Systems and processes are provided to identify a first camera model associated with a first video capture device of video capture devices within a system that aggregates video feeds from the video capture devices. A process includes receiving, by the video processing device, a first video sample from the first video capture device; sending, from the video processing device, a first command to the first video capture device; receiving, by the video processing device, a second video sample from the first video capture device subsequent to the sending of the first command; evaluating, by the video processing device, the first video sample and the second video sample in view of the first command to identify a first command response; and determining the first camera model based on the identified first command response.