Embodiments of the disclosure relate generally to automatic focus selection in a multi-imager environment. Embodiments include methods, systems, and apparatuses configured for capturing by a first image sensor, a first image of a visual object with a background associated with a subject. A characteristic difference between the visual object in the first image and the background in the first image is determined and a distance determination mode is selected based on the determined characteristic difference. Accordingly, a distance to the subject is calculated based on the selected distance determination mode and a second image sensor is controlled to capture a second image of the subject, based on the calculated distance to the subject.