If you're looking to pick out small details or recognise objects in images, your go-to tool has always been the human eye. There are even platforms like Zooniverse that help scientists recruit large numbers of volunteers online to review images, combining the ability of humans to pick out features in images with the scale that usually only machines can achieve.
However, computer vision is fast catching up with our capabilities. And for some specific visual tasks, technology now far surpasses the human eye. A recent research paper outlines new techniques for machines to estimate the heart rate of humans from video footage, claiming to significantly outperform existing methods. Imagine a live broadcast of a political speech, with an accompanying live data feed on the politician's heart rate from AI interpretation of the footage - a feat no human eye could achieve. The potential for super-human machine vision and AI could have transformative impacts on a wide range of industries, from self-driving cars to industrial safety inspections, and I'm excited to find the startups that will take advantage of this.
Recent studies in computer vision have shown that, while practically invisible to a human observer, skin color changes due to blood flow can be captured on face videos and, surprisingly, be used to estimate the heart rate (HR).