Detection methods, detection systems, storage media, and computer program products

Abstract

The present invention provides a detection method, detection system, storage medium, and computer program product that can more efficiently detect the cargo storage depth of a target column. [Solution] A laser radar is used to detect the cargo storage depth of a target column (11) in a shelf (1), and the laser radar is located on the side of the target column (11) away from the shipping side (111). Point cloud data is obtained by scanning the target column (11), wherein the scanning plane of the laser radar is positioned to intersect with the bottom surface of the target column (11) while scanning the target column (11), the distance between the cargo in the target column (11) and the laser radar is determined based on the point cloud data, and the cargo storage depth of the target column (11) is determined based on the distance. The cargo storage depth of the target column can be detected more efficiently.

Description

[Technical Field]

[0001] This disclosure relates to a detection method, a detection system, a storage medium, and a computer program product. [Background technology]

[0002] In the warehousing and logistics sector, it is often necessary to conduct inventory counts on each column of shelves, either regularly or irregularly, to understand the inventory status. In some related technologies, when conducting inventory counts on columns of shelves, a laser ranging sensor is used to detect the storage depth of the goods. A single laser beam emitted from the sensor measures along the direction of the column, obtaining the distance from the laser ranging sensor to the goods within the column, thereby further estimating the actual storage depth of the goods. [Overview of the project]

[0003] Upon investigation, it was found that the measurement method employed in related technologies requires the emission angle of the laser beam emitted from the sensor to be as parallel as possible to the column, and that the column must be extremely flat, in order for the laser beam to accurately reach the surface of the package being measured. However, in real-world scenarios, the column is long and therefore susceptible to deformation, making it difficult to ensure flatness, and the laser beam may be obstructed by the deformed column. For thin packages, if the emission angle of the laser beam is not sufficiently parallel to the column, or if there is obvious column deformation, the laser beam path may deviate from the package surface and fail to accurately reach the package. These situations make it more difficult to detect the storage depth.

[0004] In view of this, embodiments of the present disclosure provide a detection method, a detection system, a storage medium, and a computer program product that can more efficiently detect the cargo storage depth of a target column.

[0005] One aspect of the present disclosure provides a detection method for detecting the storage depth of goods in a target column on a shelf, comprising scanning the target column with a laser radar located on the side of the target column away from the shipping side to obtain point cloud data, wherein the scanning plane of the laser radar is positioned to intersect with the bottom surface of the target column while scanning the target column, determining the distance between the goods in the target column and the laser radar based on the point cloud data, and determining the storage depth of the goods in the target column based on the distance.

[0006] In some embodiments, the step of determining the distance between the cargo in the target column and the laser radar based on the point cloud data includes selecting point cloud data corresponding to the target column from the point cloud data, and determining the distance between the cargo in the target column and the laser radar based on each sampling angle and length value in the point cloud data corresponding to the target column.

[0007] In some embodiments, the step of selecting point cloud data corresponding to the target column from the point cloud data includes determining point cloud data from the point cloud data in which the absolute values ​​of the differences between the length values ​​corresponding to sampling angles that have continuously exceeded a predetermined number and the length values ​​corresponding to the initial count are all less than or equal to a predetermined length threshold, thereby obtaining a continuous segment record of the point cloud data, wherein the continuous segment record includes the sampling angle corresponding to the initial count, the length value corresponding to the initial count, and the number of continuous sampling points, and removing continuous segment records from the obtained continuous segment record in which the sampling angle and length value do not satisfy a predetermined correspondence relationship, thereby determining the point cloud data corresponding to the target column.

[0008] In some embodiments, the step of removing consecutive segment records from the obtained consecutive segment records in which the sampling angle and length value do not satisfy a predetermined correspondence includes querying each consecutive segment record from a correspondence lookup table of sampling angle and length value to determine consecutive segment records that do not satisfy a predetermined correspondence in the correspondence lookup table, and removing consecutive segment records that do not satisfy a predetermined correspondence in the correspondence lookup table.

[0009] In some embodiments, the step of removing from the obtained continuous segment records any continuous segment records in which the sampling angle and length value do not satisfy a predetermined correspondence includes removing from the obtained continuous segment records any continuous segment records of the sampling angle and length value corresponding to the support beam of the target column and the support beam of the adjacent column, respectively.

[0010] In some embodiments, the step of selecting point cloud data corresponding to the target column from the point cloud data includes further selecting point cloud data corresponding to the target column from the point cloud data based on the sampling angle and length values ​​corresponding to the support beams of the target column and the support beams of adjacent columns, respectively.

[0011] In some embodiments, the step of determining the distance between the cargo in the target column and the laser radar based on the point cloud data includes selecting point cloud data from the point cloud data whose sampling angles satisfy a predetermined angular range, wherein the target column is located within the predetermined angular range, and determining the distance between the cargo in the target column and the laser radar based on the sampling angle and the corresponding length value in the point cloud data that satisfy the predetermined angular range.

[0012] In some embodiments, the angle value corresponding to the predetermined angle range is less than 45°.

[0013] In some embodiments, the shelf includes multiple layers of columns, and the point cloud data satisfying the predetermined angular range includes point cloud data corresponding to the target column and point cloud data corresponding to columns adjacent to the target column whose bottom surface intersects the scanning plane, and the step of determining the distance between the luggage in the target column and the laser radar based on the point cloud data includes further selecting point cloud data corresponding to the target column from the point cloud data satisfying the predetermined angular range, and determining the distance between the luggage in the target column and the laser radar based on each sampling angle and length value in the point cloud data corresponding to the target column.

[0014] In some embodiments, the detection method further includes, in response to a command to perform detection on the target column, driving the laser radar to move to a position above the extension of the target column on the side away from the shipping side along the column's length, and performing a scanning operation at that position.

[0015] In some embodiments, the vertical distance of the laser radar's position when it performs a scanning operation relative to the extension line is less than or equal to the height of the target column.

[0016] One aspect of the present disclosure provides a detection system including a laser radar, a memory, and a processor coupled to the memory and configured to perform the detection method described above based on instructions stored in the memory.

[0017] One aspect of this disclosure provides a computer-readable storage medium in which, when executed by a processor, computer instructions for implementing the aforementioned detection method are stored non-temporarily.

[0018] One aspect of this disclosure provides a computer program product that, when executed by a processor, includes a computer program that implements the detection method described above.

[0019] According to the embodiments of the present disclosure, the laser radar scans the target column with a scanning plane intersecting the bottom surface of the target column. Since the laser radar can cover a large spatial range, the cargo in the column is easily captured by the laser radar, reducing the influence on cargo detection caused by factors such as column deformation and cargo thickness. Compared with single ranging data of laser ranging sensors in the related art, the point cloud data obtained by scanning with the laser radar has more detailed information, which is advantageous for eliminating interference to the cargo storage depth detection of the target column caused by structures such as other columns and support beams, thereby detecting the cargo storage depth of the target column more efficiently. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The drawings, which form a part of the specification, illustrate the embodiments of the present disclosure, and together with the specification, are used to interpret the principles of the present disclosure.

[0021] The present disclosure will be understood more clearly from the following detailed description with reference to the accompanying drawings. [Figure 1] It is a schematic diagram of a scene structure to which an embodiment of the detection method according to the present disclosure is applied. [Figure 2] It is a schematic diagram illustrating that the laser radar scans a shelf in an embodiment of the detection method according to the present disclosure. [Figure 3] It is a schematic diagram showing the flow of several embodiments of the detection method according to the present disclosure. [Figure 4] It is a schematic diagram showing the relationship between the scanning plane and the bottom surfaces of the target column and the adjacent column in an embodiment of the detection method according to the present disclosure. [Figure 5] It is a schematic diagram illustrating the principle of sorting cargo by the acquired continuous segment records in an embodiment of the detection method according to the present disclosure. [Figure 6] It is a schematic diagram illustrating the principle of eliminating other interferences except the cargo of the target column in an embodiment of the detection method according to the present disclosure. [Figure 7] It is a schematic diagram illustrating the processing of point cloud data corresponding to the support beam in an embodiment of the detection method according to the present disclosure. [Figure 8] FIG. 1 is a schematic structural diagram of several embodiments of the detection system according to the present disclosure.

[0022] Note that the dimensions of each part shown in the drawings are not drawn in actual proportional relationships. In addition, the same or similar reference numerals are assigned to the same or similar members. DETAILED DESCRIPTION OF EMBODIMENTS FOR CARRYING OUT THE INVENTION

[0023] Hereinafter, various exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. The descriptions of the exemplary embodiments are merely illustrative and should in no way be construed as any limitation on the present disclosure and its application or use. The present disclosure is not limited to the embodiments described in the specification and may be implemented in many different forms. These embodiments are provided so that the present disclosure will be thorough and complete, and will fully convey the scope of the present disclosure to those skilled in the art. Unless otherwise specified, the relative arrangements of members and steps, components of materials, mathematical formulas, and numerical values described in these embodiments are merely exemplary and should not be construed as limiting.

[0024] The terms "first", "second" and similar terms used in the present disclosure do not denote any particular order, number or importance, but are only used to distinguish different components. Similar words such as "comprise" and "contain" mean that the element preceding the word includes the elements listed after the word, and do not exclude the possibility that other elements may also be included. "upper", "lower", "left", "right" and the like are only used to represent relative positional relationships, and if the absolute position of the described object changes, this relative positional relationship will also change accordingly.

[0025] Where a particular device is described as being located between a first device and a second device, there may or may not be an intervening device between the particular device and the first device or the second device. Where a particular device is described as being connected to another device, the particular device may be directly connected to the other device without an intervening device, or it may not be directly connected to the other device with an intervening device.

[0026] All terms used in this disclosure (including technical or scientific terms) have the same meaning as those understood by those skilled in the art in the field to which this disclosure pertains, unless otherwise defined. Furthermore, terms defined in general dictionaries or similar publications should be interpreted as having the meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an idealized or overly formalized sense unless explicitly defined.

[0027] Techniques, methods, and apparatus known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and apparatus should be considered part of the specification.

[0028] In several related technologies, when inventorying columns on a shelf, a laser ranging sensor is used to detect the storage depth of the goods. A single laser beam emitted from the sensor measures along the direction of the column, obtaining the distance from the laser ranging sensor to the goods within the column, thereby further estimating the actual storage depth of the goods.

[0029] Upon investigation, it was found that the measurement method employed in related technologies requires the emission angle of the laser beam emitted from the sensor to be as parallel as possible to the column, and that the column must be extremely flat, in order for the laser beam to accurately reach the surface of the package being measured. However, in real-world scenarios, the column is long and therefore susceptible to deformation, making it difficult to ensure flatness, and the laser beam may be obstructed by the deformed column. For thin packages, if the emission angle of the laser beam is not sufficiently parallel to the column, or if there is obvious column deformation, the laser beam path may deviate from the package surface and fail to accurately reach the package. These situations make it more difficult to detect the storage depth.

[0030] In view of this, embodiments of the present disclosure provide a detection method, a detection system, a storage medium, and a computer program product that can more efficiently detect the cargo storage depth of a target column.

[0031] Figure 1 is a schematic diagram of a scene structure to which an embodiment of the detection method according to this disclosure is applied. Figure 2 is a schematic diagram showing a laser radar scanning a shelf in an embodiment of the detection method according to this disclosure. Figure 3 is a schematic diagram showing the flow of several embodiments of the detection method according to this disclosure.

[0032] Referring to Figures 1 to 3, embodiments of the present disclosure provide a detection method for detecting the cargo storage depth of a target column 11 in a shelf 1. The shelf 1 has at least one column for storing cargo. The target column 11 is the column to be detected in the shelf 1 and may be determined by a detection instruction. The cargo storage depth may be defined as the distance from a column entrance reference plane to the cargo closest to the column entrance in the column and may be used to determine the number and size of cargo that can be re-stored in the column.

[0033] Figure 1 shows an example of a shelf 1, which may include a plurality of pillars 12, which may be divided into at least two groups, and which may have one or more cross members 13 between at least two pillars 12 within each group. The shelf 1 may also include a plurality of columns, which may be arranged as multiple layers of columns, or further as multiple rows of columns. Cross members 13 provided between pillars 12 of different groups may support multiple columns as support beams.

[0034] Each column may, but is not limited to, a gravity-type column employing an inclined arrangement. The lower end of the column has a stopper for securing the load. This end may also serve as the shipping end 111 for shipping the load. The upper end of the column can serve as the column inlet for receiving the load.

[0035] The detection method of the embodiment of this disclosure includes steps S1, S2, and S3.

[0036] In step S1, the laser radar 2, located on the side of the target column 11 away from the shipping side 111, scans the target column 11 to obtain point cloud data, and while scanning the target column 11, the scanning surface 21 of the laser radar 2 is positioned to intersect with the bottom surface 112 of the target column 11.

[0037] The laser light emitted from the laser radar 2 can form a scanning surface 21, and based on the signals reflected from the object scanned on the scanning surface 21, corresponding point cloud data can be generated. The scanning surface 21 may be a 360° circular scanning surface or a sector scanning surface within a predetermined angular range. The laser radar 2 may employ various existing laser radars capable of forming the scanning surface 21, such as a mechanically rotating single-line laser radar, a micro-mechanical-electronic system laser radar, or a rotating mirror laser radar.

[0038] The laser radar 2 may be pre-installed at a position away from the shipping side 111 of the target column, or it may be moved to a position away from the shipping side 111 of the target column by another drive mechanism.

[0039] The laser radar 2 scans the target column 11 to obtain point cloud data, and can obtain point cloud data of the target column 11 and objects inside it while scanning, as well as point cloud data of other objects scanned on the scanning surface 21 other than the target column 11.

[0040] In step S2, the distance between the cargo in the target column 11 and the laser radar 2 is determined based on the point cloud data.

[0041] The point cloud data obtained by the laser radar 2 includes length values ​​corresponding to each sampling angle. Based on these length values, the straight-line distance from the laser radar 2 to the cargo in the target column 11 can be determined, or the distance from the laser radar 2 to the cargo in the target column 11 along the direction of extension of the target column 11 can be determined.

[0042] For example, when the laser radar 2 scans to the leading edge of the cargo closest to the column entrance in the target column 11 (i.e., the end face on the side closer to the column entrance), the resulting point cloud data includes the straight-line distance (i.e., length value) from the laser radar 2 to the end face. In some situations, for example, when the length of the target column 11 is considerably greater than its height, or when the perpendicular distance of the laser radar 2 to the extension of the column 11 is close to the height of the cargo, the distance from the laser radar 2 to the end face along the length of the target column 11 may not differ significantly from the straight-line distance from the laser radar 2 to the end face. In this case, the straight-line distance may be used as the distance between the cargo in the target column 11 and the laser radar 2.

[0043] If the distance from the laser radar 2 to the end face of the target column 11 along its length is taken as the distance between the cargo inside the target column 11 and the laser radar 2, then the straight-line distance from the laser radar 2 to the end face can be calculated using trigonometric functions.

[0044] In step S3, the cargo storage depth of the target column 11 is determined based on the distance.

[0045] The laser radar 2 is located outside the target column 11 and may be at a predetermined distance from the column entrance. Accordingly, the cargo storage depth of the target column 11 may be determined by first determining the distance between the cargo inside the target column 11 and the laser radar 2, and then subtracting the predetermined distance.

[0046] In this embodiment, the scanning surface 21 of the laser radar 2 is positioned to intersect with the bottom surface 112 of the target column 11. This allows the laser radar 2 to cover a large spatial range, making it easier for the cargo inside the column to be detected by the laser radar 2. This reduces the influence of factors such as column deformation and cargo thickness on cargo detection, thereby reducing the possibility of missed or false detections of cargo.

[0047] Compared to single distance measurement data from a laser rangefinder in related technologies, the point cloud data obtained by scanning with the laser radar 2 contains more detailed information, which is advantageous in removing interference from other structures such as other columns and support beams to the detection of the target column's cargo storage depth, thereby enabling more efficient detection of the target column's cargo storage depth.

[0048] Figure 4 is a schematic diagram showing the relationship between the scanning plane and the bottom surfaces of the target column and adjacent columns in an embodiment of the detection method according to this disclosure. Figures 4(a) and 4(b) schematically show three layers of columns, the second layer of which is the target column 11, and the first and third layers of which are adjacent columns 11a of the target column 11. Here, the adjacent columns 11a of the target column 11 include columns that are one layer adjacent (i.e., directly adjacent) and also include columns that are two or more layers adjacent. The target column 11 and the adjacent columns 11a may store luggage 114.

[0049] In some column implementation configurations, the column may be surrounded by beams on both sides, thus having a partially hollow bottom surface (indicated by a dashed line). From the viewpoint where the laser radar 2 is facing the target column 11, the bottom surfaces of each layer column in Figures 4(a) and 4(b), and the scanning plane 21 of the laser radar 2 are both represented as straight line segments. The scanning plane 21 and the bottom surface 112 of the target column 11 may intersect diagonally as shown in Figure 4(a), or perpendicularly as shown in Figure 4(b), with the intersection point located on the bottom surface 112 indicated by the dashed line. The scanning plane 21 may be located in the center of the column, or it may be off-center to one side, as long as it can scan the contents of the column.

[0050] The scanning plane 21 may also intersect the reference plane perpendicular to the column length direction ld at an oblique angle or perpendicularly. For a package 114 having a rectangular parallelepiped shape as shown in Figures 4(a) and 4(b), its vertical and horizontal surfaces are approximately parallel to the column bottom surface, and the front surface close to the laser radar 2 is approximately parallel to the reference plane perpendicular to the column length direction. Therefore, the scanning plane 21 also passes through the vertical, horizontal, and front surfaces of the package 114, allowing the package 114 to be scanned accurately.

[0051] As can be seen from Figures 4(a) and 4(b), the scanning plane 21 not only intersects with the bottom surface 112 of the target column 11, but also with the bottom surfaces 112a of multiple adjacent columns 11a in the same row. This allows for the acquisition of point cloud data of the cargo in the target column 11, as well as point cloud data of the cargo in the adjacent columns 11a.

[0052] Referring to Figure 2, in some embodiments, step S2 is to select point cloud data from the point cloud data whose sampling angle satisfies a predetermined angular range AR, and to determine the distance between the cargo 114 in the target column 11 and the laser radar 2 based on the target column 11 being located in the predetermined angular range AR and the length values ​​corresponding to the sampling angles in the point cloud data that satisfies the predetermined angular range AR.

[0053] Of the point cloud data acquired by the laser radar 2, only the length values ​​corresponding to some sampling angles may be relevant to the target column 11. By selecting point cloud data based on a predetermined angular range AR and discarding point cloud data outside the predetermined angular range AR before subsequent processing, the amount of data processing is reduced and detection efficiency is improved.

[0054] In Figure 2, a predetermined angular range AR is enclosed by two opposing arc arrows, and it can be seen that the laser beam based on this predetermined angular range AR covers the target column 11 and several adjacent columns 11a of the target column 11.

[0055] The position and covered angle values ​​of the predetermined angular range AR may be set according to the position of the laser radar 2 relative to the target column 11 during scanning, and the target column 11 must be positioned within the predetermined angular range AR. The angle values ​​corresponding to the predetermined angular range AR are selectively set to less than 45°. This further reduces the amount of data to be processed and further improves detection efficiency.

[0056] In some embodiments, by setting a narrow predetermined angular range (AR), the point cloud data obtained by the laser radar 2 may include only the point cloud data corresponding to the target column 11. This reduces the amount of data processing required and minimizes interference between the point cloud data corresponding to other columns and the point cloud data corresponding to the target column.

[0057] Referring to Figure 2, in some embodiments, the shelf 1 may include multiple layers of columns, and the point cloud data satisfying the predetermined angular range AR may include point cloud data corresponding to the target column 11 and point cloud data corresponding to the column among the adjacent columns 11a of the target column 11 whose bottom surface 112a intersects the scanning plane 21.

[0058] In Figure 4, the bottom surfaces 112a of the adjacent columns 11a above and below the target column 11 also intersect with the scanning plane 21. Therefore, the laser radar 2 can acquire point cloud data corresponding to these two adjacent columns 11a. This reduces the requirement for precision in the installation position of the laser radar 2 and reduces the possibility of detection failures caused by the predetermined angular range AR not covering or not completely covering the target column.

[0059] Point cloud data that satisfies a predetermined angular range AR includes both point cloud data corresponding to the target column 11 and point cloud data corresponding to the adjacent column 11a. Therefore, in some embodiments, the step of determining the distance between the luggage 114 in the target column 11 and the laser radar 2 based on the point cloud data includes further selecting point cloud data corresponding to the target column 11 from the point cloud data that satisfies the predetermined angular range AR, and determining the distance between the luggage 114 in the target column 11 and the laser radar 2 based on each sampling angle and length value in the point cloud data corresponding to the target column 11.

[0060] After acquiring point cloud data that satisfies a predetermined angular range AR, it is determined from this point cloud data which sampling angle and length value corresponds to the cargo 114 in the target column 11. This eliminates interference from point cloud data corresponding to adjacent columns 11a, thereby obtaining a more accurate distance between the cargo 114 in the target column 11 and the laser radar 2.

[0061] To reduce the amount of data to be processed, the step of selecting point cloud data corresponding to the target column 11 may be applied to point cloud data that satisfies a predetermined angular range AR. However, in some situations, for example, when the point cloud data for all angular ranges obtained by the laser radar 2 is finite or has sufficient data processing capacity, the step of selecting point cloud data corresponding to the target column 11 may be applied to point cloud data for all angular ranges obtained by the laser radar 2. For this reason, in some embodiments, the step of determining the distance between the luggage 114 in the target column 11 and the laser radar 2 based on the point cloud data in step S2 may include selecting point cloud data corresponding to the target column 11 from the point cloud data and determining the distance between the luggage 114 in the target column 11 and the laser radar 2 based on each sampling angle and length value in the point cloud data corresponding to the target column 11. Figure 5 is a schematic diagram showing the principle of luggage sorting by acquired continuous segment recording in an embodiment of the detection method according to this disclosure. As shown in Figure 5, the laser beam of the laser radar 2 may form multiple sampling points on the leading surface of the package 114, and obtain length values ​​corresponding to multiple sampling angles. For a package with a regular shape, its leading surface is continuous and regular, and the laser beam is nearly perpendicular to the leading surface of the package 114, or at a relatively small angle, so the length values ​​in the multiple point cloud data obtained on the leading surface of the package 114 will also be relatively close. Based on this principle, the target package can be identified by the close proximity of the length values ​​corresponding to multiple consecutive sampling angles in the point cloud data.

[0062] In some embodiments, the step of further selecting point cloud data corresponding to the target column 11 from the point cloud data includes determining point cloud data from the point cloud data in which the absolute values ​​of the differences between the length values ​​corresponding to sampling angles that have continuously exceeded a predetermined number and the length values ​​corresponding to the initial count are all less than or equal to a predetermined length threshold, thereby obtaining a continuous segment record of the point cloud data, wherein the continuous segment record includes the sampling angle corresponding to the initial count, the length value corresponding to the initial count, and the number of continuous sampling points, and removing continuous segment records from the obtained continuous segment record in which the sampling angle and length value do not satisfy a predetermined correspondence relationship, thereby determining the point cloud data corresponding to the target column 11.

[0063] Here, the interval between adjacent sampling angles may be determined by the resolution of the laser radar, and each sampling angle may correspond to a length value obtained by the laser radar 2. The absolute value of the difference between the length values ​​corresponding to more than a predetermined number of adjacent sampling angles may be calculated, and if the absolute value of the difference is less than or equal to a predetermined length threshold, a continuous segment recording cs of the point cloud data may be determined from this group of point cloud data. The continuous segment recording here may include the sampling angle corresponding to the initial count in the point cloud data of this group, the length value corresponding to the initial count, and the number of continuous sampling points.

[0064] For example, for a mechanically rotating single-line laser radar, the current sampling angle A in the direction of rotation of the laser beam is n Take the corresponding length value L n And the next sampling angle A n+1 (that is, A n Length value L (where +a0 is a predetermined interval of the sampling angle) n+1 If the absolute value of the difference is less than or equal to a predetermined length threshold, the sampling angle and length value may be set to sampling angle A0 and length value L0 corresponding to the initial count, and the number of continuous sampling points S may be set to 1. At this time, the next sampling angle is selected. At this time, the current sampling angle A n This is the A from the previous operation.n+1 and is a length value L n is the L from the previous operation n+1 and accordingly, for the next sampling angle A n+1 the corresponding length value L n+1 calculates the absolute value of the difference between it and the length value L0 corresponding to the initial count, and if the absolute value of the difference is still less than or equal to a predetermined length threshold, the number of consecutive sampling points S is set to 2, and the operation corresponding to the next sampling angle is subsequently performed. The increment of the count of the number of consecutive sampling points S is stopped until the absolute value of the difference exceeds the predetermined length threshold.

[0065] At this time, if the number of consecutive sampling points S exceeds a predetermined number N, a continuous segment record cs is determined based on the point cloud data of this group and the number of consecutive sampling points S, and the continuous segment record cs may include the sampling angle A0 corresponding to the initial count, the length value L0 corresponding to the initial count, and the number of consecutive sampling points S. If the number of consecutive sampling points S does not exceed the predetermined number N, it indicates that the point cloud data of this group does not correspond to the continuous surface of one piece of cargo, so it is not determined as the continuous segment record cs. The setting of the predetermined number N is related to factors such as the height of the detection target cargo, the angular resolution of the laser radar, and the farthest detection distance.

[0066] With reference to Figure 5, in some embodiments, the vertical distance h of the position where the laser radar 2 is located when performing the scanning operation, relative to the extension line 113 along the column length direction ld of the target column 11, is less than or equal to the height H of the target column 11.

[0067] In Figure 5, the laser radar 2 is located outside the target column 11, and the vertical distance h with respect to the extension line 113 of the bottom surface 112 is less than the height H of the target column 11. This vertical distance h may be 1 / 4, 1 / 3, 1 / 2, 2 / 3, etc., of the height H. For target columns that mainly store thin packages (e.g., cartridges), the vertical distance h may be set to a size close to the height of the package. This makes it possible to make the absolute difference in length values ​​in the point cloud data of the leading edge of the package inside the target column 11 closer, making it easier to identify the package inside the target column 11.

[0068] Figure 6 is a schematic diagram illustrating the principle of removing interference other than the cargo on the target column in an embodiment of the detection method according to this disclosure. Referring to Figure 6, for a structure in which each layer column has a hollow section, the point cloud data corresponding to the cargo 114 in the target column 11 and the adjacent column 11a can all form continuous segment recordings.

[0069] In Figure 6, objects labeled A, B, C, D, and E (which may be luggage, but are not limited to luggage) correspond to continuous segment records cs1, cs2, cs3, cs4, and cs5, respectively. The continuous segment record cs1 corresponding to the object labeled A in target column 11 does not differ significantly in length from the continuous segment record cs2 corresponding to the object labeled B in the adjacent column 11a. However, the sampling angles corresponding to each continuous segment record are clearly different. Therefore, the length value and sampling angle of continuous segment record cs2 do not satisfy the predetermined correspondence between the length value and sampling angle in the continuous segment records of target column 11. As a result, continuous segment record cs2 whose sampling angle does not satisfy the target column 11 can be removed.

[0070] For objects marked with E in target column 11, the corresponding continuous segment recording cs5 and the continuous segment recording cs3 corresponding to objects marked with C in adjacent column 11a have relatively close sampling angles. However, the length value of continuous segment recording cs5 is clearly different from the length value of continuous segment recording cs3. Therefore, the length value and sampling angle of continuous segment cs3 do not satisfy the predetermined correspondence between the length value and sampling angle in the continuous segment recording of target column 11. This makes it possible to remove continuous segment recording cs3 whose sampling angle does not satisfy the target column 11.

[0071] For objects marked D in the adjacent column 11a, the corresponding sampling angle is almost entirely outside the range of the target column 11. Therefore, the length value and sampling angle of the corresponding continuous segment recording cs4 clearly do not satisfy the predetermined correspondence between the length value and sampling angle in the continuous segment recording of the target column 11. This makes it possible to remove continuous segment recording cs4 whose sampling angle does not meet the requirements of the target column 11.

[0072] This allows for the removal of continuous segment records from the obtained point cloud data after obtaining continuous segment records in which the sampling angle and length value do not satisfy a predetermined correspondence. This efficiently removes interference from point cloud data of other columns to the detection of luggage within the target column when determining the point cloud data corresponding to the target column 11.

[0073] To facilitate selection, a lookup table of correspondence between sampling angle and length value that matches the target column 11 may be set in advance. Based on this, the step of excluding consecutive segment records from the obtained consecutive segment records in which the sampling angle and length value do not satisfy a predetermined correspondence may include querying each consecutive segment record from the lookup table of correspondence between sampling angle and length value to determine consecutive segment records that do not satisfy a predetermined correspondence in the lookup table, and removing consecutive segment records that do not satisfy a predetermined correspondence in the lookup table.

[0074] Here, the records in the correspondence lookup table may be obtained by combining the results of multiple actual measurements. For example, the relationship between the sampling angle and length value corresponding to the cargo in the target column at different storage depths may be determined by loading a small amount of cargo into the column or loading a full amount of cargo. The correspondence lookup table may also obtain a record of the correspondence between each sampling angle and length value through calculation.

[0075] Figure 7 is a schematic diagram showing the processing of point cloud data corresponding to support beams in an embodiment of the detection method according to the present disclosure. In Figure 7, for a structure in which the columns of each layer have hollow sections, the support beam 115 of the target column 11 and the support beam 115a of the adjacent column 11a can both be scanned by the scanning plane 21 of the laser radar 2, and the point cloud data of the support beams 115 and 115a having a predetermined height can also form a continuous segment recording.

[0076] In Figure 7, it can be seen that there are two support beams 115 supporting the target column 11, which can form continuous segment records cs13 and cs15, and that the two support beams 115a of the adjacent column 11a above the target column 11 can form continuous segment records cs14 and cs16. The objects labeled F and G in the target column 11 and the adjacent column 11a correspond to continuous segment records cs11 and cs12, respectively.

[0077] Since the mounting position of the support beams relative to the columns is fixed, the sampling angle and length values ​​corresponding to the support beams may be obtained in advance as a basis for data filtering. For this reason, in some embodiments, the step of removing continuous segment records from the obtained continuous segment records in which the sampling angle and length values ​​do not satisfy a predetermined correspondence includes removing the continuous segment records of the sampling angle and length values ​​corresponding to the support beam 115 of the target column 11 and the support beam 115a of the adjacent column, respectively, from the obtained continuous segment records.

[0078] Even in the specific situation where the leading edge of the cargo in the target column 11 and the leading edge of the support beam 115 are on the same plane, the sampling angle and length value corresponding to the support beam 115 can be used to eliminate interference, and the continuous segment recording corresponding to the leading edge of the cargo can be clearly determined. This makes it possible to easily eliminate interference from the support beams 115 and 115a on the detection of cargo in the target column 11, thereby improving the accuracy of column storage depth detection.

[0079] Referring to Figure 7, and considering that each column has support beams on both its lower and upper sides, the sampling angle corresponding to the internal load of the target column 11 is almost exactly between the sampling angles corresponding to the support beam 115 on the side of the target column 11 closest to the laser radar 2 and the support beam 115a of the adjacent column 11a above it. This can be used as the basis for determining the point cloud data corresponding to the target column.

[0080] Therefore, in some embodiments, the step of selecting point cloud data corresponding to the target column 11 from the point cloud data may include further selecting point cloud data corresponding to the target column 11 from the point cloud data based on the sampling angle and length value corresponding to the support beam 115 of the target column 11 and the support beam 115a of the adjacent column, respectively. This makes it easy to remove point cloud data at angles other than the support beams 115 and 115a, and allows for faster and easier selection of point cloud data corresponding to the target column 11.

[0081] In the above embodiment, the basis for selecting point cloud data corresponding to the target column 11 may be point cloud data that satisfies a predetermined angular range AR, or it may be point cloud data for all angular ranges obtained by the laser radar 2.

[0082] In the embodiments described above, with reference to Figure 2, in some embodiments, the detection method further includes, in response to a command to detect the target column 11, driving the laser radar 2 to move to a position above the extension line 113 on the side away from the shipping side 111 along the column length direction ld, and performing a scanning operation at that position.

[0083] Referring to Figure 2, the laser radar 2 may be mounted on the drive mechanism 5. The drive mechanism 5 can drive the laser radar 2 to move to an appropriate detection position on the target column 11. The drive mechanism 5 may be an XYZ 3-axis linear module, an articulated robot, or the like.

[0084] Figure 8 is a schematic diagram of the structure of several embodiments of the detection system according to the present disclosure. Referring to Figure 8, and based on the detection methods of each embodiment described above, embodiments of the present disclosure provide a detection system including a laser radar 2, a memory 3, and a processor 4 coupled to the memory. The processor 4 is configured to execute the detection method of any one of the embodiments described above based on instructions stored in the memory.

[0085] Memory 3 may be high-speed RAM memory, non-volatile memory, etc., and memory 3 may be a memory array, or it may be in blocks, and the blocks may be combined into a virtual volume with a certain regularity. The processor 4 may be a central processing unit CPU, an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the detection method of the Disclosure.

[0086] Embodiments of the present disclosure further provide a computer-readable storage medium which, when executed by a processor, non-temporarily stores computer instructions that implement the detection method of any one of the embodiments described above.

[0087] The computer-readable medium as used herein may be a computer-readable signal medium or a computer-readable storage medium or any combination thereof. The computer-readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device or any combination thereof. The computer-readable storage medium may include, as an example, an electrical connection having one or more wires, a portable computer disk, a hard disk, RAM, ROM, Erasable Programmable Read-Only Memory (EPROM), or flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0088] In some embodiments of this disclosure, the computer-readable storage medium may be any tangible medium containing or storing a program, which can be used in or in combination with an instruction execution system, apparatus, or device. In some embodiments of this disclosure, the computer-readable signaling medium may contain a data signal propagated in the baseband or a data signal partially propagated on a carrier wave, which contains computer-readable program code. The data signal propagated in this manner may take various forms, including electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signaling medium may further be any computer-readable medium other than the computer-readable storage medium, which can transmit, propagate, or transmit a program used in or in combination with an instruction execution system, apparatus, or device. The program code contained in the computer-readable medium can be transmitted on any suitable medium, which may include wires, optical cables, radio frequencies (RF), or any suitable combination thereof.

[0089] Embodiments of the present disclosure further provide a computer program product that, when executed by a processor, implements the detection method of any one of the embodiments described above.

[0090] Computer program code can be written using one or more programming languages ​​or a combination thereof. These programming languages ​​may include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as general procedural programming languages ​​such as C or similar languages. The program code can run entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, it can be connected to the user's computer via any network, including a LAN or WAN, or to an external computer (for example, via the Internet using an Internet service provider).

[0091] Up to this point, each embodiment of the present disclosure has been described in detail. Some details known in the art have not been described so as not to obstruct the concept of the present disclosure. Those skilled in the art will be able to fully understand from the above description how to implement the technical invention disclosed herein.

[0092] As is customary, several specific embodiments of this disclosure have been described in detail, but as those skilled in the art will understand, these examples are for illustrative purposes only and not to limit the scope of this disclosure. Those skilled in the art will understand that they may modify the above embodiments or replace some technical features with equivalent ones without departing from the scope and spirit of this disclosure. The scope of this disclosure is set forth in the appended claims.

Claims

1. A detection method for detecting the storage depth of cargo in a target column (11) on a shelf (1), The method involves obtaining point cloud data by scanning the target column (11) with a laser radar (2) located on the side of the target column (11) away from the shipping side (111), wherein the scanning surface (21) of the laser radar (2) is positioned to intersect with the bottom surface (112) of the target column (11) while scanning the target column (11). Based on the point cloud data, the distance between the cargo (114) in the target column (11) and the laser radar (2) is determined. A detection method comprising determining the cargo storage depth of the target column (11) based on the distance.

2. The step of determining the distance between the cargo (114) in the target column (11) and the laser radar (2) based on the point cloud data is as follows: Selecting point cloud data corresponding to the target column (11) from the aforementioned point cloud data, The detection method according to claim 1, further comprising determining the distance between the luggage (114) in the target column (11) and the laser radar (2) based on each sampling angle and length value in the point cloud data corresponding to the target column (11).

3. The step of selecting point cloud data corresponding to the target column (11) from the point cloud data is as follows: From the point cloud data, a continuous segment record (cs) of the point cloud data is obtained by determining point cloud data in which the absolute difference between the length value corresponding to a sampling angle that continuously exceeds a predetermined number and the length value corresponding to the initial count is all less than or equal to a predetermined length threshold, wherein the continuous segment record (cs) includes the sampling angle corresponding to the initial count, the length value corresponding to the initial count, and the number of continuous sampling points. The detection method according to claim 2, further comprising removing from the obtained continuous segment recordings (cs) any continuous segment recordings (cs) in which the sampling angle and length value do not satisfy a predetermined correspondence, and determining point cloud data corresponding to the target column (11).

4. The step of removing continuous segment recordings (cs) from the obtained continuous segment recordings (cs) in which the sampling angle and length value do not satisfy a predetermined correspondence is: The process involves querying each consecutive segment record (cs) from a lookup table of correspondence between sampling angle and length value, and determining consecutive segment records (cs) that do not satisfy a predetermined correspondence in the lookup table. The detection method according to claim 3, further comprising removing consecutive segment records (cs) that do not satisfy a predetermined correspondence in the correspondence lookup table.

5. The step of removing from the obtained continuous segment recordings (cs) any continuous segment recordings (cs) in which the sampling angle and length value do not satisfy a predetermined correspondence is: The detection method according to claim 3, further comprising removing the continuous segment recordings (cs) of sampling angle and length values ​​corresponding to the support beam (115) of the target column (11) and the support beam (115a) of the adjacent column (11a), respectively, from the obtained continuous segment recordings (cs).

6. The step of selecting point cloud data corresponding to the target column (11) from the point cloud data is as follows: The detection method according to claim 2, further comprising selecting point cloud data corresponding to the target column (11) from the point cloud data based on the sampling angle and length value corresponding to the support beam (115) of the target column (11) and the support beam (115a) of the adjacent column (11a), respectively.

7. The step of determining the distance between the cargo (114) in the target column (11) and the laser radar (2) based on the point cloud data is as follows: From the point cloud data, select point cloud data whose sampling angle satisfies a predetermined angular range (AR), wherein the target column (11) is located within the predetermined angular range (AR), The detection method according to claim 1, further comprising determining the distance between the luggage (114) in the target column (11) and the laser radar (2) based on the sampling angle and corresponding length value in the point cloud data that satisfies the predetermined angular range (AR).

8. The detection method according to claim 7, wherein the angle value corresponding to the predetermined angle range (AR) is less than 45°.

9. The shelf (1) includes multiple layers of columns, and the point cloud data satisfying the predetermined angular range (AR) includes point cloud data corresponding to the target column (11) and point cloud data corresponding to the column whose bottom surface intersects the scanning plane (21) among the adjacent columns (11a) of the target column (11). The step of determining the distance between the cargo (114) in the target column (11) and the laser radar (2) based on the point cloud data is as follows: From the point cloud data that satisfies the predetermined angular range (AR), further select point cloud data corresponding to the target column (11), The detection method according to claim 7, further comprising determining the distance between the luggage (114) in the target column (11) and the laser radar (2) based on each sampling angle and length value in the point cloud data corresponding to the target column (11).

10. The detection method according to claim 1, further comprising driving the laser radar (2) to move to a position above the extension line (113) on the side away from the shipping side (111) along the column length direction (ld), in response to a command to detect the target column (11), and performing a scanning operation at that position.

11. The detection method according to claim 10, wherein the distance of the position of the laser radar (2) when it performs a scanning operation, in the direction perpendicular to the extension line (113), is less than or equal to the height of the target column (11).

12. Laser radar (2), Memory (3) and A detection system comprising a processor (4) coupled to the memory and configured to perform the detection method according to any one of claims 1 to 11 based on instructions stored in the memory.

13. A computer-readable storage medium that non-temporarily stores computer instructions that, when executed by a processor, realize the detection method described in any one of claims 1 to 11.

14. A computer program product comprising a computer program that, when executed by a processor, realizes the detection method described in any one of claims 1 to 11.

Images