Object recognition device that determines overlapping states for a plurality of objects
An object recognition device according to an embodiment includes a camera that captures an image of an imaging area. A storage device stores, for each of a plurality of registered objects, dictionary feature information for identifying the corresponding object and dictionary boundary information for identifying an actual boundary area of the corresponding object. A processor receives the captured image from the camera, and determines an object area in the captured image. The processor extracts feature information from the object area, and, based on the extracted feature information compared to the dictionary feature information, identifies each object included in the object area. The processor also extracts boundary information corresponding to each identified object included in the object area, and, based on the extracted boundary information compared to the dictionary boundary information with respect to each identified object, determines an overlap state of each identified object in the object area.
1. An object recognition device comprising:
a camera configured to capture an image of an imaging area including an object position area;
a storage device that stores, for each of a plurality of registered objects, dictionary feature information for identifying the corresponding object and dictionary boundary information for identifying an actual boundary area of the corresponding object; and
a processor configured to:
receive the captured image from the camera,
determine an object area in the captured image,
extract feature information from the object area,
based on the extracted feature information compared to the dictionary feature information, identify each object included in the object area,
extract boundary information corresponding to each identified object included in the object area,
based on the extracted boundary information compared to the dictionary boundary information with respect to each identified object, determine an overlap state of each identified object relative to additional objects in the object area,
based on the determined overlap state of each identified object, determine whether two or more identified objects in the object area are portions of the same object, and
perform a settlement processing for a transaction with respect to each identified object, wherein two or more identified objects that are determined to be portions of the same object are treated as a single identified object in the transaction.
2. The device according to claim 1 , the processor being further configured to:
determine a distance between a reference point and a target object in the imaging area, the object area being determined based on the determined distance.
3. The device according to claim 2 , wherein the processor determines a plurality of object areas based on the determined distance.
4. The device according to claim 3 , wherein the processor identifies a number of objects equal to the number of determined object areas.
5. The device according to claim 3 , the processor being further configured to:
determine whether two or more identified objects are the same type of object, wherein the determination of whether two or more identified objects in the object area are portions of the same object is further based on whether the two or more identified objects are the same type of object.
6. The device according to claim 2 , further comprising:
a distance sensor configured to generate a range image indicating a distance from the reference point to each object included in the object position area, wherein the processor receives the range image and determines the distance between the reference point and the target object based on the range image.
7. The device according to claim 6 , wherein the distance sensor includes a lens that is shared with the camera.
8. The device according to claim 1 , wherein the dictionary boundary information is information indicating at least a portion of a contour of the corresponding object.
9. The device according to claim 8 , wherein the dictionary boundary information further indicates, with respect to each registered object, a positional dependence relationship with respect to the dictionary feature information and the contour.
10. The device according to claim 9 , wherein the processor identifies each object included in the object area further based on the positional dependence relationship.
11. An object recognition method comprising the steps of:
storing, for each of a plurality of registered objects, dictionary feature information for identifying the corresponding object and dictionary boundary information for identifying an actual boundary area of the corresponding object;
capturing an image of an imaging area including an object position area;
determining an object area in the captured image;
extracting feature information from the object area;
based on the extracted feature information compared to the dictionary feature information, identifying each object included in the object area;
extracting boundary information corresponding to each identified object included in the object area;
based on the extracted boundary information compared to the dictionary boundary information with respect to each identified object, determining an overlap state of each identified object relative to additional objects in the object area;
based on the determined overlap state of each identified object, determining whether two or more identified objects in the object area are portions of the same object; and
performing a settlement processing for a transaction with respect to each identified object, wherein two or more identified objects that are determined to be portions of the same object are treated as a single identified object in the transaction.
12. The method according to claim 11 , further comprising the step of:
determining a distance between a reference point and a target object in the imaging area, the object area being determined based on the determined distance.
13. The method according to claim 12 , wherein a plurality of object areas are each determined based on the determined distance.
14. The method according to claim 13 , wherein a number of identified objects is equal to the number of determined object areas.
15. The method according to claim 13 , further comprising the step of:
determining whether two or more identified objects are the same type of object, wherein the determination of whether two or more identified objects in the object area are portions of the same object is further based on whether the two or more identified objects are the same type of object.
16. The method according to claim 12 , further comprising:
generating a range image indicating a distance from the reference point to each object included in the object position area, wherein the distance between the reference point and the target object is determined based on the range image.
17. The method according to claim 16 , wherein:
a distance sensor generates the range image,
a camera generates the image of the imaging area, and
the distance sensor and the camera share a lens.
18. The method according to claim 11 , wherein the dictionary boundary information is information indicating at least a portion of a contour of the corresponding object.
19. The method according to claim 18 , wherein the dictionary boundary information further indicates, with respect to each registered object, a positional dependence relationship with respect to the dictionary feature information and the contour.
20. The method according to claim 19 , wherein each object included in the object area is identified further based on the positional dependence relationship.