Method and apparatus for visual positioning based on mobile edge computing

A mobile edge computing (MEC) node comprising:

• at least one processor;
• and
• a memory in communication with the at least one processor;
• wherein, the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform operations, the operations comprising:
• receiving, an environmental image captured by a to-be-positioned device in an area covered by the MEC node;
• determining by using an approximate nearest neighbor search algorithm, a target image matching the environment image from a plurality of candidate images pre-stored in the MEC node, wherein the MEC node pre-stores the plurality of candidate images and a plurality of pieces of position and pose information of a device capturing the plurality of candidate images;
• finding, by using a best-bin-first algorithm, a plurality of pairs of matching feature points from image features of the environment image and image features of the target image, to form a feature point pair set;
• calculating position and pose information of the to-be-positioned device based on the feature point pair set and position and pose information of a device at a time that the target image was captured by the device;
• and
• sending the position and pose information of the to-be-positioned device to the to-be-positioned device, so that the to-be-positioned device determines positioning information in an electronic map according to the position and pose information.

A non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform operations, the operations comprising:

• receiving, by a MEC node, an environmental image captured by a to-be-positioned device in an area covered by the MEC node;
• determining, by the MEC node and by using an approximate nearest neighbor search algorithm, a target image matching the environment image from a plurality of candidate images pre-stored in the MEC node, wherein the MEC node pre-stores the plurality of candidate images and a plurality of pieces of position and pose information of a device capturing the plurality of candidate images;
• finding, by using a best-bin-first algorithm, a plurality of pairs of matching feature points from image features of the environment image and image features of the target image, to form a feature point pair set;
• calculating position and pose information of the to-be-positioned device based on the feature point pair set and position and pose information of a device at a time that the target image was captured by the device;
• and
• sending, by the MEC node, the position and pose information of the to-be-positioned device to the to-be-positioned device, so that the to-be-positioned device determines positioning information in an electronic map according to the position and pose information.