This paper presents a dual-modal (RGB/NIR) technique to estimate remote Plethysmogram (rPPG) signal, or, the heart rate, from facial image sequence. We developed denoising techniques with a modified amplitude selective filtering (ASF), wavelets decomposition and robust principal component analysis (RPCA), to enhance the uncovering of the rPPG signal through the well-known ICA algorithm. A new dataset built with RealSense RGB-D camera is considered in experiments: regular brightness, under-illumination, and face motion. Experimental results show that the proposed method has reached competitive performances among the state-of-the-art methods in motion and under-illuminated scenarios even at a shorter input video length (10-20 seconds).