Problem
Research questions and friction points this paper is trying to address.
Remote photoplethysmography
In-vehicle monitoring
High dynamic range
Exposure control
Signal degradation
Pixel-wise Exposure for Highly Robust In-Vehicle Remote-PPG
🤖 AI Summary
This study addresses the challenge of facial overexposure or underexposure caused by global exposure in high dynamic range (HDR) vehicular environments, which severely degrades remote photoplethysmography (rPPG) signals and compromises heart rate monitoring. We propose PixExpo, a novel framework that introduces a pixel-level exposure fusion mechanism trading temporal resolution for spatial dynamic range. By sequentially cycling through exposures to capture multiple frames and performing non-iterative, rPPG-target-intensity-guided pixel-level fusion, this method overcomes the physical limitations of conventional auto-exposure without requiring sensor hardware modifications, thereby preserving signal integrity at the source. Evaluated on the real-world driving dataset MEX-Drive, PixExpo reduces the mean absolute error to 6.73 bpm and increases the monitoring success rate to 63.24% (+37.29%), significantly outperforming manufacturer default exposure schemes.
📝 Abstract
Remote photoplethysmography (rPPG) offers a promising non-contact solution for heart rate monitoring, yet its real-world robustness is fundamentally limited by an inherent hardware limitation: existing camera exposure control paradigms, whether fixed or auto-exposure, impose a uniform exposure time across all pixels within a frame. In high-dynamic-range scenes such as automotive cabins with strong directional sunlight, this spatially invariant exposure constraint inevitably leads to localized facial overexposure or underexposure, irreversibly corrupting the subtle pulsatile signals essential for rPPG at the point of capture, a physical degradation that no downstream algorithm can recover. To overcome this bottleneck, we propose PixExpo (Pixel-wise Exposure), a "temporal-for-spatial" framework that sequentially captures frames under a predefined cyclic exposure schedule and performs non-iterative pixel-wise fusion. At each pixel location, PixExpo selects the observation closest to an rPPG-motivated target intensity. This criterion seeks to reduce local saturation and severe underexposure rather than optimize perceptual appearance. PixExpo requires no sensor modification but assumes programmable frame-level exposure control. We validate the proposed PixExpo framework using our newly introduced MEX-Drive dataset, comprising 48 participants under real-world driving conditions. Experimental results demonstrate that PixExpo outperforms manufacture-default auto-exposure methods, reducing the mean absolute error (MAE) by 7.21 bpm (from 13.94 to 6.73 bpm) and increasing the success rate by 37.29 percentage points (from 25.95% to 63.24%) across challenging driving scenarios.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Pixel-wise Exposure
Remote Photoplethysmography (rPPG)
High Dynamic Range
Temporal-for-Spatial Fusion
In-Vehicle Monitoring
🔎 Similar Papers
No similar papers found.
