Pallet identification system and pallet identification method

Abstract

The present invention provides a pallet identification device that can quickly and accurately identify pallets placed on a loading platform. [Solution] The pallet identification device 20 of the present invention identifies the type of pallet 3 using a pre-registered image of pallet 3 in the image information including pallet 3 acquired by the imaging device 10, calculates the size of pallet 3 based on the number of pixels in the field of view size of the imaging device 10 calculated using distance information from the imaging device 10 to pallet 3 and the pixel size of pallet 3 in the image information, and corrects the type of pallet 3 identified using the image of pallet 3 by comparing the size of pallet 3 with the pre-registered size for each type of pallet 3.

Description

Technical Field

[0001] The present invention relates to a pallet identification technology for identifying pallets installed on a loading platform.

Background Art

[0002] As a technology for managing goods in a warehouse, a method has been proposed for managing the installation locations of goods and pallets in the warehouse by reading identification codes assigned to the goods and pallets. Recently, a technology has been proposed for reducing the load of inspections and inventory work of goods in the warehouse by acquiring image information of goods and pallets in the warehouse using cameras mounted on transport vehicles or drones moving in the warehouse.

[0003] For example, in Patent Documents 1 and 2, a pallet detection system using a robot or drone equipped with a camera for photographing images of goods in a warehouse has been proposed. By reading barcodes installed on goods or shelves with a camera mounted on a robot or drone, information on the types and quantities of goods can be obtained.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, the barcode reading technology described above requires acquiring images of the goods or pallets from a relatively close distance and from the front. Therefore, when inspecting goods or pallets placed on the back of a truck, it may not be possible to accurately detect the goods or pallets. When loading or unloading goods from trucks, there is a need for a technology that can quickly and accurately determine the number of goods or pallets in a simpler way compared to goods stored in a warehouse.

[0006] This invention was made to solve the above-mentioned problems, and aims to provide a pallet identification device that can identify pallets installed on a loading platform in a simpler, faster, and more accurate way. [Means for solving the problem]

[0007] To solve the problems described above, the present invention provides a pallet identification device comprising: an imaging device that acquires image information including an image of a pallet loaded on a loading platform, distance information to the pallet on the loading platform, a pallet identification unit that identifies the type of pallet based on a pre-registered image of the pallet in the image information including the image of the pallet acquired by the imaging device, and a pallet size calculation unit that calculates the size of the identified pallet based on the field of view size of the imaging device calculated using the distance information, the number of pixels in the field of view size of the imaging device, and the pixel size of the identified pallet in the image information. The pallet identification unit corrects the type of pallet identified based on the image of the pallet by comparing the size of the pallet calculated by the pallet size calculation unit with the sizes of each type of pallet that have been pre-registered.

[0008] To solve the problems described above, the present invention provides a pallet identification method that is performed in a pallet identification system for identifying the type of pallet loaded on a cargo bed, wherein the pallet identification system comprises an imaging device and a pallet identification device, the imaging device acquiring image information including an image of a pallet loaded on a cargo bed and distance information to the pallet on the cargo bed; the pallet identification device identifying the type of pallet based on a pre-registered image of the pallet in the image information including the image of the pallet acquired by the imaging device; calculating the size of the identified pallet based on the field of view size of the imaging device calculated using the distance information, the number of pixels in the field of view size of the imaging device, and the pixel size of the identified pallet in the image information; and correcting the type of pallet identified based on the image of the pallet by comparing the size of the pallet with the sizes of each type of pallet pre-registered. [Effects of the Invention]

[0009] According to the present invention, it is possible to provide a pallet identification device that can identify pallets installed on a loading platform in a simpler, faster, and more accurate manner. [Brief explanation of the drawing]

[0010] [Figure 1] Figure 1 shows an example of a system configuration equipped with a pallet identification device according to an embodiment of the present invention. [Figure 2] Figure 2 shows an example of the functional block of a pallet identification device in an embodiment of the present invention. [Figure 3] Figure 3 is a diagram illustrating a pallet identification method in an embodiment of the present invention. [Figure 4] Figure 4 is a diagram illustrating a pallet identification method in an embodiment of the present invention. [Figure 5] Figure 5 is a diagram illustrating a pallet identification method in an embodiment of the present invention. [Figure 6] Figure 6 is a diagram illustrating the method for calculating the pallet size in an embodiment of the present invention. [Figure 7] Figure 7 is a diagram illustrating the pallet identification results in an embodiment of the present invention. [Figure 8] Figure 8 shows an example of the operation flow of the pallet identification method in an embodiment of the present invention. [Figure 9] Figure 9 shows an example of the operation flow of the pallet size calculation method in an embodiment of the present invention. [Modes for carrying out the invention]

[0011] Embodiments of the present invention will be described below with reference to the drawings. It should be noted that the present invention can be implemented in various embodiments and is not limited to the embodiments of the invention described below.

[0012] <Configuration of the Palette Detection System> Figure 1 shows an example of a system configuration equipped with a pallet identification device according to an embodiment of the present invention. The pallet identification system in Figure 1 consists of a camera 10 that acquires image information of the pallet 3 with goods 2 placed on it, where a pallet 3 with goods 2 placed on it is loaded on the cargo bed 1 of a transport vehicle such as a truck, and a pallet identification device 20 that identifies the type of pallet 3 on the cargo bed 1 using the acquired image information.

[0013] The pallet identification system shown in Figure 1 is configured to detect a pallet 3 on which cargo 2 is placed, which is loaded onto the truck bed 1, by comparing image information acquired by camera 10 with pre-registered image information of pallet 3.

[0014] Camera 10 may be a fixed camera installed on a truck berth or the like, or a photographer holding camera 10 may be positioned at a designated location on a truck berth or the like to acquire image information of the pallet 3 on which the cargo 2 is placed.

[0015] When loading or unloading the goods 2 placed on the loading platform 1 of a transport vehicle such as a truck, it is necessary to identify and confirm the pallet 3 in the state where it is installed on the loading platform 1 of the transport vehicle such as a truck to check whether the goods 2 to be transported are loaded. Therefore, compared with the case of checking the goods stored in the warehouse, there are time or location restrictions, so there is a demand to identify the pallet 3 on which the goods 2 are loaded quickly and accurately by a simpler method.

[0016] In the configuration example of FIG. 1, on the loading platform 1 of a transport vehicle such as a truck, a plurality of pallets 3 on which a plurality of goods 2 are placed are arranged in a stacked state. Since the types of the pallets 3 on the loading platform 1 of the transport vehicle such as a truck are not limited to one type, it is necessary to identify the types of a plurality of types of pallets 3 by acquiring an overall image of the goods 2 on the loading platform 1.

[0017] The pallet identification device 20 acquires the image information of the entire loading platform 1 including the image of the pallet 3, and identifies the image of the pallet 3 from the image information of the entire loading platform 1 by comparing it with the pre-registered image information of the pallet 3. The pre-registered image information of the pallet 3 includes information for representing the characteristics of the pallet 3 such as the color and shape of the pallet 3.

[0018] As the image information of the pallet 3, images taken for each type of the pallet 3 may be registered, or the image information learned using the image information of a large number of pallets 3 may be used. By detecting the information for representing the characteristics of the pallet 3 such as the color and shape of the pallet 3 from the image information of the entire loading platform 1 including the image information of the pallet 3, the type of the pallet 3 on the loading platform 1 can be identified.

[0019] Here, when identifying the type of pallet 3 on the loading platform 1 by detecting information that represents the characteristics of pallet 3, such as its color and shape, there is a problem in that the identification rate for identifying pallets of the same color but different sizes is lower compared to identifying pallets of different colors. This is because, since pallets 3 are identified using 2D image processing, differences in size are more difficult to distinguish than differences in color.

[0020] In the pallet identification system of this embodiment, the camera 10 has the function of acquiring distance information in addition to image information of the pallet 3. The pallet identification device 20 is configured to correct the identification result of the type of pallet 3 based on image information by comparing the size of the pallet 3 calculated using the distance information of the pallet 3 with pre-registered size information of the pallet 3.

[0021] In the pallet identification system of this embodiment, the identification rate of different pallets 3 of the same color but different sizes can be improved by correcting the identification result of the pallet 3 using the size of the pallet 3, making it possible to quickly and accurately identify various types of pallets 3 installed on the loading platform 1.

[0022] <Configuration of the pallet identification device> The configuration of the pallet identification device 20 will be explained using Figure 2. Figure 2 is an example of a functional block of the pallet identification device in an embodiment of the present invention.

[0023] The pallet identification device 20 includes a central processing unit 21 that identifies pallets 3 on the cargo bed 1 using image information and distance information acquired by a camera 10 installed on a truck berth, etc., a storage unit 22 for storing various information such as pre-registered image information and distance information of pallets 3, acquired image information and distance information of pallets 3, and the type of identified pallet 3, an input unit 23 for inputting information to the pallet identification device 20, a display unit 24 for displaying the identification result of the pallet 3, and a wireless unit 25 which is a communication means for receiving image information and distance information from the camera 10.

[0024] The central processing unit 21 functions as a pallet size calculation unit 21-1 that calculates the size of the pallet 3 using image information and distance information acquired by a camera 10 installed on a truck berth, etc., and a pallet identification unit 21-2 that identifies the pallet 3 on the cargo bed 1 using the image information acquired by the camera 10, and corrects the identification result of the pallet 3 identified using the image information using the calculated pallet 3 size information.

[0025] The palette size calculation unit 21-1 calculates the size of the identified palette 3 based on the angle of view size of the camera 10 calculated using distance information acquired by the camera 10, the number of pixels in the angle of view size of the camera 10, and the pixel size of the identified palette 3 in the image information.

[0026] The pallet identification unit 21-2 identifies the type of pallet 3 based on pre-registered images of pallet 3 in the image information which includes the image of pallet 3 acquired by the camera 10, and corrects the type of pallet identified based on the image of pallet 3 by comparing the size of pallet 3 calculated by the pallet size calculation unit 21-1 with the size of each type of pallet 3 that has been pre-registered.

[0027] The memory unit 22 stores various information such as pre-registered image information and distance information of palette 3, acquired image information and distance information of palette 3, and the type of identified palette 3. The pre-registered image information of palette 3 includes information that represents the characteristics of the palette, such as the color and shape of palette 3. Image data that has been trained using image data of multiple palette 3 may be used as the image information of palette 3.

[0028] The memory unit 22 stores image information of the pallet 3 for comparison with the acquired image information of the pallet 3 on the loading platform 1, as well as size information for each type of pallet 3. By comparing the size of the pallet 3 calculated by the pallet size calculation unit 21-1 with the pre-registered size information for each type of pallet 3, the type of pallet identified based on the image of the pallet 3 can be corrected.

[0029] As the camera 10 that acquires image information and distance information for palette 3, a digital camera equipped with a general-purpose RGB sensor and a general-purpose distance measuring sensor such as a TOF (Time of Flight) sensor or LiDAR sensor can be used.

[0030] The pallet identification device 20 can be configured as a computer equipped with a CPU, memory, and means for communicating with external devices. In the embodiment described above, a system configuration in which the camera 10 and the pallet identification device 20 are made up of separate hardware has been described, but the pallet identification device 20 may also be configured to have the functions of the camera 10.

[0031] <Palette identification using size information> Figures 3 to 5 illustrate the identification of pallets using pallet size information. Figures 3 to 5 are diagrams illustrating a pallet identification method in an embodiment of the present invention.

[0032] In this embodiment, the type of palette 3 is identified based on a pre-registered image of palette 3 in the image information that includes the image of palette 3 acquired by camera 10. Figure 3 shows the palette identification result using the image information.

[0033] In this embodiment, the pallet identification device 20 stores information representing the characteristics of each pallet 3, such as its color and shape, for each type: "Pallet Type #A," "Pallet Type #B," and "Pallet Type #C." As described above, when identifying the type of pallet 3 based on two-dimensional image information such as the color and shape of the pallet 3, there is a problem that the identification rate is lower when identifying pallets of the same color but different sizes compared to identifying pallets of different colors.

[0034] In the identification results shown in Figure 3, 15 palettes 3 of "Palette Type #A" are identified based on the "Palette Color" in the pre-registered image information of palette 3. However, if "Palette Type #A," "Palette Type #B," and "Palette Type #C" have the same "Palette Color," there is a possibility that palettes 3 of the same color but different sizes may be incorrectly identified as the same "Palette Type #A" palette 3.

[0035] The pallet identification device 20 of this embodiment corrects the identification result of the type of pallet 3 based on image information by comparing the size of the pallet 3 calculated using the distance information of the pallet 3 with pre-registered size information of the pallet 3. Figure 4 shows the result of calculating the size of the pallet 3 in the image information of Figure 3.

[0036] The calculation results in Figure 4 show that of the 15 palettes of the same color, 9 palettes have "palette size #1", 3 palettes have "palette size #2", and 3 palettes have "palette size #3".

[0037] The pallet identification device 20 of this embodiment corrects the type of pallet identified based on the image of the pallet 3 by comparing the calculated size of the pallet 3 with the sizes of each type of pallet 3 that have been registered in advance. Figure 5 shows the result of correcting the pallet type identification result in Figure 3 using the pallet size calculation result in Figure 4.

[0038] In this embodiment, the pallet identification device 20 has registered information representing the characteristics of the pallet 3, such as color and shape, as well as the pallet size, for each type of pallet, namely "Pallet Type #A," "Pallet Type #B," and "Pallet Type #C." The pallet identification result in Figure 3 is corrected by comparing the "Pallet Size #1," "Pallet Size #2," and "Pallet Size #3" of the pallet 3 calculated in Figure 4 with the pre-registered pallet sizes of "Pallet Type #A," "Pallet Type #B," and "Pallet Type #C."

[0039] In the corrected results shown in Figure 5, out of 15 palettes of the same color, 9 palettes are identified as "Palette Type #A", 3 palettes as "Palette Size #B", and 3 palettes as "Palette Type #C".

[0040] In the pallet identification system of this embodiment, the identification rate of different pallets 3 of the same color but different sizes can be improved by correcting the identification result of the pallet 3 using the size of the pallet 3, making it possible to quickly and accurately identify various types of pallets 3 installed on the loading platform 1.

[0041] Figure 6 is a diagram illustrating a method for calculating the pallet size in an embodiment of the present invention. The pallet identification device 20 calculates the size of the identified pallet 3 based on the field of view size of the camera 10 calculated using distance information acquired by the camera 10, the number of pixels in the field of view size of the camera 10, and the pixel size of the identified pallet 3 in the image information.

[0042] The pallet size calculation unit 21-1 of the pallet identification device calculates the field of view size "L" at the distance "D" from the camera 10 to the pallet 3 using equation (1). L = D × tan(θ / 2)···(1) Here, "θ" represents the camera's field of view.

[0043] Next, using the field of view size "L" calculated in equation (1), the size coefficient "K" per pixel in camera 10 is calculated using equation (2). K = L / (H / 2) ... (2) Here, "H" represents the number of horizontal pixels in the camera's field of view.

[0044] Finally, using the size coefficient "K" calculated in equation (2), the size "X_m" of pallet 3 is calculated using equation (3). X_m = K × X_p ···(3) Here, "X_p" is the pixel size of palette 3, which is the object of measurement in the camera image.

[0045] In this embodiment, the size of the palette 3, which is the object of measurement, is calculated using the angle of view size of the camera 10 calculated using distance information acquired by the camera 10, the number of pixels in the angle of view of the camera 10, and the pixel size of the palette 3 in the image information.

[0046] The above explanation described an example of calculating the width of pallet 3, which is the object of measurement. However, the height of pallet 3 may also be calculated. Since the width of pallet 3 is greater than its height, calculating the width of pallet 3 is thought to improve the accuracy of identifying the type of pallet 3. It is also possible to use information on both the width and height of pallet 3 to refine the identification result of pallet 3.

[0047] Figure 7 is a diagram illustrating the pallet identification results in an embodiment of the present invention. Figure 7 shows the pallet identification results in the pallet identification method described in Figures 3 to 5.

[0048] In the example in Figure 7, information representing the characteristics of palette 3, such as color and shape, and the palette size (width) are registered for each palette type: "Palette Type #A", "Palette Type #B", and "Palette Type #C".

[0049] In the example in Figure 7, as explained in Figures 3-5, out of 15 palettes of the same color, 9 palettes are identified as "Palette Type #A", 3 palettes as "Palette Size #B", and 3 palettes as "Palette Type #C".

[0050] As shown in Figure 7, a numerical value with a predetermined width is registered as the pallet size information. This is because it is assumed that the installation position of the transport vehicle, the loading platform 1, or the installation position of the pallet 3 on the loading platform 1 and the installation position of the camera 10 are not in the ideal positional relationship as described in Figure 6. In this embodiment, if the size of the identified pallet 3 is within the predetermined range shown in Figure 7, it can be determined that the type of identified pallet 3 is the pallet 3 registered in Figure 7.

[0051] <Operation Flow of Pallet Identification Device> Figures 8 and 9 illustrate the pallet identification operation in the pallet identification system. Figure 8 is an example of the operation flow of the pallet identification method in an embodiment of the present invention.

[0052] When a transport vehicle enters a truck berth or similar area, camera 10 acquires image information that includes an image of the transport vehicle's cargo bed 1 loaded with cargo 2 (S1-1).

[0053] The pallet identification unit 21-2 of the pallet identification device 20 identifies the type of pallet 3 based on a pre-registered image of pallet 3 in the image information which includes the image of pallet 3 acquired by the camera 10 (S1-2).

[0054] The pallet size calculation unit 21-1 of the pallet identification device 20 acquires distance information for each pallet 3 identified from the camera 10 (S1-3), and calculates the size of the identified pallet 3 based on the angle of view size of the camera 10 calculated using the distance information of the identified pallet 3, the number of pixels in the angle of view size of the camera 10, and the pixel size of the identified pallet 3 in the image information (S1-4).

[0055] The pallet identification unit 21-2 of the pallet identification device 20 determines whether the pallet size calculated by the pallet size calculation unit 21-1 is within a predetermined range registered in advance for each type of pallet 3. If the pallet size is within the predetermined range (S1-5: YES), the type of pallet is determined (S1-7). If the pallet size is not within the predetermined range (S1-5: NO), the type of pallet is corrected (S1-6).

[0056] Figure 9 shows an example of the operation flow of the pallet size calculation method in an embodiment of the present invention. Figure 9 shows the specific processing details of the pallet size calculation step (S1-4) in Figure 8.

[0057] In the step of calculating the palette size (S1-4), as explained in Figure 6, the field of view size L at the distance D from camera 10 to palette 3 is calculated (S2-1), a size coefficient K indicating the size per pixel is calculated using the field of view size L (S2-2), and the size of palette 3 is calculated by multiplying the number of pixels of palette 3, which is the object of measurement, by the size coefficient K (S2-3).

[0058] In the pallet identification system of this embodiment, the camera 10 has the function of acquiring distance information in addition to image information of the pallet 3. The pallet identification device 20 is configured to correct the identification result of the type of pallet 3 based on image information by comparing the size of the pallet 3 calculated using the distance information of the pallet 3 with pre-registered size information of the pallet 3.

[0059] In the pallet identification system of this embodiment, the identification rate of different pallets 3 of the same color but different sizes can be improved by correcting the identification result of the pallet 3 using the size of the pallet 3, making it possible to quickly and accurately identify various types of pallets 3 installed on the loading platform 1. [Explanation of Symbols]

[0060] 1...Loading platform, 2...Cargo, 3...Pallet, 10...Camera, 20...Pallet identification device, 21...Central processing unit, 22...Storage unit, 23...Input unit, 24...Display unit, 25...Wireless unit.

Claims

1. An imaging device that acquires image information including an image of a pallet loaded on a truck bed, and distance information to the pallet on the truck bed, Image information including an image of the pallet acquired by the imaging device includes a pallet identification unit that identifies the type of the pallet based on a pre-registered image of the pallet, A palette size calculation unit calculates the size of the identified palette based on the field of view size of the imaging device calculated using the distance information, the number of pixels in the field of view size of the imaging device, and the number of pixels of the identified palette in the image information. Equipped with a pallet identification device, The pallet identification unit is, By comparing the size of the pallet calculated by the pallet size calculation unit with the sizes of each type of pallet that have been registered in advance, the type of pallet identified based on the image of the pallet is corrected. Pallet identification system.

2. A pallet identification method performed in a pallet identification system for identifying the type of pallet loaded on a cargo bed, The pallet identification system comprises an imaging device and a pallet identification device. The aforementioned imaging device The steps include obtaining image information including an image of a pallet loaded on a truck bed, and distance information to the pallet on the truck bed, The pallet identification device, In the image information which includes an image of the pallet acquired by the imaging device, the step of identifying the type of the pallet based on a pre-registered image of the pallet, A step of calculating the size of the identified palette based on the field of view size of the imaging device calculated using the distance information, the number of pixels in the field of view size of the imaging device, and the number of pixels of the identified palette in the image information. The steps include: correcting the type of palette identified based on the image of the palette by comparing the size of the palette with the sizes of each type of palette that have been registered in advance; has Pallet identification method.

Images