Video Photoplethysmography (vPPG) allows for estimation of blood volume pulse (BVP) from the skin by means of a video camera recording at high frequency rate. The estimation procedure presents several drawbacks in its application to real world conditions, such as light changes or movements that often generate artifacts in the extracted BVP waveform. In addition, the process requires a skin segmentation algorithm to distinguish skin pixels from the background. To date, even the most refined skin segmentation algorithms still need a manual definition that could lead to incorrect pixel classification, and consequently to a decrease in the signal-to-noise ratio (SNR). We here propose a fully autonomic procedure able to extract BVP from video recordings of the skin in real world conditions.The experimental protocol is designed to record the signals of interest and to evaluate changes in the Autonomic Nervous System modulation of the heart during a baseline condition and a controlled breathing phase. Video recordings are gathered from 4 young healthy subjects (age: 21±1 years). vPPG signals are processed in order to extract the BVP waveform, and a peak detection algorithm detects pulse wave peaks that are then used to compute specific measures of heart rate variability (HRV).The procedure is successfully validated by comparing the extracted HRV measures against those extracted using a finger photoplethysmograph (fPPG) using three different skin segmentation algorithms from BVP signals.