Heart rate is a strong indicator of a person’s psychophysiological state. For this reason, many applications would benefit from the ability to measure noncontact heart rate. The present work describes a new procedure for estimating blood volume pulse from video of a person’s face, with an emphasis on real-life scenarios like driving. The approach builds on the algorithm known as Eulerian VidMag, which has shown promise under laboratory conditions, but exhibits problems when applied in naturalistic situations. In particular, problems arise due to movement by the subject, changing illumination conditions, and low-frame-rate video. This work describes methods developed to address some of these problems, including working with video rates down to 10 frames per second. The methods were tested using videos of indoor subjects, as well as videos of drivers in naturalistic situations. We assessed the method through analysis of different stress levels using the extracted heart rate information for a driver on the road by comparing heart rate variability at different stress levels. Experiments showed that a systematic post-processing strategy can improve the accuracy of the VidMag algorithm’s raw output and achieve a good correlation in both instantaneous heart rate and average heart rate with the ground truth heart rate measurements. This, in particular, improves with higher quality video sources and more controlled experimental conditions. However, the robust broad application of the methods on existing lower-quality naturalistic video data remains a challenge.