Object recognition apparatus and object recognition method
The present invention comprises: an input unit that enters scene information indicating the state of a prescribed scene in a container that stores an object; a processing unit that, on the basis of the scene information entered into the input unit, sorts objects in the container by size and, on the basis of the number of sorted objects of different sizes, detects objects of sizes that are not acceptable for storage in the container; and an output unit that outputs the results of processing by the processing unit.
1 . An object recognition apparatus comprising:
an input unit configured to input scene information indicating a state of a predetermined scene in a container that stores an object;
a processing unit configured to execute processing of selecting an object present in the container for each size based on the scene information received from the input unit, and detecting an object having a size unallowable for storage in the container based on the number of selected objects for each size; and
an output unit configured to output a result of the processing executed by the processing unit;
wherein a size of the object present in the container is a combination of values of parameters representing an original shape of the object;
wherein the processing unit selects the object present in the container for each combination of the values of the parameters representing the original shape of the object based on the scene information received from the input unit; and
wherein the processing unit creates a histogram indicating a frequency distribution of the object present in the container according to a predetermined range set for each parameter representing the original shape of the object and determined to have the same parameter value, and detects the object having the size unallowable for storage in the container based on the number of elements in each bin of the created histogram.
2 . The object recognition apparatus according to claim 1 , wherein
the scene information received from the input unit includes at least one of a color image, a point group, a depth image, and a grayscale image, and
the processing unit estimates the size of the object present in the container based on the scene information received from the input unit and selects the object present in the container for each size based on the estimated size of the object.
3 . The object recognition apparatus according to claim 1 , wherein
the scene information received from the input unit includes sensor information on a state of the container acquired by a sensor, and
the processing unit estimates the size of the object present in the container based on the sensor information included in the scene information received from the input unit and selects the object present in the container for each size based on the estimated size of the object.
4 . The object recognition apparatus according to claim 3 , wherein
the processing unit estimates the values of the parameters representing the original shape of the object as the size of the object present in the container based on the sensor information included in the scene information received from the input unit.
5 . The object recognition apparatus according to claim 4 , wherein
the processing unit estimates a posture of the object using the estimated size of the object, and
the output unit outputs the size of the object and the posture of the object that are estimated by the processing unit.
6 . The object recognition apparatus according to claim 5 , wherein
the processing unit estimates the posture of the object by aligning the estimated size of the object with a model of the original shape of the object.
7 . The object recognition apparatus according to claim 1 , wherein
the scene information received from the input unit includes sensor information on a state of the container acquired by a sensor, and
the processing unit estimates the size of the object and a posture of the object by repeatedly executing fitting between a model of the original shape of the object and an object point group obtained by cutting out the object from the sensor information included in the scene information received from the input unit, and adjustment of values of parameters of the model of the original shape of the object.
8 . The object recognition apparatus according to claim 1 , wherein
the output unit outputs information indicating the object having the size unallowable for storage in the container, the object being detected by the processing unit.
9 . The object recognition apparatus according to claim 1 , wherein
the input unit inputs presence information indicating the number of types of objects present in the container, and
the processing unit detects the object having the size unallowable for storage in the container based on the presence information.
10 . The object recognition apparatus according to claim 1 , wherein
the parameters representing the original shape of the object are length, width, and height, or length and width when the original shape of the object is a box shape, and are radius and height, radius, or height when the original shape of the object is a cylindrical shape.
11 . An object recognition method comprising:
inputting, by an input unit, scene information indicating a state of a predetermined scene in a container that stores an object;
executing, by a processing unit, processing of selecting an object present in the container for each size based on the scene information received from the input unit, and detecting an object having a size unallowable for storage in the container based on the number of selected objects for each size; and
outputting, by an output unit, a result of the processing executed by the processing unit;
wherein a size of the object present in the container is a combination of values of parameters representing an original shape of the object;
wherein the processing unit selects the object present in the container for each combination of the values of the parameters representing the original shape of the object based on the scene information received from the input unit; and
wherein the processing unit creates a histogram indicating a frequency distribution of the object present in the container according to a predetermined range set for each parameter representing the original shape of the object and determined to have the same parameter value, and detects the object having the size unallowable for storage in the container based on the number of elements in each bin of the created histogram.