Systems and methods for an enhanced computer vision module are presented. The system receives host locating information, and determines a position and a location of the host based on the host locating information. The system determines a field of view (FOV) of the host based on the host locating information, and controls a camera associated with the host that is configured to record a video stream comprising the FOV. The system and method provide an improvement over conventional computer vision (CV) systems by utilizing object locating information that is transmitted, and also by keeping a storage table of learned and fixed objects. The provided system and method improve the efficiency of object recognition and computer aided maintenance (CAM).