A method of analyzing objects in images recorded by a camera of a head mounted device is disclosed. The method comprises performing eye tracking while recording the images; determining a region of interest of an image based upon the eye tracking; generating a bounding box based upon the region of interest; cropping an image based upon the bounding box to generate a cropped image; performing a fine cropping of the cropped image; and detecting an object in the cropped image. An electronic device for analyzing objects in images recorded by a camera of a head mounted device is also disclosed.