Unified framework for precise vision-aided navigation

An apparatus for landmark recognition comprising:

• a plurality of cameras that capture a pair of stereo images comprising a view of one or more landmarks obtained by each of the plurality of cameras, where each camera in the plurality of cameras has different position measurement data comprising location, depth and pose as compared to position measurement data of each other camera;
• one or more processors, coupled to the plurality of cameras;
• and
• one or more storage devices with executable instructions stored thereon that when executed by the one or more processors perform a method comprising:
• computing a descriptor for each of the one or more landmarks based on the pair of stereo images;
• computing a landmark snapshot for each landmark of the one or more landmarks in the pair of stereo images, the landmark snapshot comprising the descriptor for the landmark combined with a spatial configuration for the landmark;
• and
• comparing between the landmark snapshot for each of the one or more landmarks in the pair of stereo images to identify corresponding landmarks in the pair of stereo images.