System and method for unmanned aerial vehicle navigation for inventory management
This disclosure relates generally to inventory management, and more particularly to system and method for airborne shelf inspection and inventor management. When a UAV has to be navigated based on navigation information embedded in visual markers on different items in the inventory, and if one or more of the visual markers are not completely visible due to occlusion, then the UAV automatically recovers data that is missing due to the occlusion, and accordingly navigates the UAV.
1. A processor-implemented method, comprising:
capturing, via one or more hardware processors, at least one image of visual marker on a target, by an image capturing module of the UAV;
determining, via the one or more hardware processors, whether entire area of the visual marker is covered in the captured image, by an image processing module of the UAV;
recovering, via the one or more hardware processors, missing area of the visual marker, if the entire area of the visual marker is found to be not visible in the captured image, by said image processing module; and
navigating the UAV automatically, via the one or more hardware processors, based on at least one data decoded from the visual marker after recovering the missing area of the visual marker, by a navigation module of the UAV.
2. The method as claimed in claim 1 , wherein said navigation of the UAV involves localization of the UAV within an environment where the UAV is present, wherein said localization comprises of:
generating a map of the environment, by an exploratory module of the UAV, by traversing entire area of the environment, wherein the map is generated in terms of position a plurality of visual markers in the environment; and
identifying location of the UAV, with respect to at least one visual marker in the proximity of the UAV and the map, by a localization module of the UAV.
3. The method as claimed in claim 1 , wherein recovering missing area of the visual marker further comprises of:
extracting parity codes corresponding to data being encoded in the visual marker, from the captured image, by the image processing module; and
calculating values of the missing area of the visual marker, based on the extracted parity codes, by the image processing module.
4. The method as claimed in claim 1 , wherein the visual marker is polygonal in shape, wherein the visual marker comprises of:
a binary code representing information pertaining to at least the target, within a plurality of borders of the polygon; and
a set of parity codes corresponding to the binary code, wherein said binary code is reconstructed from said set of parity codes when needed, said set of parity codes are encoded in blocks surrounding the binary code, within all borders of the polygon, wherein the parity codes adjacent to all borders of the polygon represent same values.
5. An Unmanned Aerial Vehicle (UAV), said UAV comprising:
a hardware processor; and
a storage medium comprising a plurality of instructions, said plurality of instructions causing the hardware processor to:
capture at least one image of visual marker on a target, by an image capturing module of the UAV;
determine whether entire area of the visual marker is covered in the captured image, by an image processing module of the UAV;
recover missing area of the visual marker, if the entire area of the visual marker is found to be not visible in the captured image, by said image processing module; and
navigate the UAV automatically, based on at least one data decoded from the visual marker after recovering the missing area of the visual marker, by a navigation module of the UAV.
6. The UAV as claimed in claim 5 , wherein said navigation module is configured to navigate the UAV based on localization of the UAV within an environment where the UAV is present, by:
generating a map of the environment, by an exploratory module of the UAV, by traversing entire area of the environment, wherein the map is generated in terms of position a plurality of visual markers in the environment; and
identifying location of the UAV, with respect to at least one visual marker in the proximity of the UAV and the map, by a localization module of the UAV.
7. The UAV as claimed in claim 5 , wherein the image processing module is configured to recover missing area of the visual marker by:
extract parity codes corresponding to data being encoded in the visual marker, from the captured image; and
calculate values of the missing area of the visual marker, based on the extracted parity codes, by the image processing module.
8. A non-transitory computer readable medium embodying a program executable in a computing device, the program comprising:
a program code for capturing, via one or more hardware processors, at least one image of visual marker on a target, by an image capturing module of the UAV;
determining, via the one or more hardware processors, whether entire area of the visual marker is covered in the captured image, by an image processing module of the UAV;
recovering, via the one or more hardware processors, missing area of the visual marker, if the entire area of the visual marker is found to be not visible in the captured image, by said image processing module; and
navigating the UAV automatically, via the one or more hardware processors, based on at least one data decoded from the visual marker after recovering the missing area of the visual marker, by a navigation module of the UAV.