AutoHR: A Strong End-to-end Baseline for Remote Heart Rate Measurement with Neural Searching
| Autor: | Guoying Zhao, Jingang Shi, Xiaobai Li, Zitong Yu, Xuesong Niu |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
business.industry Computer science Applied Mathematics Computer Vision and Pattern Recognition (cs.CV) RPPG Computer Science - Computer Vision and Pattern Recognition 020206 networking & telecommunications Pattern recognition 02 engineering and technology Convolution neural architecture search Heart rate measurement End-to-end principle Photoplethysmogram Signal Processing Heart rate heart rate 0202 electrical engineering electronic engineering information engineering Benchmark (computing) Artificial intelligence Electrical and Electronic Engineering business Baseline (configuration management) |
| DOI: | 10.48550/arxiv.2004.12292 |
| Popis: | 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. Comment: Submitted to IEEE Signal Processing Letters |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|