Method for the computer-aided recognition of a transport container being empty, control device and checkout terminal
A method for the computer-aided recognition of a transport container being empty can comprise: determining one or more than one segment of image data of the transport container using depth information assigned to the image data; assigning the image data to one from a plurality of classes, of which a first class represents the transport container being empty, and a second class represents the transport container being non-empty, wherein the one or more than one segment is not taken into account in the assigning; outputting a signal which represents the filtered image data being assigned to the second class.
1 . A method for the computer-aided recognition of a transport container being empty comprising:
determining one or more segments of an image data of the transport container using depth information that is assigned to the image data but is provided by a 3D camera separately from the image data itself and wherein the determined one or more segments do not belong to the transport container but rather to a background of the transport container;
filtering out and discarding the one or more segments from the image data determined during said determining before the image data is processed further whereby leaner processing algorithms during further processing;
assigning, after said filtering, the image data to one of a plurality of classes of which a first class represents the transport container being empty and a second class represents the transport container being non-empty, wherein the one or more segments is not taken into account during said assigning; and
outputting a signal which represents the image data being assigned to the second class.
2 . The method as claimed in claim 1 wherein said determining is further defined as:
determining the one or more segments of the image data of the transport container using depth information assigned to the image data but provided by a 3D camera separately from the image data, wherein the one or more segments is determined if the depth information assigned to the one or more segments satisfies a stored criterion.
3 . The method as claimed in claim 1 wherein the one or more segments of the image data is not taken into account in the assigning.
4 . The method as claimed in claim 1 wherein a contour of the transport container is freed by means of filtering.
5 . The method as claimed in claim 1 wherein the one or more segments represents a background of the transport container.
6 . The method as claimed in claim 1 wherein said outputting is further defined as:
outputting the signal which represents the image data being assigned to the second class and also comprises an instruction to put a checkout session into a standby state.
7 . The method as claimed in claim 6 wherein the checkout session further comprises:
determining a payment information on the basis of a product identifier; and
initiating a payment process on the basis of the payment information.
8 . The method as claimed in claim 1 wherein said outputting is further defined as:
outputting the signal which represents the image data being assigned to the second class and also comprises an instruction to display color information of the image data of the transport container.
9 . The method as claimed in claim 1 wherein said outputting is further defined as:
outputting the signal which represents the image data being assigned to the second class and also comprises an instruction to request a user input.
10 . The method as claimed in claim 1 wherein said outputting is further defined as:
outputting the signal which represents the image data being assigned to the second class and also comprises an instruction to output an alarm.
11 . The method as claimed in claim 1 wherein the image data comprises stereoscopic image data and the depth information is determined on the basis of the stereoscopic image data.
12 . The method as claimed in claim 1 wherein said assigning is further defined as:
assigning, after said filtering, the image data to one of a plurality of classes of which a first class represents the transport container being empty and a second class represents the transport container being non-empty, wherein the one or more segments is not taken into account during said assigning, and effected by means of an artificial neural network.