Touchless photo capture in response to detected hand gestures

An image capture system, comprising:

• an eyewear device comprising a processor, a memory, an image processing system, a localization system, and a display;
• programming in the memory, wherein execution of said programming by the processor configures the eyewear device to perform functions, including functions to:
• capture frames of video data of a physical environment with a camera system, wherein each frame of video data comprises depth information for a plurality of pixels;
• determine an eyewear location relative to the physical environment with the localization system;
• detect a hand shape in the captured frames of video data with the image processing system;
• determine whether the detected hand shape in a first frame matches a shutter gesture;
• select a subset of the captured frames of video data, the subset comprising one or more frames immediately preceding and following the first frame;
• identify, from among the subset, one or more capture frames that do not include the detected hand shape;
• and
• present on the display a captured still image of the physical environment, wherein the captured still image is selected from one of the identified one or more capture frames.

A non-transitory computer-readable medium storing program code which, when executed, is operative to cause an electronic processor to perform the steps of:

• capturing frames of video data of a physical environment with a camera system, wherein each frame of video data comprises depth information for a plurality of pixels, and wherein the camera system is coupled to an eyewear device comprising a processor, a memory, an image processing system, and a localization system;
• determining an eyewear location relative to the physical environment with the localization system;
• detecting a hand shape in the captured frames of video data with the image processing system;
• determining whether the detected hand shape in a first frame matches a shutter gesture;
• selecting a subset of the captured frames of video data, the subset comprising one or more frames immediately preceding and following the first frame;
• identifying, from among the subset, one or more capture frames that do not include the detected hand shape;
• and
• presenting on a display a captured still image of the physical environment, wherein the captured still image is selected from one of the identified one or more capture frames.