An apparatus for obtaining a vital sign of a subject includes: an image sensor and a vital sign processor. The image sensor is employed for capturing a video of the subject to generate a plurality of first video frames. The vital sign processor is employed for processing the plurality of first video frames to generate a vital sign signal. Additionally, the vital sign processor adjusts a first parameter set for configuring the image sensor to make the plurality of first video frames suitable for obtaining the vital sign of the subject.
