Object detection device, program therefor, and object detection method

Abstract

To specify an object that is placed on or removed from an installation part with high reliability.SOLUTION: An object detection device comprises weight measurement means, pressure detection means, and specification means. The weight measurement means measures the weight of an object placed on an installation part. The pressure detection means detects a pressure applied to the surface of the installation part on which the object is placed. An object is specified from an amount of change in the weight measured by the weight measurement means before and after the change in pressure detected by the pressure detection means, and the shape of a range in which the pressure has changed.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] FIELD Embodiments of the present invention relate to an object detection device, a program therefor, and an object detection method. [Background technology]

[0002] A technology for identifying an object placed on a shelf based on information from a pressure sensor installed on the shelf is already known. Conventional technologies of this type estimate the shape and weight of the object from the information from the pressure sensor, and then identify the object from the estimated shape and weight. As such, conventional technologies identify objects by estimating not only their shape but also their weight, which has led to poor reliability. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2017-071470 Summary of the Invention [Problem to be solved by the invention]

[0004] The problem to be solved by the embodiments of the present invention is to provide an object detection device that can identify an object placed on or removed from a placement section with high reliability. [Means for solving the problem]

[0005] In one embodiment, the object detection device includes a weight measuring means, a pressure detecting means, and an identifying means. The weight measuring means measures the weight of an object placed on the placement unit. The pressure detecting means detects the pressure applied to the surface of the placement unit on which the object is placed. The object is identified based on the amount of change in weight measured by the weight measuring means before and after a change in pressure detected by the pressure detecting means occurs, and the shape of the area where the change in pressure occurs. [Brief explanation of the drawings]

[0006] [Figure 1] FIG. 1 is a configuration diagram of an object detection device according to an embodiment. [Figure 2] FIG. 2 is an explanatory diagram of a pressure sensor. [Figure 3] FIG. 3 is a schematic diagram showing the main data structure of an item record stored in the item database. [Figure 4] FIG. 4 is a schematic diagram showing the data structure of the history table. [Figure 5] FIG. 5 is a flowchart showing the procedure of information processing executed by the processor with one sensor device according to the control program. [Figure 6] FIG. 6 is a flowchart showing the procedure of information processing executed by the processor with one sensor device according to a control program. [Figure 7] FIG. 7 is a flowchart showing the procedure of information processing executed by the processor with one sensor device according to the control program. [Figure 8] FIG. 8 is a flowchart showing the procedure of the primary search process in FIG. [Figure 9] FIG. 9 is a flowchart showing the procedure of the secondary search process in FIG. [Figure 10] FIG. 10 is a schematic diagram showing an example of the state of the pressure sensor when an article is placed on the placement section. [Figure 11] FIG. 11 is a schematic diagram showing another example of the state of the pressure sensor when an article is placed on the placement section. DETAILED DESCRIPTION OF THE INVENTION

[0007] Hereinafter, an embodiment of an object detection device will be described with reference to the drawings. In this embodiment, an object detection device that detects an object placed on or removed from a shelf in a logistics warehouse, a store, or the like is exemplified. That is, the object is, for example, a product. The object is an example of an object.

[0008] 1 is a configuration diagram of an object detection device 100 according to one embodiment. The object detection device 100 includes a sensor device 1 and an information processing unit 10. In other words, the object detection device 100 can be referred to as an object detection system including the sensor device 1 and the information processing unit 10.

[0009] The sensor device 1 is installed on a shelf on which an object to be detected is placed. For example, one sensor device 1 is installed on one shelf level. Alternatively, if one shelf level is divided into multiple sections in the longitudinal direction, one sensor device 1 is installed on each section. Therefore, the number of sensor devices 1 depends on the number of shelf levels or the number of sections. In FIG. 1, it is assumed that a sensor device 1 is installed on each of three shelves or shelves divided into three sections. Therefore, the number of sensor devices 1 is three.

[0010] The sensor device 1 includes a weight sensor 2 and a pressure sensor 3. The weight sensor 2 has, for example, a rectangular parallelepiped shape, and is installed on a shelf with the placement section 21 facing upward, so that one of the large opposing flat surfaces serves as the placement section 21 for items. The weight sensor 2 measures the total weight of the items, etc. placed on the placement section 21. The weight sensor 2 periodically outputs a weight data signal corresponding to the total weight to the information processing section 10. Here, the weight sensor 2 functions as a weight measuring means that measures the weight of the object (item) placed on the placement section 21.

[0011] The pressure sensor 3 is a thin-film sensor attached to the mounting portion 21 so as to cover the entire area of ​​the mounting portion 21. As shown in FIG. 2, the pressure sensor 3 is configured by arranging a large number of pressure detection elements 31 two-dimensionally in a dot matrix. Each pressure detection element 31 is assigned a unique address indicated by (X, Y) coordinates with the base point O as the origin (0, 0). The pressure sensor 3 periodically outputs a pressure data signal corresponding to the pressure value detected by each pressure detection element 31 to the information processing unit 10, in association with the address of each pressure detection element 31. Here, the pressure sensor 3 functions as a pressure detection means that detects the pressure applied to the surface of the mounting portion 21 on which an object (article) is placed.

[0012] The cycle in which the weight sensor 2 outputs a weight data signal may or may not match the cycle in which the pressure sensor 3 outputs a pressure data signal. It is sufficient that the cycle is long enough for the information processing unit 10 to recognize, in approximately real time, the pressure and weight that change when an item is placed on or removed from the placement unit 21.

[0013] 1, an information processing unit 10 includes a processor 11, a main memory 12, an auxiliary storage device 13, a clock 14, an interface 15, an input device 16, a display device 17, an alarm device 18, and a system transmission path 19. The system transmission path 19 includes an address bus, a data bus, a control signal line, and the like. The system transmission path 19 connects the processor 11 to each of the other units directly or via a signal input / output circuit, and transmits data signals exchanged between them. The information processing unit 10, to which the processor 11, the main memory 12, the auxiliary storage device 13, the clock 14, and the like are connected by the system transmission path 19, constitutes a computer of the object detection device 100.

[0014] The processor 11 corresponds to the central part of the computer. The processor 11 controls each part to realize various functions of the object detection device 100 in accordance with an operating system or an application program. The processor 11 is, for example, a CPU (Central Processing Unit).

[0015] The main memory 12 corresponds to the main storage portion of the computer. The main memory 12 includes a nonvolatile memory area and a volatile memory area. The main memory 12 stores an operating system or application programs in the nonvolatile memory area. The main memory 12 may store data required for the processor 11 to execute processes for controlling each part in either the nonvolatile or volatile memory area. The main memory 12 uses the volatile memory area as a work area where data is rewritten by the processor 11 as appropriate. The nonvolatile memory area is, for example, ROM (Read Only Memory). The volatile memory area is, for example, RAM (Random Access Memory).

[0016] The auxiliary storage device 13 corresponds to the auxiliary storage portion of the computer. For example, an EEPROM (Electric Erasable Programmable Read-Only Memory), an HDD (Hard Disc Drive), or an SSD (Solid State Drive) can be the auxiliary storage device 13. The auxiliary storage device 13 stores data used by the processor 11 when performing various processes, data created by the processes in the processor 11, etc. The auxiliary storage device 13 may also store the application programs described above.

[0017] The clock 14 keeps track of the date and time. The processor 11 processes the date and time kept by the clock 14 as the current date and time.

[0018] The interface 15 is a circuit for receiving weight data signals and pressure data signals output from each sensor device 1 to the information processing unit 10. The interface 15 may receive each data signal from each sensor device 1 via a wired cable, or may receive each data signal via wireless communication.

[0019] The input device 16 is a device used by an operator to input various pieces of information. For example, a keyboard, a mouse, a touch sensor, etc. are used as the input device 16.

[0020] The display device 17 is a device used to display various information to the operator. For example, a liquid crystal display, an organic EL display, or the like is used as the display device 17.

[0021] The notification device 18 is a device used to provide various notifications to the operator. For example, an LED lamp, a buzzer, etc. may be used as the notification device 18. The display device 17 may also serve as the notification device 18.

[0022] The information processing unit 10 configured as above stores an item database 20 in the auxiliary storage device 13. The item database 20 is a collection of item records 201 (see FIG. 3) generated for each item that can be placed on a shelf. The information processing unit 10 also uses a part of the volatile memory area of ​​the main memory 12 as a history table 30. The history table 30 is used to store information on items that have been placed on and removed from the shelf on which the sensor device 1 is installed, in chronological order, based on each data signal from the sensor device 1. The same number of history tables 30 as the number of sensor devices 1 connected to the interface 15 are prepared.

[0023] FIG. 3 is a schematic diagram showing the main data structure of an item record 201 stored in the item database 20. As shown in the figure, the item record 201 is a record that records data related to each item, such as the item ID, item name, unit weight, contact surface shape, and center of gravity distance. The item ID is a unique code assigned to each item to identify each item. For example, if the item is a product, the product code specific to that product may be the item ID. The item name is the unique name of the item identified by the item ID. For example, if the item is a product, the product name may be the item name.

[0024] The unit weight is the weight per item. In this embodiment, it is assumed that all unit weights of the same item are the same. When multiple items are combined to form a single item, the unit weight may be the total weight of the items in that set. Incidentally, some items are categorized by size. For such items, even if they are the same type, an item ID is assigned for each size, and each item record 201 is created and stored in the item database 20.

[0025] The contact surface shape is the shape of the surface of an item that comes into contact with the shelf when the item is placed on the shelf. Generally, items have a top and a bottom, and are placed so that the lower surface, or the so-called bottom surface, comes into contact with the shelf. Therefore, the contact surface shape can also be said to be the shape of the bottom surface. Note that some items are placed so that the side surface, rather than the bottom surface, comes into contact with the shelf. For such items, the shape of the side surface is used as the contact surface shape. Alternatively, the shapes of the side surface and the bottom surface may each be registered as contact surface shapes in the item record 201.

[0026] The center of gravity distance is expressed as the straight-line distance between the center of the contact surface of the item with the shelf and the center of gravity of the contact surface of the item.

[0027] 4 is a schematic diagram showing the data structure of the history table 30. As shown in the figure, the history table 30 has an area 301 for storing device IDs. A unique device ID that has been set in advance for the corresponding sensor device 1 is written in the area 301 of each history table 30. The history table 30 also has an area 302 for storing a large number of history records. A history record is a record that records data related to each item, such as date and time, item ID, item name, quantity, weight, and condition.

[0028] The status is data indicating whether an item is placed on a shelf or has been removed from the shelf. In this embodiment, the status of being placed on a shelf is represented by "+", and the status of being removed from a shelf is represented by "-". The item ID and item name are the item ID and item name of the item placed on or removed from the shelf. The quantity is the number of items placed on or removed from the shelf. The date and time is the date and time when the item was placed on or removed from the shelf.

[0029] Next, the main functions of the information processing unit 10 will be described. The information processing unit 10 functions as an identification means for identifying an object (item) based on the difference in weight measured by the weight measuring means (weight sensor 2) before and after a change in pressure detected by the pressure detection means (pressure sensor 3), i.e., the amount of weight change, and the shape of the area where the change in pressure occurred.

[0030] The identification means includes functions as an estimation means that estimates the contact surface shape of the object (article) from an area where a change in pressure detected by the pressure detection means (pressure sensor 3) occurs, and a calculation means that calculates the weight of the object (article) from a first weight measured by the weight measurement means (weight sensor 2) before the change in pressure occurs and a second weight measured by the weight measurement means (weight sensor 2) after the change in pressure occurs. The identification means searches the article database 20 based on the contact surface shape and weight to identify the object (article) placed on or removed from the placement unit 21. Specifically, the identification means identifies the object (article) placed on the placement unit 21 when the measured weight changes in a positive direction, and identifies the object (article) removed from the placement unit 21 when the measured weight changes in a negative direction.

[0031] Furthermore, the identification means includes a center of gravity determination means for determining the center of gravity of the object (article) from the distribution of pressure detected by the pressure detection means (pressure sensor 3).The identification means can also identify the object (article) based on the center of gravity.

[0032] The information processing unit 10 also functions as a first notification means that issues a notification when the pressure detected by the pressure detection means (pressure sensor 3) reaches the upper limit of the detection range. There is an upper limit to the pressure that the pressure sensor 3 can detect. The pressure sensor 3 cannot correctly detect pressure that exceeds the upper limit. If the pressure cannot be correctly detected, the information processing unit 10 cannot correctly identify the item. Therefore, when the pressure detected by the pressure sensor 3 reaches the upper limit, there is a possibility that pressure exceeding the upper limit has been applied, and there is a risk that the item may not be correctly identified, so the information processing unit 10 issues a notification by functioning as a first notification means.

[0033] Furthermore, the information processing unit 10 also functions as a second notification unit that notifies when weight is measured by the weight measurement unit (weight sensor 2) without pressure being detected by the pressure detection unit (pressure sensor 3). When an item is placed on or removed from the placement unit 21, at least one pressure detection element constituting the pressure sensor 3 detects a change in pressure. The weight sensor 2 then waits for the weight applied to the weight sensor 2 to stabilize before measuring the weight. Therefore, if the pressure sensor 3 is operating normally, the pressure sensor 3 first detects pressure, and then the weight sensor 2 measures the weight. Therefore, if the weight sensor 2 measures a weight without pressure being detected by the pressure sensor 3, the information processing unit 10 notifies by functioning as the second notification unit, since there is a risk that the pressure sensor 3 is not operating normally.

[0034] Furthermore, there is a lower limit to the pressure that the pressure sensor 3 can detect. If a pressure smaller than the lower limit is applied to the pressure detection element 31, the pressure sensor 3 cannot detect that pressure. For example, if a lightweight sheet-like item is placed on the placement section 21, the pressure applied to each pressure detection element 31 may be less than the lower limit, and the pressure sensor 3 may not be able to detect the pressure. In such a case, the information processing section 10 cannot identify the item even if the weight sensor 2 measures the weight of the item. Therefore, the information processing section 10 issues a notification by functioning as a second notification means.

[0035] Each function of the information processing unit 10 will become clear by explaining the procedure of information processing executed by the processor 11 in accordance with the control program. The control program is one of the application programs stored in the main memory 12 or the auxiliary storage device 13. There are no particular limitations on the method for installing the control program in the main memory 12 or the auxiliary storage device 13. The control program can be installed in the main memory 12 or the auxiliary storage device 13 by recording it on a removable recording medium or by distributing it via communication over a network. The recording medium can be in any form, such as a CD-ROM or memory card, as long as it can non-temporarily store a program and is readable by the device.

[0036] 5 to 9 are flow charts showing the procedure of information processing that the processor 11 executes in accordance with a control program between one sensor device 1. The procedure of information processing that the processor 11 executes between other sensor devices 1 is similar, so a description thereof will be omitted here. Note that the information processing procedure described below is an example. The procedure or content can be changed as appropriate as long as a similar effect can be obtained.

[0037] When the information processing unit 10 is reset, the processor 11 starts processing the procedure shown in the flowchart of Fig. 5. First, the processor 11 reads the measured weight from the sensor device 1 as ACT1. The measured weight can be read by analyzing the weight data signal output from the weight sensor 2 of the sensor device 1. The processor 11 writes the measured weight in the first work area Wa as ACT2.

[0038] In ACT3, the processor 11 checks whether or not there has been a change in the pressure detected by the pressure sensor 3 of the sensor device 1. If there has been no change in the pressure, the processor 11 determines NO in ACT3 and proceeds to ACT4. In ACT4, the processor 11 checks whether or not there has been a change in the weight measured by the weight sensor 2 of the sensor device 1. If there has been no change in the weight, the processor 11 determines NO in ACT4 and returns to ACT3. In this way, the processor 11 waits in ACT3 and ACT4 for a change in pressure or weight to occur on the mounting portion 21. Incidentally, a change in pressure refers to a change in which the pressure increases or decreases. The same applies to a change in weight.

[0039] If a change in weight occurs without a change in pressure during the standby state of ACT3 and ACT4, the processor 11 determines YES in ACT4 and proceeds to ACT5. The processor 11 controls the notification device 18 so that a sensor error is notified in ACT5. This control causes, for example, an LED for indicating a sensor error provided in the notification device 18 to light up or flash. Here, the processor 11 functions as a first notification means by executing the processing of ACT5 in cooperation with the notification device 18.

[0040] After controlling the notification, processor 11 returns to ACT 1. Then, processor 11 executes the processes from ACT 1 onward in the same manner as described above. Therefore, the notification of the sensor error continues until the sensor error is resolved.

[0041] If a change occurs in the pressure during the standby state of ACT3 and ACT4, the processor 11 determines YES in ACT3 and proceeds to ACT6. In ACT6, the processor 11 checks whether the pressure value detected by the pressure sensor 3 has reached the upper limit. If it has reached the upper limit, the processor 11 determines YES in ACT6 and proceeds to ACT7. In ACT7, the processor 11 controls the notification device 18 to notify a placement error. By this control, for example, an LED for a placement error provided in the notification device 18 lights up or flashes. Here, the processor 11 functions as a second notification means by executing the processing of ACT7 in cooperation with the notification device 18.

[0042] After controlling the notification, processor 11 returns to ACT 1. Then, processor 11 executes the processes from ACT 1 onward in the same manner as described above. Therefore, the notification of the placement error continues until the placement error is resolved, that is, until at least some of the articles placed on placement section 21 are removed and the pressure detected by pressure sensor 3 becomes less than the upper limit value.

[0043] If the pressure detected by the pressure sensor 3 is less than the upper limit value, the processor 11 determines NO in ACT6 and proceeds to ACT11 in Fig. 6. In ACT11, the processor 11 estimates the shape of the contact surface of the article.

[0044] 10, when an object 41 having a circular contact surface is placed on the placement unit 21, the pressure detection elements 31 detect pressure in a distribution 42 as shown in the figure. The processor 11 estimates this distribution 42 as the contact surface shape.

[0045] The processor 11 copies the measured weight stored in the first work area Wa to the second work area Wb as ACT 12. Then, the processor 11 reads the measured weight from the sensor device 1 as ACT 13. The processor 11 writes the measured weight in the first work area Wa as ACT 14.

[0046] The processor 11 calculates the differential weight ΔW by subtracting the measured weight in the first work area Wa from the measured weight in the second work area Wb in ACT 15. The processor 11 executes a primary search process in ACT 16.

[0047] 8 is a flow chart showing the procedure for the primary search process. When the primary search process begins, the processor 11 clears the primary candidate memory in ACT51. The primary candidate memory is, for example, a part of a volatile memory area in the main memory. The processor 11 resets both the primary candidate counter Ca and the item number counter N to "0" in ACT52. The primary candidate counter Ca and the item number counter N are both provided by the processor 11.

[0048] The processor 11 counts up the item number counter N by "1" in ACT 53. Then, the processor 11 checks whether the item number counter N has exceeded the upper limit value Nmax in ACT 54. The upper limit value Nmax is the total number of item records 201 stored in the item database 20.

[0049] If the item number counter N does not exceed the upper limit value Nmax, the item record 201 to be searched is stored in the item database 20. The processor 11 determines NO in ACT54 and proceeds to ACT55. In ACT55, the processor 11 detects the item record 201 having the record number corresponding to the item number counter N from the item database 20. In ACT56, the processor 11 compares the contact surface shape estimated in the processing of ACT11 with the contact surface shape of the item record 201. In ACT57, the processor 11 checks whether the two contact surface shapes are similar. For example, if the similarity between the two contact surface shapes is less than the threshold and it can be determined that they are not similar, the processor 11 determines NO in ACT57 and returns to ACT53. The threshold is the minimum value of similarity at which the contact surface shapes can be determined to be similar.

[0050] If the similarity between the contact patch shapes is equal to or greater than the threshold and can be determined to be similar, the processor 11 determines YES in ACT57 and proceeds to ACT58. In ACT58, the processor 11 compares the differential weight ΔW calculated in ACT15 with the unit weight of the item record 201. In ACT59, the processor 11 checks whether the differential weight ΔW is K times the unit weight (K is a positive integer). If the differential weight ΔW is not K times the unit weight, the processor 11 determines NO in ACT59 and returns to ACT53.

[0051] If the differential weight ΔW is K times the unit weight, the processor 11 determines YES in ACT 59 and proceeds to ACT 60. In ACT 60, the processor 11 checks whether the differential weight ΔW is a positive value or a negative value.

[0052] If the differential weight ΔW is a positive value, the processor 11 determines YES in ACT60 and proceeds to ACT61. In ACT61, the processor 11 writes the value of the primary candidate counter Ca, the item ID and item name of the item record 201, the quantity K, and the status (+) into the primary candidate memory. If the differential weight ΔW is a negative value, the processor 11 determines NO in ACT60 and proceeds to ACT62. In ACT62, the processor 11 writes the value of the primary candidate counter Ca, the item ID and item name of the item record 201, the quantity K, and the status (-) into the primary candidate memory. Incidentally, the quantity K is the quotient obtained by dividing the differential weight ΔW by the unit weight.

[0053] After completing the processing in ACT61 or ACT62, the processor 11 proceeds to ACT63. In ACT63, the processor 11 counts up the primary candidate counter Ca by "1". Thereafter, the processor 11 returns to ACT53.

[0054] After returning to ACT53, the processor 11 executes the processes from ACT53 onwards in the same manner as described above. That is, the processor 11 executes the processes from ACT56 to ACT63 each time it sequentially detects an item record stored in the item database 20. As a result, the primary candidate memory stores the item ID, quantity K, and state (+) or state (-) of the item record 201 whose contact patch shape data is similar to the contact patch shape estimated from the pressure distribution and whose unit weight is an integer multiple of the differential weight ΔW, in association with a consecutive number starting from "1" up to the count value of the primary candidate counter Ca.

[0055] In this way, when the processes of ACT56 to ACT63 have been executed for all the product records 201, the record number counter N exceeds the maximum value Nmax. The processor 11 determines YES in ACT54 and returns to ACT16 in FIG.

[0056] When the primary search process is completed, processor 11 checks whether primary candidate counter Ca is "1" in ACT 17. If primary candidate counter Ca is "1", only one item was detected by the primary search process. In other words, the item placed on or removed from placement section 21 has been identified.

[0057] Processor 11 determines YES in ACT 17 and proceeds to ACT 18. In ACT 18, processor 11 records the date and time kept by clock 14, and the item ID, item name, quantity K, and status (+) or (-) written in the primary candidate memory in history table 30. Processor 11 then returns to ACT 3. Processor 11 then executes the processing from ACT 3 onwards in the same manner as described above.

[0058] On the other hand, if the primary candidate counter Ca is not "1", the processor 11 determines "NO" in ACT 17 and proceeds to ACT 19. In ACT 19, the processor 11 checks whether the primary candidate counter Ca is 2 or greater. If the primary candidate counter Ca is not 2 or greater, i.e., if it is "0", it means that no candidate item was selected by the primary search process. For example, this may occur if the object placed on the placement unit 21 is not an item managed in the item database 20. The processor 11 determines "NO" in ACT 19 and proceeds to ACT 20. The processor 11 notifies the user of a specific error in ACT 20. For example, the processor 11 turns on or blinks an LED for a specific error provided on the notification device 18. After that, the processor 11 returns to ACT 3. The processor 11 then executes the processes from ACT 3 onwards in the same manner as described above.

[0059] On the other hand, if the primary candidate counter Ca is 2 or greater, multiple items have been selected as primary candidate items by the primary search process. This type of event can occur when there are multiple items with similar placement surface shapes and the same unit weight. Processor 11 determines YES in ACT 19 and proceeds to ACT 31 in Figure 7. In ACT 31, processor 11 calculates the center of gravity of the pressure distribution and calculates the distance from the center of the contact surface shape to the center of gravity of the pressure distribution, which is known as the center-of-gravity distance.

[0060] As shown in Figure 11, when an item 43 with a rectangular contact surface is placed on the placement unit 21, the distribution 44 of the pressure detection elements 31 that detected the pressure will be as shown. The processor 11 estimates this distribution 44 as the contact surface shape. The processor 11 then calculates the center point Pa of the distribution 44. The processor 11 also calculates the center of gravity Pb ​​of the item 43 from the pressure detection values ​​of the pressure detection elements 31 that detected the pressure. The processor 11 calculates the linear distance from the center point Pa to the center of gravity Pb ​​as the center of gravity distance.

[0061] Incidentally, when an item 45 identical to item 43 is rotated 90 degrees and placed on placement section 21, distribution 46 of pressure detection elements 31 that detect pressure will be as shown in the figure. In this case, processor 11 also calculates the linear distance from center point Pa to center of gravity Pb ​​as the center of gravity distance using the procedure described above. The linear distance calculated from pressure distribution 46 is equal to the linear distance calculated from pressure distribution 44. In other words, even if the item is placed by rotating it around an axis of rotation that is perpendicular to the ground surface, the center of gravity distance remains constant.

[0062] After calculating the centroid distance, the processor 11 executes a secondary search process in ACT32. 9 is a flow chart showing the procedure for the secondary search process. When the secondary search process begins, the processor 11 clears the secondary candidate memory in ACT 71. The secondary candidate memory is, for example, part of a volatile memory area in the main memory. In ACT 72, the processor 11 resets both the secondary candidate counter Cb and the search candidate counter R to "0." The primary candidate counter Ca and the search candidate counter R are both provided by the processor 11.

[0063] In ACT 73, the processor 11 counts up the search candidate counter R by "1". Then, in ACT 74, the processor 11 checks whether the search candidate counter R has exceeded the primary candidate counter Ca. If the search candidate counter R has not reached the primary candidate counter Ca, data on the primary candidate item to be searched is stored in the primary candidate memory. The processor 11 determines NO in ACT 74 and proceeds to ACT 75. In ACT 75, the processor 11 acquires the item ID of the primary candidate item stored in the primary candidate memory in association with the value of the search candidate counter R. Then, in ACT 76, the processor 11 searches the item database 20 for an item record 201 that includes that item ID.

[0064] In ACT 77, the processor 11 compares the center of gravity distance calculated in the processing of ACT 31 with the center of gravity distance of the item record 201. In ACT 78, the processor 11 checks whether the two center of gravity distances match. If the two center of gravity distances do not match, the processor 11 determines NO in ACT 78 and returns to ACT 73.

[0065] If the two center-of-gravity distances match, in ACT 79, the processor 11 divides the weight difference ΔW calculated in ACT 15 by the item record 201, and rounds off the quotient to the nearest integer to calculate the quantity K. In ACT 80, the processor 11 checks whether the weight difference ΔW is a positive value or a negative value.

[0066] If the differential weight ΔW is a positive value, the processor 11 determines YES in ACT80 and proceeds to ACT81. In ACT81, the processor 11 writes the value of the secondary candidate counter Cb, the item ID and item name of the primary candidate item, the quantity K calculated in ACT79, and the status (+) into the secondary candidate memory. If the differential weight ΔW is a negative value, the processor 11 determines NO in ACT80 and proceeds to ACT82. In ACT82, the processor 11 writes the value of the secondary candidate counter Cb, the item ID and item name of the primary candidate item, the quantity K calculated in ACT79, and the status (-) into the secondary candidate memory.

[0067] After completing the processing in ACT81 or ACT82, the processor 11 proceeds to ACT 83. In ACT 83, the processor 11 counts up the secondary candidate counter Cb by "1". After that, the processor 11 returns to ACT 73.

[0068] After returning to ACT 73, processor 11 executes the processes from ACT 73 onwards in the same manner as described above. That is, processor 11 executes the processes of ACT 76 to ACT 83 each time it sequentially acquires the item ID of a primary candidate item stored in the primary candidate memory. As a result, the secondary candidate memory stores the item ID and item name of the primary candidate item whose center of gravity distance calculated in ACT 31 matches the center of gravity distance in the item record 201, the quantity K calculated in ACT 79, and the status (+) or status (-), in association with a consecutive number starting from "1" up to the count value of the secondary candidate counter Cb.

[0069] In this way, when the processes of ACT76 to ACT83 are executed for all primary candidate items, the search candidate counter R exceeds the primary candidate counter Ca. The processor 11 determines YES in ACT74 and returns to ACT32 in FIG.

[0070] When the secondary search process is completed, processor 11 checks whether secondary candidate counter Cb is "1" in ACT 33. If secondary candidate counter Cb is "1," only one item was detected by the secondary search process. In other words, the item placed on or removed from placement section 21 has been identified.

[0071] The processor 11 determines YES in ACT 33 and proceeds to ACT 34. In ACT 34, the processor 11 records the date and time kept by the clock 14, and the item ID, item name, quantity K, and status (+) or (-) written in the secondary candidate memory in the history table 30. Thereafter, the processor 11 returns to ACT 3. The processor 11 then executes the processing from ACT 3 onwards in the same manner as described above.

[0072] On the other hand, if the secondary candidate counter Cb is not "1", the processor 11 determines NO in ACT33 and proceeds to ACT35. In ACT35, the processor 11 checks whether the secondary candidate counter Cb is 2 or greater. If the secondary candidate counter Cb is not 2 or greater, i.e., if it is "0", it means that an item could not be identified by the secondary search process. For example, this can occur if the center of gravity position of a primary candidate item that should have been identified in the secondary search process has shifted for some reason. The processor 11 determines NO in ACT35 and proceeds to ACT36. In ACT36, the processor 11 displays a list of primary candidate items stored in the primary candidate memory on the display device 17.

[0073] On the other hand, if the secondary candidate counter Cb is 2 or greater, multiple items have been selected as secondary candidate items by the secondary search process. This can occur if the center of gravity of a primary candidate item that should not have been identified in the secondary search process shifts for some reason and ends up matching the center of gravity of a primary candidate item that should have been identified. The processor 11 determines YES in ACT 35 and proceeds to ACT 37. In ACT 37, the processor 11 displays a list of secondary candidate items stored in the secondary candidate memory on the display device 17.

[0074] After completing the processing of ACT35 or ACT37, processor 11 waits for one item to be selected from the list. When the list of primary candidate items or secondary candidate items is displayed on display device 17, the operator operates input device 16 to select from the list an item to be placed on or removed from placement unit 21. If the item to be selected is not on the list, the operator operates input device 16 to indicate "no candidate."

[0075] If any item is selected from the list, processor 11 determines YES in ACT 38 and proceeds to ACT 39. In ACT 39, processor 11 records the date and time kept by clock 14, and the item ID, item name, quantity K, and status (+) or (-) of the selected item in history table 30. Incidentally, if a primary candidate item is selected, the item ID, item name, quantity K, and status (+) or (-) of the item stored in the primary candidate memory are recorded in history table 30. If a secondary candidate item is selected, the item ID, item name, quantity K, and status (+) or (-) of the item stored in the secondary candidate memory are recorded in history table 30.

[0076] On the other hand, if no item is selected, the processor 11 determines NO in ACT 38 and proceeds to ACT 40. The processor 11 notifies the user of a specific error in ACT 40. For example, the processor 11 lights or blinks an LED for a specific error provided in the notification device 18.

[0077] Thus, when the processing of ACT 39 or ACT 40 is completed, the processor 11 returns to ACT 3. Then, the processor 11 executes the processing from ACT 3 onwards in the same manner as described above.

[0078] Here, processor 11 functions as an identification means by executing the processes of ACT11 to ACT83 shown in Figures 6 to 9. Specifically, processor 11 functions as an estimation means by the process of ACT11. Processor 11 also functions as a calculation means by the process of ACT15. Then, processor 11 identifies the item placed on or removed from placement unit 21 by executing the primary search process of ACT16 based on the results of the estimation means and the calculation means.

[0079] Processor 11 also functions as a center of gravity determination means by the processing of ACT 31. Even if an item cannot be identified by the primary search processing, processor 11 identifies the item placed on or removed from placement unit 21 by executing secondary search processing of ACT 32 based on the result of the center of gravity determination means.

[0080] As described above, according to the object detection device 100 of this embodiment, an item is identified from the contact surface shape of the item estimated from the pressure distribution on the loading section 21 detected by the pressure sensor 3 and the actual weight of the item measured by the weight sensor 2, so that an item placed on or removed from the loading section 21 can be identified with high reliability.

[0081] Furthermore, the object detection device 100 determines the center of gravity of an object from the pressure distribution detected by the pressure sensor 3, and identifies the object from the position of this center of gravity. Even if there are multiple objects with similar contact surface shapes and the same unit weight, the positions of their centers of gravity will in most cases be different. Therefore, according to this embodiment, it is possible to identify the object with higher accuracy.

[0082] Furthermore, when the weight measured by the weight sensor 2 changes in a positive direction, the object detection device 100 sets the status to "+" and records the date and time as well as the item ID, item name, and quantity of the identified item in the history table 30, and when the measured weight changes in a negative direction, the object detection device 100 sets the status to "-" and records the date and time as well as the item ID, item name, and quantity of the identified item in the history table 30. Therefore, from the information stored in the history table 30, detailed information such as when and how many items were placed on the placement unit 21 and when and how many were removed from the placement unit 21 can be easily managed.

[0083] The object detection device 100 also includes an alarm device 18. This alarm device 18 notifies the user of a sensor error, a placement error, a specific error, etc. Therefore, the user can correctly recognize error information such as whether the pressure sensor 3 is malfunctioning, whether an object heavier than the specified weight has been placed on the placement unit 21, or whether an object outside the scope of management has been placed on the placement unit 21.

[0084] Although the embodiment of the object detection device has been described above, the embodiment is not limited to this.

[0085] For example, in the above embodiment, the primary candidate memory stores the item ID and item name of the item record. In another embodiment, the primary candidate memory stores the item ID, item name, and center of gravity distance of the item record. By doing so, the process of ACT76 in the secondary search process can be omitted.

[0086] In the above embodiment, if an item cannot be identified through the primary search process, the secondary search process is executed. In another embodiment, the process of ACT31, i.e., the process of calculating the center of gravity distance, is executed before the primary search process, for example, after the process of ACT15. Then, after determining YES in ACT59 of the primary search process shown in Figure 8, the processes of ACT77 and ACT78 of the secondary search process are executed. By doing so, it becomes possible to identify items with different center of gravity positions in a single search process, even among multiple items that have similar placement surface shapes and the same unit weight.

[0087] In the above embodiment, the information processing unit 10 includes the notification device 18. In another embodiment, the information processing unit 10 includes a wireless unit that wirelessly transmits error signals such as a sensor error, a placement error, and a specific error. The error signals are then transmitted to a wireless communication device such as a smartphone carried by the user, thereby notifying the user of various errors from the wireless communication device. This allows the user to quickly learn of the occurrence of an error even if they are not near the information processing unit 10.

[0088] In the above embodiment, the auxiliary storage device 13 of the information processing unit 10 stores the item database 20. In another embodiment, the item database 20 is stored in a computer on the cloud. The information processing unit 10 then accesses the item database 20 via a network such as the Internet. This allows for centralized management of data related to items placed in, for example, multiple stores or logistics warehouses, making management easier.

[0089] Although several embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be embodied in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their modifications are included within the scope of the invention and the scope of the inventions and their equivalents as defined in the claims. The following is the scope of the claims as originally filed: (1) a weight measuring means for measuring the weight of an object placed on the placement portion; a pressure detection means for detecting a pressure applied to a surface of the placement portion on which the object is placed; an identification means for identifying the object based on a change in weight measured by the weight measuring means before and after a change in pressure detected by the pressure detecting means and a shape of an area where the change in pressure has occurred; An object detection device comprising: (2) The object detection device according to (1), wherein the identifying means determines the center of gravity of the object from the distribution of the pressure detected by the pressure detecting means, and identifies the object from this center of gravity. (3) The object detection device according to (1) or (2), wherein the identification means identifies an object placed on the placement section when the measured weight changes in a positive direction, and identifies an object removed from the placement section when the measured weight changes in a negative direction. (4) a first notification means for notifying when the pressure detected by the pressure detection means reaches an upper limit value of a detection range; The object detection device according to any one of (1) to (3), further comprising: (5) a second notification means for notifying when the weight is detected by the weight measuring means without the pressure being detected by the pressure detecting means; The object detection device according to any one of (1) to (4), further comprising: (6) a computer for an object detection device including a weight measuring means for measuring the weight of an object placed on a placement section, and a pressure detecting means for detecting a pressure applied to a surface of the placement section on which the object is placed; an estimation means for estimating the shape of the contact surface of the object from an area where a change occurs in the pressure detected by the pressure detection means; a calculation means for calculating a weight of the object from a first weight measured by the weight measuring means before the change in pressure occurs and a second weight measured by the weight measuring means after the change in pressure occurs; an identification unit for identifying an object placed on or removed from the placement unit based on the contact surface shape and the weight; A program to function as a (7) An object detection method for an object detection device including a weight measuring means for measuring a weight of an object placed on a placement section, and a pressure detecting means for detecting a pressure applied to a surface of the placement section on which the object is placed, the method comprising: estimating a contact surface shape of the object from a region where a change in pressure detected by the pressure detection means occurs; calculating a weight of the object from a first weight measured by the weight measuring means before the change in pressure occurs and a second weight measured by the weight measuring means after the change in pressure occurs; An object detection method for identifying an object placed on or removed from the placement section based on the contact surface shape and the weight. [Explanation of symbols]

[0090] 1...sensor device, 2...weight sensor, 2...pressure sensor, 10...information processing unit, 11...processor, 12...main memory, 13...auxiliary storage device, 14...clock, 15...interface, 16...input device, 17...display device, 18...alarm device, 20...item database, 21...placing unit, 30...history table, 100...object detection device.

Claims

1. a weight measuring means for measuring the weight of an object placed on the placement portion; a pressure detection means for detecting a pressure applied to a surface of the placement portion on which the object is placed; an identification means for identifying the object based on a change in weight measured by the weight measuring means before and after a change in pressure detected by the pressure detecting means, the shape of the range in which the change in pressure has occurred, and the distance from the center of the shape of the range in which the change in pressure has occurred to the center of gravity of the pressure distribution in the range in which the change in pressure has occurred; An object detection device comprising:

2. 2. The object detection device according to claim 1, wherein the identification means identifies an object placed on the placement section when the measured weight changes in a positive direction, and identifies an object removed from the placement section when the measured weight changes in a negative direction.

3. a first notification means for notifying when the pressure detected by the pressure detection means reaches an upper limit value of a detection range; The object detection device according to claim 1 or 2, further comprising:

4. a second notification means for notifying when the weight is detected by the weight measuring means without the pressure being detected by the pressure detecting means; 4. The object detection device according to claim 1, further comprising:

5. a computer for an object detection device including a weight measuring means for measuring the weight of an object placed on a placement section, and a pressure detecting means for detecting a pressure applied to a surface of the placement section on which the object is placed; an estimation means for estimating the shape of the contact surface of the object from an area where a change occurs in the pressure detected by the pressure detection means; a calculation means for calculating a weight of the object from a first weight measured by the weight measuring means before the change in pressure occurs and a second weight measured by the weight measuring means after the change in pressure occurs; an identification means for identifying an object placed on or removed from the placement section based on the contact surface shape, the weight, and a center-of-gravity distance from the center of the contact surface shape to the center of gravity of the pressure distribution on the contact surface; A program to function as a

6. An object detection method for an object detection device including a weight measuring means for measuring a weight of an object placed on a placement section, and a pressure detecting means for detecting a pressure applied to a surface of the placement section on which the object is placed, the method comprising: estimating a contact surface shape of the object from a region where a change in pressure detected by the pressure detection means occurs; calculating a weight of the object from a first weight measured by the weight measuring means before the change in pressure occurs and a second weight measured by the weight measuring means after the change in pressure occurs; An object detection method for identifying an object placed on or removed from the placement section based on the contact surface shape, the weight, and the center of gravity distance from the center of the contact surface shape to the center of gravity of the pressure distribution on the contact surface.

Images