Method and apparatus for creating map and positioning moving entity
Exemplary embodiments of the present disclosure provide a method, apparatus and computer readable storage medium for creating a map and positioning a moving entity. A method for creating a map includes acquiring an image acquired when an acquisition entity is moving and location data and point cloud data associated with the image, the location data indicating a location where the acquisition entity is located when the image is acquired, the point cloud data indicating three-dimensional information of the image. The method further includes generating a first element in a global feature layer of the map based on the image and the location data. The method further includes generating a second element in a local feature layer of the map based on the image and the point cloud data, the first element corresponding to the second element.
1. A method for creating a map, the method comprising:
acquiring an image acquired when an acquisition entity is moving and location data and point cloud data associated with the image, the location data indicating a location where the acquisition entity is located when the image is acquired, and the point cloud data indicating three-dimensional information of the image;
extracting a global feature of the image, the global feature representing an overall attribute of the image and comprising a spatial envelope of the image; and associating the location data with the global feature to generate a first element in a global feature layer of the map; and
extracting a local feature of the image, the local feature representing an attribute related to an area around a pixel in the image; extracting three-dimensional information associated with the local feature from the point cloud data; and associating the local feature with the three-dimensional information to generate a second element in a local feature layer of the map, the first element corresponding to the second element.
2. The method according to claim 1 , wherein the acquiring the image, the location data and the point cloud data comprises:
acquiring the image acquired by a camera arranged in association with the acquisition entity;
acquiring the location data of the acquisition entity, the location data being acquired by a position sensor in synchronization with acquiring the image by the camera; and
acquiring the point cloud data, the point cloud data being acquired by a laser radar in synchronization with acquiring the image by the camera.
3. The method according to claim 1 , the method comprising:
acquiring a second image acquired when an moving entity is moving;
acquiring second location data regarding a location where the moving entity is located when the second image is acquired; and
positioning the moving entity based on the second image, the second location data, and the map.
4. The method according to claim 3 , wherein the positioning the moving entity comprises:
extracting a global feature and a local feature of the second image, the global feature representing an overall attribute of the second image, the local feature representing an attribute related to a part of the second image;
determining a set of candidate elements from the global feature layer of the map based on the second location data of the moving entity;
determining, from the set of candidate elements, a global matching element matching the global feature;
determining, from a local feature layer of the map, a local matching element corresponding to the global matching element;
determining three-dimensional information associated with the local feature based on the local matching element; and
positioning the moving entity based on the three-dimensional information.
5. The method according to claim 3 , further comprising:
acquiring a planned path of the moving entity; and
downloading a portion of the map associated with the planned path.
6. The method according to claim 3 , wherein the acquiring the second image comprises:
acquiring the second image acquired by a camera arranged in association with the moving entity.
7. The method according to claim 6 , wherein the acquiring second location data of the moving entity comprises:
acquiring the second location data of the acquisition entity, the second location data being acquired by a position sensor in synchronization with acquiring the image by the camera.
8. An apparatus for creating a map, the apparatus comprising:
at least one processor; and
a memory storing instructions, wherein the instructions when executed by the at least one processor, cause the at least one processor to perform operations, the operations comprising:
acquiring an image acquired when an acquisition entity is moving and location data and point cloud data associated with the image, the location data indicating a location where the acquisition entity is located when the image is acquired, and the point cloud data indicating three-dimensional information of the image;
extracting a global feature of the image, the global feature representing an overall attribute of the image and comprising a spatial envelope of the image; and associating the location data with the global feature to generate a first element in a global feature layer of the map; and
extracting a local feature of the image, the local feature representing an attribute related to an area around a pixel in the image; extracting three-dimensional information associated with the local feature from the point cloud data; and associating the local feature with the three-dimensional information to generate a second element in a local feature layer of the map, the first element corresponding to the second element.
9. The apparatus according to claim 8 , wherein the acquiring the image, the location data and the point cloud data comprises:
acquiring the image acquired by a camera arranged in association with the acquisition entity;
acquiring the location data of the acquisition entity, the location data being acquired by a position sensor in synchronization with acquiring the image by the camera; and
acquiring the point cloud data, the point cloud data being acquired by a laser radar in synchronization with acquiring the image by the camera.
10. The apparatus according to claim 8 , wherein the operations comprise:
acquiring a second image acquired when an moving entity is moving;
acquiring second location data regarding a location where the moving entity is located when the second image is acquired; and
positioning the moving entity based on the second image, the second location data, and the map.
11. The apparatus according to claim 10 , wherein the positioning the moving entity comprises:
extracting a global feature and a local feature of the second image, the global feature representing an overall attribute of the second image, the local feature representing an attribute related to a part of the second image;
determining a set of candidate elements from the global feature layer of the map based on the second location data of the moving entity;
determining, from the set of candidate elements, a global matching element matching the global feature;
determining, from a local feature layer of the map, a local matching element corresponding to the global matching element;
determining three-dimensional information associated with the local feature based on the local matching element; and
positioning the moving entity based on the three-dimensional information.
12. The apparatus according to claim 10 , wherein the operations further comprise:
acquiring a planned path of the moving entity; and
downloading a portion of the map associated with the planned path.
13. The apparatus according to claim 10 , wherein the acquiring the second image comprises:
acquiring the second image acquired by a camera arranged in association with the moving entity.
14. The apparatus according to claim 13 , wherein the acquiring second location data of the moving entity comprises:
acquiring the second location data of the acquisition entity, the second location data being acquired by a position sensor in synchronization with acquiring the image by the camera.
15. A non-transitory computer storage medium, storing a computer program thereon, the computer program, when executed by a processor, cause the processor to perform operations, the operations comprising:
acquiring an image acquired when an acquisition entity is moving and location data and point cloud data associated with the image, the location data indicating a location where the acquisition entity is located when the image is acquired, and the point cloud data indicating three-dimensional information of the image;
extracting a global feature of the image, the global feature representing an overall attribute of the image and comprising a spatial envelope of the image; and associating the location data with the global feature to generate a first element in a global feature layer of the map; and
extracting a local feature of the image, the local feature representing an attribute related to an area around a pixel in the image; extracting three-dimensional information associated with the local feature from the point cloud data; and associating the local feature with the three-dimensional information to generate a second element in a local feature layer of the map, the first element corresponding to the second element.
16. The non-transitory computer storage medium, wherein the operations comprise:
acquiring a second image acquired when an moving entity is moving;
acquiring second location data regarding a location where the moving entity is located when the second image is acquired; and
positioning the moving entity based on the second image, the second location data, and the map.