Loaded attitude state detecting device
The loaded attitude state detecting device 10 includes a camera 11 that acquires loaded attitude image data D of pallets 4 and cargos 5 , an area extracting unit 15 that extracts areas of the pallets 4 and the cargos 5 in the loaded attitude image data D, and a loaded attitude abnormality determining unit 16 that determines whether or not the detection target pallet 4 interferes with the pallet 4 neighboring in the lateral direction based on the areas of the pallets 4 in the loaded attitude image data D, and determines whether or not the detection target cargo 5 interferes with the cargo 5 or the pallet 4 neighboring in the lateral direction based on the areas of the pallets 4 and the cargos 5 in the loaded attitude image data D.
1 . A loaded attitude state detecting device configured to detect loaded attitude states of a plurality of pallets and cargos when a forklift performs loading/unloading in a state where the cargos are placed on the pallets aligned and disposed in a lateral direction seen from the forklift, the loaded attitude state detecting device comprising:
at least one processor and a memory storing a program executed by the one or more processors, wherein the processors are configured to:
acquire loaded attitude detection data of the pallets and the cargos by detecting loaded attitudes of the pallets and the cargos;
extract areas of the pallets and the cargos in the loaded attitude detection data;
determine whether or not a detection target pallet interferes with a pallet neighboring in the lateral direction based on the areas of the pallets in the loaded attitude detection data;
determine whether or not a detection target cargo interferes with a cargo or a pallet neighboring in the lateral direction based on the areas of the pallets and the cargos in the loaded attitude detection data;
create, along the lateral direction, a plurality of sets of cargo sets indicating areas including the pallets and the cargos that are in contact with each other in an upper-lower direction in the loaded attitude detection data;
determine whether or not a pallet of a detection target cargo set among the plurality of sets of cargo sets interferes with a pallet of a cargo set neighboring in the lateral direction; and
determine whether or not a cargo of the detection target cargo set interferes with a cargo or a pallet of a cargo set neighboring in the lateral direction.
2 . The loaded attitude state detecting device according to claim 1 , wherein, when the pallet of the detection target cargo set contacts the pallet of the cargo set neighboring in the lateral direction, and an attitude angle of the pallet of the detection target cargo set is a predetermined threshold or more, the processors are configured to determine that the pallet of the detection target cargo set interferes with the pallet of the cargo set neighboring in the lateral direction.
3 . The loaded attitude state detecting device according to claim 1 , wherein, when the detection target cargo set overlaps an inner area of two virtual lines formed by extending, in the upper-lower direction, both left and right ends of a pallet of the cargo set neighboring in the lateral direction, the processors are configured to determine that the cargo of the detection target cargo set interferes with the cargo or the pallet of the cargo set neighboring in the lateral direction.
4 . The loaded attitude state detecting device according to claim 1 , wherein the processors are configured to:
acquire a loaded attitude image data of the pallets and the cargos as the loaded attitude detection data by imaging the loaded attitudes of the pallets and the cargos, and
extract the areas of the pallets and the cargos in the loaded attitude image data in units of pixels of the loaded attitude image data.
5 . The loaded attitude state detecting device according to claim 4 , wherein the processors are configured to extract the areas of the pallets and the cargos in the loaded attitude image data by using learned data including loaded attitude images of a plurality of types of pallets and cargos and pixel information of the plurality of types of the pallets and the cargos.
6 . The loaded attitude state detecting device according to claim 5 , wherein the learned data is generated by performing transfer learning on data obtained by annotating the pixel information of the pallets and the cargos to the loaded attitude images of the pallets and the cargos, using pre-learning data obtained by pre-learning a formula driven database.