AutoHR: A Strong End-to-end Baseline for Remote Heart Rate Measurement with Neural Searching

Abstract

Remote photoplethysmography (rPPG), which aims at measuring heart activities without any contact, has great potential in many applications (e.g., remote healthcare). Existing end-to-end rPPG and heart rate (HR) measurement methods from facial videos are vulnerable to the less-constrained scenarios (e.g., with head movement and bad illumination). In this letter, we explore the reason why existing end-to-end networks perform poorly in challenging conditions and establish a strong end-to-end baseline (AutoHR) for remote HR measurement with neural architecture search (NAS). The proposed method includes three parts: 1) a powerful searched backbone with novel Temporal Difference Convolution (TDC), intending to capture intrinsic rPPG-aware clues between frames; 2) a hybrid loss function considering constraints from both time and frequency domains; and 3) spatio-temporal data augmentation strategies for better representation learning. Comprehensive experiments are performed on three benchmark datasets to show our superior performance on both intra- and cross-dataset testing.

Submitted to IEEE Signal Processing Letters

References in corpus (2)

• RhythmNet: End-to-end Heart Rate Estimation from Face via Spatial-temporal Representation
• EVM-CNN: Real-Time Contactless Heart Rate Estimation from Facial Video

Cited by in corpus (5)

• NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofing
• Real-time Webcam Heart-Rate and Variability Estimation with Clean Ground Truth for Evaluation
• A Central Difference Graph Convolutional Operator for Skeleton-Based Action Recognition
• Non-contact PPG Signal and Heart Rate Estimation with Multi-hierarchical Convolutional Network
• Phase-shifted remote photoplethysmography for estimating heart rate and blood pressure from facial video