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

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

URL: http://arxiv.org/abs/2004.12292v1
Date: Sun, 26 Apr 2020 05:43:21 GMT
Title: AutoHR: A Strong End-to-end Baseline for Remote Heart Rate Measurement with Neural Searching
Authors: Zitong Yu, Xiaobai Li, Xuesong Niu, Jingang Shi, Guoying Zhao
Abstract summary: We investigate the reason why existing end-to-end networks perform poorly in challenging conditions and establish a strong baseline for remote HR measurement with architecture search (NAS) Comprehensive experiments are performed on three benchmark datasets on both intra-temporal and cross-dataset testing.
Score: 76.4844593082362
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
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.