Video-based Heart Rate Estimation using Embedded Architectures

Monitoring a driver’s heart rate is an important determinant to his health condition. The monitoring system must be accurate and non restrictive the user’s actions. Estimating change in usual beat pattern can prevent undesirable outcomes. Several methods exist estimate without any contact. In this paper, we are focusing on method that uses remote photoplethysmography (rPPG). rPPG technique where extracted from PPG signal. signal changes blood flow corresponds color variations recorded through RGB camera. work, different study was based existing algorithm presented determine its processing time. proposed divided into global blocks each block functional (FBs). Though evaluating all blocks’ time, it possible most time consuming blocks. results implemented architectures: Desktop, Odroid XU4 Jetson Nano provide higher performance.