-frame models achieve root-mean-square errors (RMSE) of 2.54 and 2.13 bpm, respectively—significantly outperforming the 30 FPS frame-camera baseline (2.92 bpm). The method further offers low latency and low power consumption, enabling robust, remote, and high-accuracy non-contact physiological monitoring.

0 citationsRead paper