Luggage area identification method, electronic equipment and storage medium

Abstract

The invention provides a luggage area identification method, electronic equipment and a storage medium, and relates to the technical field of luggage area identification, and the method comprises the steps: obtaining an initial point cloud coordinate of each initial point in a point cloud image corresponding to a luggage barrow parking area; determining each middle point from all the initial points according to a preset coordinate of the luggage barrow area; determining each target point corresponding to the luggage according to the height difference between the middle point and the bottom plate of the luggage barrow, and further determining a luggage area according to each target point; the method is based on the point cloud image corresponding to the luggage barrow parking area, the calculation amount is small in the whole luggage area recognition process, and therefore the luggage area recognition efficiency is high.

Description

Technical Field

[0001] The present invention relates to the technical field of luggage area recognition, and in particular, to a luggage area recognition method, an electronic device, and a storage medium. Background Art

[0002] In the civil aviation field, luggage handling is a major challenge in the modern aviation industry. Due to the increasing passenger flow at airports, the number of passengers' luggage is also rising continuously. For luggage handling, in order to improve the handling efficiency of luggage, some airports use automated luggage handling equipment to transport luggage from the conveyor belt to the luggage cart, and then transport it to the corresponding flight's aircraft by the luggage cart for loading and consignment. Before the automated handling equipment transports the luggage to the luggage cart, it is necessary to identify the luggage area on the luggage cart to determine the subsequent luggage stacking position. In the prior art, a large model is used to identify the luggage area from the luggage cart image. However, this method has a large amount of calculation, and the luggage area recognition efficiency and accuracy are relatively low. Summary of the Invention

[0003] In view of the above technical problems, the technical solution adopted by the present invention is as follows:

[0004] According to a first aspect of the present application, there is provided a luggage area recognition method, the method comprising the following steps:

[0005] S100, obtaining the initial point cloud coordinates of each initial point in the point cloud image corresponding to the luggage cart parking area, so as to obtain an initial point coordinate list A=(A 1 , A 2 , …, A i , …, A n ), i = 1, 2, …, n; wherein, A i is the initial point coordinate of the i-th initial point corresponding to the luggage cart parking area, and n is the number of initial points in the point cloud image corresponding to the luggage cart parking area.

[0006] S200, determining each intermediate point from all the initial points according to the coordinates of the preset luggage cart area, so as to obtain an intermediate point coordinate list B=(B 1 , B 2 , …, B j , …, B m ), j = 1, 2, …, m; wherein, B j is the determined j-th intermediate point, and m is the number of determined intermediate points; B j =(B j，x , B j，y , B j，z ); B j，x is the X-axis coordinate of the j-th intermediate point, and B j，y is the Y-axis coordinate of the j-th intermediate point, Bj，z is the Z-axis coordinate of the j-th intermediate point.

[0007] S300. Traverse B. If YZ min <|B j，z -PB z |<YZ max , then determine B j as the target point to obtain the target point list C = (C 1 , C 2 , …, C p , …, C q ), where p = 1, 2, …, q; among them, C p is the p-th target point determined, and q is the number of target points determined; PB z is the preset height of the luggage cart floor, and YZ min is the preset first height difference threshold, and YZ max is the preset second height difference threshold.

[0008] S400. Determine the luggage area according to C.

[0009] According to another aspect of the present application, there is also provided a non-transitory computer-readable storage medium storing at least one instruction or at least one program segment, and the at least one instruction or at least one program segment is loaded and executed by a processor to implement the above-mentioned luggage area recognition method.

[0010] According to another aspect of the present application, there is also provided an electronic device including a processor and the above-mentioned non-transitory computer-readable storage medium.

[0011] The present invention has at least the following beneficial effects:

[0012] The luggage area recognition method of the present invention obtains the initial point cloud coordinates of each initial point in the point cloud image corresponding to the luggage cart parking area; determines each intermediate point from all the initial points according to the coordinates of the preset luggage cart area; determines each target point corresponding to the luggage according to the height difference between the intermediate point and the luggage cart floor, and further determines the luggage area according to each target point; the method in the present invention is based on the point cloud image corresponding to the luggage cart parking area, and the calculation amount is small during the entire luggage area recognition process. Therefore, the recognition efficiency of the luggage area is high.

[0013] Furthermore, in the luggage area recognition method of the present invention, the point cloud coordinates of each initial point in the point cloud image of the luggage cart parking area can be obtained by a lidar, and the accuracy of the point cloud coordinates is very high; therefore, the accuracy of the subsequent recognized luggage area is also high. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for description in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0015] Figure 1 It is a flowchart of the luggage area recognition method provided by the embodiment of the present invention. Specific implementation manners

[0016] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present invention.

[0017] It should be noted that based on this disclosure, those skilled in the art should understand that one aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects described herein can be used to implement the device and / or practice the method. In addition, this device and / or practice this method can be implemented using other structures and / or functions in addition to one or more of the aspects described herein.

[0018] Embodiment 1:

[0019] The following will refer to Figure 1 the flowchart of the luggage area recognition method shown to introduce a luggage area recognition method.

[0020] S100. Obtain the initial point cloud coordinates of each initial point in the point cloud image corresponding to the luggage cart parking area to obtain an initial point coordinate list A=(A 1 , A 2 , …, A i , …, A n ), where i = 1, 2, …, n; where A i is the initial point coordinate of the i-th initial point corresponding to the luggage cart parking area, and n is the number of initial points in the point cloud image corresponding to the luggage cart parking area.

[0021] In this embodiment, the luggage carried by the robotic arm from the luggage conveyor needs to be stacked onto the luggage cart; there is a preset parking area for the luggage cart, and a point cloud image acquisition device, such as a lidar or a depth camera, is installed above the parking area of the luggage cart; the point cloud image of the parking area of the luggage cart can be obtained; it should be noted that the area occupied by the parking area of the luggage cart is larger than the actual area occupied by the luggage cart, so as to ensure that the image of the luggage cart can be completely captured.

[0022] S200. Determine each intermediate point from all the initial points according to the coordinates of the preset luggage cart area, so as to obtain the intermediate point coordinate list B = (B 1 , B 2 , …, B j , …, B m ), where j = 1, 2, …, m; among them, B j is the determined j-th intermediate point, and m is the number of determined intermediate points; B j = (B j，x , B j，y , B j，z ); B j，x is the X-axis coordinate of the j-th intermediate point, B j，y is the Y-axis coordinate of the j-th intermediate point, and B j，z is the Z-axis coordinate of the j-th intermediate point.

[0023] In this embodiment, step S200 may include the following steps:

[0024] S210. Obtain the maximum X-axis coordinate PB x，max , minimum X-axis coordinate PB x，min , maximum Y-axis coordinate PB y，max and minimum Y-axis coordinate PB y，min of the preset luggage cart area.

[0025] After the luggage cart is parked in the preset position, the maximum X-axis coordinate, minimum X-axis coordinate, maximum Y-axis coordinate and minimum Y-axis coordinate of the luggage cart are PB x，max , PB x，min , PB y，max and PB y，min respectively.

[0026] S220. If PB x，min ≤ B j，x ≤ PB x，max and PB y，min ≤ B j，y ≤ PB y，max , then determine B j as the intermediate point.

[0027] In this embodiment, the luggage cart parking area is larger than the actual area occupied by the luggage cart. Therefore, it is necessary to delete the point cloud outside the luggage cart in the point cloud image corresponding to the luggage cart parking area, and only retain the point cloud corresponding to the luggage cart to reduce the computational complexity of subsequent luggage area recognition and improve the computational efficiency.

[0028] S300, traverse B. If YZ min <|B j，z -PB z |<YZ max , then determine B j as the target point to obtain the target point list C = (C 1 , C 2 , …, C p , …, C q ), where p = 1, 2, …, q; among them, C p is the p-th target point determined, and q is the number of target points determined; PB z is the preset height of the luggage cart bottom plate, and YZ min is the preset first height difference threshold, and YZ max is the preset second height difference threshold.

[0029] In this embodiment, PB z can be determined through the following steps:

[0030] S310, obtain the initial height of each luggage cart to obtain the luggage cart initial height list CA = (CA 1 , CA 2 , …, CA c , …, CA d ), where c = 1, 2, …, d; among them, CA c is the initial height of the c-th luggage cart, and d is the number of luggage carts.

[0031] For each luggage cart in the airport, its height is designed according to a preset height. However, during the use of the luggage cart, there will be wear and tear, and its height will change to a certain extent; the height of each known luggage cart can be obtained through traversal to obtain CA.

[0032] S320, according to CA, determine the initial height volatility μ corresponding to CA = (1 / d) × ∑ d c＝1 (CA c -((1 / d) × ∑ d c＝1 CA c )) 2 .

[0033] S330, if μ < μ’, then determine PB z= (1 / d) × ∑ d c＝1 CA c 。

[0034] In this embodiment, if μ is the variance corresponding to CA, the larger μ is, the higher the data difference within CA is; the smaller μ is, the smaller the data difference within CA is. If μ < μ', the mean value of the initial heights of the luggage carts in CA can be directly used to determine PB z 。

[0035] Further, after step S330, the method further includes the following steps:

[0036] S340, if μ ≥ μ', then delete the largest several initial heights of the luggage carts and the smallest several initial heights of the luggage carts in CA.

[0037] S350, determine the mean value of the remaining initial heights of the luggage carts in CA as PB z 。

[0038] If μ ≥ μ', it indicates that the data difference in CA is relatively large. At this time, it is not appropriate to use the mean value of the initial heights of the luggage carts in CA. Therefore, delete the larger and smaller initial heights of the luggage carts in CA, retain the part of the data with smaller differences, and then determine the mean value of the remaining initial heights of the luggage carts in CA as PB z , to improve the rationality of the determination of PB z and further improve the accuracy of subsequent luggage area recognition.

[0039] S400, determine the luggage area according to C.

[0040] In this embodiment, step S400 may include the following steps:

[0041] S410, use a preset clustering algorithm to cluster the target points in C to obtain a cluster list D = (D 1 , D 2 , …, D a , …, D b ), a = 1, 2, …, b; where D a is the a-th cluster obtained by clustering the target points in C, and b is the number of clusters obtained by clustering the target points in C.

[0042] In this embodiment, the preset clustering algorithm may be the DBSCAN clustering algorithm. During the clustering process, the clustering between the target points can be used for clustering, and the target points with adjacent distribution positions in C can be clustered into one cluster.

[0043] S420. Obtain the volume of the point cloud corresponding to all target points within each cluster in D to obtain a list of point cloud volumes DA = (DA 1 , DA 2 , …, DA a , …, DA b ); where DA a is the volume of the point cloud corresponding to all target points within D a .

[0044] In this embodiment, the volume of the point cloud corresponding to all target points within each cluster can be represented by a minimum bounding box. It should be noted that those skilled in the art can use the existing method for determining the minimum bounding box according to actual needs to determine the minimum bounding box of the point cloud corresponding to all target points within each cluster, so as to obtain the corresponding volume, which will not be elaborated here.

[0045] S430. If DA a < QA, delete all target points within D a ; where QA is a preset minimum volume threshold for luggage.

[0046] In this embodiment, under normal circumstances, the volume of luggage has a minimum volume. For the civil aviation field, the luggage of users cannot be too small; therefore, if DA a < QA, it can be determined that the target points within D a are noise points, and the target points within D a need to be deleted to avoid misidentifying noise points as the luggage area and improve the accuracy of subsequent luggage area recognition.

[0047] S440. Determine the point cloud area corresponding to the remaining target points in C as the luggage area.

[0048] The luggage area recognition method of this embodiment obtains the initial point cloud coordinates of each initial point in the point cloud image corresponding to the luggage cart parking area; determines each intermediate point from all the initial points according to the coordinates of the preset luggage cart area; determines each target point corresponding to the luggage according to the height difference between the intermediate point and the luggage cart bottom plate, and further determines the luggage area according to each target point; the method in the present invention is based on the point cloud image corresponding to the luggage cart parking area, and the calculation amount is small during the entire luggage area recognition process. Therefore, the recognition efficiency of the luggage area is high.

[0049] In addition, for the luggage area recognition method in the present invention, the point cloud coordinates of each initial point in the point cloud image of the luggage cart parking area can be obtained by a lidar, and the accuracy of the point cloud coordinates is very high; therefore, the accuracy of the subsequent recognized luggage area is also high.

[0050] Embodiment Two:

[0051] After determining the luggage area, the luggage area can be quantified through the following steps to facilitate the subsequent stacking of luggage:

[0052] Q100. Obtain the point cloud image of the luggage area corresponding to the luggage area on the luggage cart; wherein, the point cloud image of the luggage area includes a number of points, and each point corresponds to coordinate information.

[0053] In this embodiment, the point cloud image of the luggage area corresponding to the luggage area on the luggage cart can be obtained through the method steps in Embodiment 1, which will not be elaborated here.

[0054] Q200. Perform average cutting on the point cloud image of the luggage area along the X-axis direction to obtain the first sub-enclosing box list WA = (WA 1 , WA 2 , …, WA e , …, WA f ), e = 1, 2, …, f; wherein, WA e is the e-th first sub-enclosing box obtained by performing average cutting on the point cloud image of the luggage area along the X-axis direction, and f is the number of first sub-enclosing boxes obtained by performing average cutting on the point cloud image of the luggage area along the X-axis direction; the first sub-enclosing boxes in WA are adjacent to each other in sequence.

[0055] Furthermore, step Q200 may include the following steps:

[0056] Q210. Obtain the maximum X-axis coordinate QR x，max and the minimum X-axis coordinate QR x，min of the points in the point cloud image of the luggage area; the maximum Y-axis coordinate QR y，max and the minimum Y-axis coordinate QR y，min .

[0057] In this embodiment, the coordinates of each point in the point cloud image of the luggage area can be obtained. Therefore, the maximum X-axis coordinate QR x，max , the minimum X-axis coordinate QR x，min ; the maximum Y-axis coordinate QR y，max and the minimum Y-axis coordinate QR y，min of the points in the point cloud image of the luggage area can be obtained.

[0058] Q220. According to QR y，max and QR y，min , determine the length LR of the initial first sub-enclosing box in the Y-axis direction as LR = QR y，max -QR y，min , and according to QR x，max and QR x，min , determine the width DR of the initial first sub-enclosing box in the X-axis direction as DR = (QR x，max -QR x，min) / f。

[0059] In this embodiment, when cutting along the X-axis direction, it is necessary to determine the length of the first sub-bounding box in the Y-axis direction. Using LR as the length in the Y-axis direction to cut the point cloud image of the luggage area can cut all the areas in the Y-axis direction of the point cloud image of the luggage area.

[0060] Q230, use the initial first sub-bounding box to cut the point cloud image of the luggage area sequentially along the X-axis direction from QR x，min to obtain an initial list of the first sub-bounding boxes WA’=(WA’ 1 , WA’ 2 , …, WA’ e , …, WA’ f ); where WA’ e is the e-th obtained initial first sub-bounding box.

[0061] It can be understood that the placement of the luggage is not regular. For example, it is placed in an L shape. Then, when cutting, there may be a large space without point clouds in the Y-axis direction.

[0062] Q240, obtain the maximum Y-axis coordinate GH e , the minimum Y-axis coordinate GH e y，max and the maximum Z-axis coordinate GH e y，min of the point clouds inside WA’ e z，max .

[0063] Q250, adjust the maximum Y-axis coordinate of WA’ e to GH e y，max , adjust the minimum Y-axis coordinate to GH e y，min and adjust the maximum Z-axis coordinate to GH e z，max to obtain WA e .

[0064] In this embodiment, through steps Q240 and Q250, it can be ensured that the first sub-bounding box can closely fit the corresponding point clouds, avoiding the situation that the generated first sub-bounding box is too large, resulting in waste of the space area of the luggage cart, thereby improving the space utilization rate of the luggage cart.

[0065] Q300, merge several adjacent first sub-bounding boxes in WA that meet the preset merging conditions into a first bounding box to obtain a list of first bounding boxes EA=(EA 1 , EA 2 , …, EA g , …, EAh ), g = 1, 2, …, h; where EA g is the g-th first bounding box obtained by merging the first sub-bounding boxes, and h is the number of first bounding boxes obtained by merging the first sub-bounding boxes.

[0066] Further, step Q300 may include the following steps:

[0067] Q310, obtain the first preset value BH = 1 and the second preset value HU = 1.

[0068] Q320, if |LE BH -LE BH+1 | ≤ LE’ 1 、|KD BH -KD BH+1 | ≤ LE’ 2 and |HD BH -HD BH+1 | ≤ LE’ 3 , then determine WA BH and WA BH+1 as the first sub-bounding boxes to be merged; and obtain BH = BH + 1, and enter Q320; otherwise, enter Q330; where LE BH is the length of WA BH , KD BH is the width of WA BH , and HD BH is the height of WA BH ; LE’ 1 , LE’ 2 and LE’ 3 are respectively the preset length difference threshold, width difference threshold and height difference threshold.

[0069] Q330, merge each first sub-bounding box to be merged into EA HU ; and obtain HU = HU + 1; enter Q320.

[0070] In this embodiment, LE’ 1 , LE’ 2 and LE’ 3 are empirical values, which can be obtained from a large amount of test data in the actual application process; through steps Q310 - Q330, several first sub-bounding boxes with similar sizes in the first sub-bounding boxes can be merged into one first bounding box, and when stacking luggage subsequently, the number of calculations of the bounding boxes can be reduced, improving the stacking efficiency.

[0071] Further, the length of EA HU is the maximum length of the corresponding first sub-bounding boxes to be merged, and the length of EA HUThe height is the maximum height of the corresponding first sub-bounding box to be merged, EA HU The width is the sum of the widths of the corresponding first sub-bounding boxes to be merged; thus, the merged first bounding box can completely enclose the point cloud of the corresponding luggage area, preventing the point cloud from appearing outside the first bounding box.

[0072] Q400, perform an average cut on the point cloud image of the luggage area along the Y-axis direction to obtain a list of second sub-bounding boxes WB = (WB 1 , WB 2 , …, WB k , …, WB r ), where k = 1, 2, …, r; among them, WB k is the k-th second sub-bounding box obtained by performing an average cut on the point cloud image of the luggage area along the Y-axis direction, and r is the number of second sub-bounding boxes obtained by performing an average cut on the point cloud image of the luggage area along the Y-axis direction; the second sub-bounding boxes in WB are adjacent to each other in sequence.

[0073] Furthermore, step Q400 may include the following steps:

[0074] Q410, obtain the maximum X-axis coordinate QR x，max and the minimum X-axis coordinate QR x，min of the points in the point cloud image of the luggage area; the maximum Y-axis coordinate QR y，max and the minimum Y-axis coordinate QR y，min .

[0075] Q420, according to QR x，max and QR x，min , determine the length LT of the initial second sub-bounding box in the X-axis direction as LT = QR x，max - QR x，min , and according to QR y，max and QR y，min , determine the width DR of the initial second sub-bounding box in the Y-axis direction as DR = (QR y，max - QR y，min ) / r.

[0076] Q430, use the initial second sub-bounding box to sequentially cut the point cloud image of the luggage area along the Y-axis direction starting from QR y，min to obtain a list of initial second sub-bounding boxes WB’ = (WB’ 1 , WB’ 2 , …, WB’ k , …, WB’ r ); among them, WB’ k is the k-th initial second sub-bounding box obtained.

[0077] Q440, obtain WB’ kThe maximum Y-axis coordinate EH of the internal point cloud e y，max , the minimum Y-axis coordinate EH e y，min and the maximum Z-axis coordinate EH e z，max .

[0078] Q450, adjust the maximum Y-axis coordinate of WB’ k to EH e y，max , adjust the minimum Y-axis coordinate to EH e y，min and adjust the maximum Z-axis coordinate to EH e z，max to obtain WB k .

[0079] In this embodiment, the cutting of the point cloud image of the luggage area along the Y-axis is the same as the cutting method of the corresponding point cloud image of the luggage area along the X-axis described above, and will not be elaborated here.

[0080] Q500, merge several second sub-bounding boxes that are adjacent in WB and meet the preset merging conditions into a second bounding box to obtain a second bounding box list EB=(EB 1 , EB 2 , …, EB u , …, EB v ), u = 1, 2, …, v; where EB u is the u-th second bounding box obtained by merging the second sub-bounding boxes, and v is the number of second bounding boxes obtained by merging the second sub-bounding boxes.

[0081] Furthermore, step Q500 may include the following steps:

[0082] Q510, obtain a third preset value TY = 1 and a fourth preset value RU = 1.

[0083] Q520, if |ME TY -ME TY+1 | ≤ LE’ 1 , |ND TY -ND TY+1 | ≤ LE’ 2 and |FD TY -FD TY+1 | ≤ LE’ 3 , then determine WB TY and WB TY+1 as the second sub-bounding boxes to be merged; and obtain TY = TY + 1, and enter Q520; otherwise, enter Q530; where ME TY is the length of WB TY , NDTY is WB TY 's width, FD TY is WB TY 's height; LE’ 1 、LE’ 2 and LE’ 3 are respectively a preset length difference threshold, a width difference threshold, and a height difference threshold.

[0084] Q530, merge each second sub - bounding box to be merged into EB RU ; and obtain RU = RU + 1; enter Q520.

[0085] Through steps Q510 - Q530, several second sub - bounding boxes with similar sizes in the second sub - bounding boxes can be merged into one second bounding box. When stacking luggage subsequently, the calculation times of the bounding boxes can be reduced, improving the stacking efficiency.

[0086] Furthermore, EB RU 's length is the maximum length of the corresponding second sub - bounding boxes to be merged, EB RU 's height is the maximum height of the corresponding second sub - bounding boxes to be merged, EB RU 's width is the sum of the widths of the corresponding second sub - bounding boxes to be merged; thus, it can be ensured that the merged second bounding box can completely enclose the point cloud of the corresponding luggage area, preventing the point cloud from appearing outside the second bounding box.

[0087] In this embodiment, obtain the point cloud image of the luggage area corresponding to the luggage on the luggage cart; cut the point cloud image of the luggage area corresponding to the luggage along the X - axis and Y - axis respectively to obtain the first sub - bounding box list WA and the second sub - bounding box list WB; merge several adjacent first sub - bounding boxes in WA that meet the preset merging conditions into a first bounding box to obtain the first bounding box list EA corresponding to the luggage area, and merge several adjacent second sub - bounding boxes in WB that meet the preset merging conditions into a second bounding box to obtain the second bounding box list EB corresponding to the luggage area; both the first bounding box and the second bounding box correspond to specific position and size information, thereby achieving accurate quantification of the luggage on the X - axis and Y - axis.

[0088] In addition, through the method of this embodiment, not only can the bounding box of the luggage area on the X - axis be obtained, but also the bounding box of the luggage area on the Y - axis can be obtained. When stacking luggage subsequently, the bounding box in the X - axis direction or the Y - axis direction can be used according to the position and orientation of the luggage placement.

[0089] Embodiment Three:

[0090] In the second embodiment, when generating the bounding box of the luggage, the height of the bottom plate of the luggage cart is not considered; in order to make the space utilization rate of the luggage cart higher, the bottom plate of the luggage cart can be removed through the following steps:

[0091] T100. Obtain each first bounding box corresponding to the point cloud image of the luggage area to obtain a list of first bounding boxes EA = (EA 1 , EA 2 , …, EA g , …, EA h ), where g = 1, 2, …, h; among them, EA g is the g-th first bounding box corresponding to the point cloud image of the luggage area, and h is the number of first bounding boxes corresponding to the point cloud image of the luggage area; the length of the first bounding box is along the Y-axis direction.

[0092] Furthermore, EA can be obtained through the following steps:

[0093] T110. Obtain the point cloud image of the luggage area corresponding to the luggage on the luggage cart; among them, the point cloud image of the luggage area includes several points, and each point corresponds to coordinate information.

[0094] In this embodiment, the luggage area on the luggage cart can be obtained through the method steps in the first embodiment, which will not be elaborated here.

[0095] T120. Perform average cutting on the point cloud image of the luggage area along the X-axis direction to obtain a list of first sub-bounding boxes WA = (WA 1 , WA 2 , …, WA e , …, WA f ), where e = 1, 2, …, f; among them, WA e is the e-th first sub-bounding box obtained by performing average cutting on the point cloud image of the luggage area along the X-axis direction, and f is the number of first sub-bounding boxes obtained by performing average cutting on the point cloud image of the luggage area along the X-axis direction; the first sub-bounding boxes in WA are adjacent in sequence.

[0096] In this embodiment, T120 may include the following steps:

[0097] T121. Obtain the maximum X-axis coordinate QR x，max and the minimum X-axis coordinate QR x，min of the points in the point cloud image of the luggage area; the maximum Y-axis coordinate QR y，max and the minimum Y-axis coordinate QR y，min .

[0098] In this embodiment, the coordinates of each point in the point cloud image of the luggage area can be obtained. Therefore, the maximum X-axis coordinate QR x，max, Minimum X-axis coordinate QR x，min ; Maximum Y-axis coordinate QR y，max and minimum Y-axis coordinate QR y，min .

[0099] T122, according to QR y，max and QR y，min , determine the length LR of the initial first sub-bounding box in the Y-axis direction = QR y，max - QR y，min , and according to QR x，max and QR x，min , determine the width DR of the initial first sub-bounding box in the X-axis direction = (QR x，max - QR x，min ) / f.

[0100] In this embodiment, when cutting along the X-axis direction, it is necessary to determine the length of the first sub-bounding box in the Y-axis direction, and use LR as the length in the Y-axis direction to cut the point cloud image of the luggage area, so that the area in the Y-axis direction of the point cloud image of the luggage area can be completely cut.

[0101] T123, use the initial first sub-bounding box to sequentially cut the point cloud image of the luggage area from QR x，min along the X-axis direction to obtain an initial first sub-bounding box list WA’ = (WA’ 1 , WA’ 2 , …, WA’ e , …, WA’ f ); where WA’ e is the e-th initial first sub-bounding box obtained.

[0102] It can be understood that the placement of the luggage is not regular. For example, it is placed in an L shape. Then, when cutting, there may be a large space without point cloud in the Y-axis direction.

[0103] T124, obtain the maximum Y-axis coordinate GH e of the point cloud inside WA’ e y，max , minimum Y-axis coordinate GH e y，min and maximum Z-axis coordinate GH e z，max .

[0104] T125, adjust the maximum Y-axis coordinate of WA’ e to GH e y，max , adjust the minimum Y-axis coordinate to GH e y，min and adjust the maximum Z-axis coordinate to GH e z，max, to obtain WA e .

[0105] In this embodiment, through step Q240 and step Q250, the first sub-bounding box can be made to closely adhere to the corresponding point cloud, avoiding the situation where the generated first sub-bounding box is too large, resulting in waste of the space area of the luggage cart, thereby improving the space utilization rate of the luggage cart.

[0106] T130, merge several adjacent first sub-bounding boxes in WA that meet the preset merging conditions into a first bounding box to obtain the first bounding box list EA corresponding to the luggage area.

[0107] Furthermore, step T130 may include the following steps:

[0108] T131, obtain the first preset value BH = 1 and the second preset value HU = 1.

[0109] T132, if |LE BH - LE BH+1 | ≤ LE’ 1 、|KD BH - KD BH+1 | ≤ LE’ 2 and |HD BH - HD BH+1 | ≤ LE’ 3 , then determine WA BH and WA BH+1 as the first sub-bounding boxes to be merged; and obtain BH = BH + 1, enter T132; otherwise, enter T133; where LE BH is the length of WA BH , KD BH is the width of WA BH , HD BH is the height of WA BH ; LE’ 1 , LE’ 2 and LE’ 3 are respectively the preset length difference threshold, width difference threshold and height difference threshold.

[0110] T133, merge each first sub-bounding box to be merged into EA HU ; and obtain HU = HU + 1; enter T132.

[0111] In this embodiment, LE’ 1 , LE’ 2 and LE’ 3is an empirical value and can be obtained from a large amount of experimental data during actual application; through steps T131 - T133, several first sub - bounding boxes with similar sizes in the first sub - bounding box can be merged into one first bounding box. When stacking luggage subsequently, the calculation times of the bounding boxes can be reduced, improving the stacking efficiency.

[0112] Further, the length of EA HU is the maximum length of the corresponding first sub - bounding boxes to be merged, and the height of EA HU is the maximum height of the corresponding first sub - bounding boxes to be merged, and the width of EA HU is the sum of the widths of the corresponding first sub - bounding boxes to be merged; thus, it can be ensured that the merged first bounding box can completely enclose the point cloud of the corresponding luggage area, preventing the point cloud from appearing outside the first bounding box.

[0113] T200, obtain each second bounding box corresponding to the point cloud image of the luggage area to obtain the second bounding box list EB=(EB 1 , EB 2 , …, EB u , …, EB v ), where u = 1, 2, …, v; among them, EB u is the u - th second bounding box corresponding to the point cloud image of the luggage area, and v is the number of second bounding boxes corresponding to the point cloud image of the luggage area; the length of the second bounding box is along the x - axis direction.

[0114] EB is obtained through the following steps:

[0115] T210, perform an average cut on the point cloud image of the luggage area along the Y - axis direction to obtain the second sub - bounding box list WB=(WB 1 , WB 2 , …, WB k , …, WB r ), where k = 1, 2, …, r; among them, WB k is the k - th second sub - bounding box obtained by performing an average cut on the point cloud image of the luggage area along the Y - axis direction, and r is the number of second sub - bounding boxes obtained by performing an average cut on the point cloud image of the luggage area along the Y - axis direction; the second sub - bounding boxes in WB are adjacent to each other in sequence.

[0116] T220, merge several adjacent second sub - bounding boxes in WB that meet the preset merging conditions into second bounding boxes to obtain the second bounding box list EB corresponding to the luggage area.

[0117] In this embodiment, the acquisition method of EB is the same as that of EA, which will not be elaborated here.

[0118] T300, split the overlapping and non - overlapping parts of the first bounding box in EA and the second bounding box in EB into a third bounding box to obtain a list of third bounding boxes BN=(BN 1 , BN 2 , …, BN α , …, BN β ), where α = 1, 2, …, β; among them, BN α is the α - th third bounding box obtained by splitting, and β is the number of third bounding boxes obtained by splitting.

[0119] In this embodiment, it can be understood that the first bounding box is obtained by cutting along the X - axis direction, and the second bounding box is obtained by cutting along the Y - axis direction. When stacking the luggage, it may not be stacked into a rectangle, but may be in an L - shape, and the heights of the luggage are different; therefore, there may be spaces without point clouds between the first bounding box and the second bounding box, and it is necessary to split the first bounding box and the second bounding box to further remove the bounding boxes without point clouds.

[0120] Furthermore, step T300 may include the following steps:

[0121] T310, obtain the fifth preset value WF = 1.

[0122] T311, obtain the sixth preset value WK = 1.

[0123] T312, if there is an overlapping part between EA WF and EB WF+WK-1 , then determine the overlapping part and the non - overlapping part of EA WF and EB WF+WK-1 as the third bounding box; otherwise, determine EA WF and EB WF+WK-1 as the third bounding box.

[0124] T313, if WK < v, then obtain WK = WK + 1; enter T312; otherwise, enter T314.

[0125] T314, if WF < h, then obtain WF = WF + 1; enter T311; otherwise, jump out of the current process.

[0126] Through the above steps T310 - T314, the overlapping and non - overlapping parts of the first bounding box and the second bounding box can be split into the third bounding box.

[0127] After step T314, the method further includes the following steps:

[0128] T315, traverse all the third bounding boxes, delete the third bounding boxes without point clouds inside to obtain BN.

[0129] In this embodiment, there may not be point clouds in all of the third bounding boxes. The third bounding boxes without point clouds are empty bounding boxes and there is no luggage inside. Therefore, it is necessary to delete them to release the unused space of the luggage cart and improve the space utilization rate.

[0130] T400. Obtain the maximum Z-axis coordinate of the point cloud in each third bounding box in BN to obtain the BN maximum Z-axis coordinate list PA z =(PA z，1 , PA z，2 , …, PA z，α , …, PA z，β ); where PA z，α is the maximum Z-axis coordinate of the point cloud in BN α .

[0131] T500. Adjust the Z-axis coordinate of BN α to PA z，α .

[0132] In this embodiment, both the first sub-bounding box and the second sub-bounding box are in the shape of a cuboid. The first bounding box and the second bounding box are bounding boxes with a relatively large volume, and their height is determined based on the maximum height of the corresponding luggage. If the upper surface of the corresponding luggage is not a plane but a convex surface, then there will also be a relatively large space without luggage in the corresponding first bounding box or second bounding box. Therefore, in order to make the third bounding box fit more closely to the point cloud corresponding to the luggage, the Z-axis coordinate of the third bounding box is adjusted to the maximum Z-axis coordinate of the point cloud inside it, so that the third bounding box can fit closely to the corresponding point cloud and improve the space utilization rate of the luggage cart.

[0133] In this embodiment, obtain each first bounding box corresponding to the point cloud image of the luggage area to obtain the first bounding box list EA, and obtain each second bounding box corresponding to the point cloud image of the luggage area to obtain the second bounding box list EB; split the overlapping and non-overlapping parts of the first bounding box in EA and the second bounding box in EB into third bounding boxes to obtain the third bounding box list BN; adjust the Z-axis coordinate of each third bounding box in the third bounding box list BN to the maximum Z-axis coordinate obtained from the point cloud inside it; thus, the height of the third bounding box is the same as the height of the corresponding luggage. When stacking luggage subsequently, the space of the luggage cart can be fully utilized, thereby improving the space utilization rate of the luggage cart.

[0134] Embodiment 4:

[0135] When there is no luggage on the luggage cart, the following steps can be used to determine the luggage area to improve the efficiency of luggage area determination:

[0136] H100. Determine whether there is luggage on the luggage cart.

[0137] In this embodiment, when the luggage cart arrives at the luggage cart parking area, there may or may not be luggage on the luggage cart. First, it is necessary to determine whether there is luggage on the luggage cart. Specifically, it can be determined through the following steps:

[0138] H111, obtain the Z-axis coordinate of each initial pixel point corresponding to the initial luggage cart image of the luggage cart.

[0139] H112, if the volatility of the Z-axis coordinates of all initial pixel points is less than the preset volatility threshold, it is determined that there is no luggage on the luggage cart; otherwise, it is determined that there is luggage on the luggage cart.

[0140] In this embodiment, the volatility of the Z-axis coordinates of all initial pixel points can be the variance corresponding to the Z-axis coordinates of all initial pixel points; it can be understood that when there is no luggage placed on the luggage cart, the bottom plate of the luggage cart is a plane, and the Z-axis coordinates of the pixels corresponding to the bottom plate are equal or have very little difference; when the volatility of the Z-axis coordinates of all initial pixel points is greater than the preset volatility threshold, it means that the Z-axis coordinates of all initial pixel points fluctuate greatly, indicating that there is luggage placed on the luggage cart.

[0141] H200, if there is no luggage on the luggage cart, obtain the first luggage cart image corresponding to the luggage cart.

[0142] In this embodiment, the first luggage cart image can be obtained by an industrial camera; it should be noted that the industrial camera corresponds to a camera coordinate system, and the luggage cart corresponds to a luggage cart coordinate system, and the two can perform coordinate conversion to determine the coordinate information of the pixel points in the first luggage cart image.

[0143] Furthermore, if there is luggage on the luggage cart, determine the space area occupied by the current luggage on the luggage cart through the point cloud image corresponding to the luggage cart.

[0144] In this embodiment, the method steps in Embodiment 1 can be used to determine the space area occupied by the current luggage on the luggage cart; details are not repeated here.

[0145] H300, stack the current luggage to the origin position of the luggage cart and obtain the second luggage cart image of the luggage cart; wherein, both the first luggage cart image and the second luggage cart image are two-dimensional images.

[0146] In this embodiment, when there is no luggage on the luggage cart, the luggage handling system stacks the current luggage to the origin position of the luggage cart, for example: the center point position of the luggage cart.

[0147] H400, obtain the coordinates of each pixel point corresponding to the first luggage cart image and the coordinates of each pixel point corresponding to the second luggage cart image.

[0148] In this embodiment, a camera is installed at a preset position above the luggage cart. The industrial camera corresponds to a known camera coordinate system, and the luggage cart corresponds to a known luggage cart coordinate system. The two can perform coordinate conversion to determine the coordinate information of pixel points in the first luggage cart image and the second luggage cart image. It should be noted that those skilled in the art can, according to actual needs, use existing coordinate conversion methods to obtain the coordinates of each pixel point corresponding to the first luggage cart image and the coordinates of each pixel point corresponding to the second luggage cart image, which will not be elaborated here.

[0149] H500. Determine the space area occupied by the current luggage on the luggage cart according to the coordinates of each pixel point corresponding to the first luggage cart image and the coordinates of each pixel point corresponding to the second luggage cart image.

[0150] Further, step H500 may include the following steps:

[0151] H510. Divide the first luggage cart image into several adjacent image regions to be compared to obtain the first list of image regions to be compared UA = (UA 1 , UA 2 , …, UA θ , …, UA ω ), θ = 1, 2, …, ω; where UA θ is the θ-th first image region to be compared obtained by dividing the first luggage image, and ω is the number of the first image regions to be compared obtained by dividing the first luggage image.

[0152] H520. Divide the second luggage cart image into several adjacent image regions to be compared to obtain the second list of image regions to be compared UB = (UB 1 , UB 2 , …, UB θ , …, UB ω ); where UB θ is the θ-th second image region to be compared obtained by dividing the second luggage image; UA θ and UB θ correspond to the same region of the luggage cart.

[0153] In this embodiment, the first luggage cart image and the second luggage cart image can be divided into several rectangular image regions to be compared, and the size of each image region to be compared can be determined according to actual needs.

[0154] H530. Obtain the first target height coordinates of each first image region to be compared in UA to obtain the first list of target height coordinates UC = (UC 1 , UC 2 , …, UC θ , …, UCω ); where UC θ is the first target height coordinate of UA θ ; UC θ is obtained from the Z-axis coordinates of several pixel points within UA θ .

[0155] Furthermore, UC θ is determined through the following steps:

[0156] H531, obtain the Z-axis coordinates of the pixel points at each preset position within UA θ to obtain the list of pixel point coordinates ZP θ corresponding to UA θ =(ZP θ，1 , ZP θ，2 , …, ZP θ，γ , …, ZP θ，δ ), where γ = 1, 2, …, δ; where ZP θ，γ is the Z-axis coordinate of the γth preset position pixel point within UA θ , and δ is the number of preset position pixel points within UA θ .

[0157] H532, based on ZP θ , determine UC θ =(1 / δ)×∑ δ γ＝1 ZP θ，γ .

[0158] In this embodiment, the preset positions can be the pixel points corresponding to the four vertices, the center point, and the midpoints of each side of UA θ ; the Z-axis coordinates of the pixel points at each preset position within UA θ can be obtained.

[0159] H540, obtain the second target height coordinates of each second image region to be compared within UB to obtain the second target height coordinate list UD = (UD 1 , UD 2 , …, UD θ , …, UD ω ); where UD θ is the second target height coordinate of UB θ ; UD θ is obtained from the Z-axis coordinates of several pixel points within UB θ .

[0160] In this embodiment, the determination method of UD θ is the same as that of UC θ ; it should be noted that UA θEach pixel point at a preset position inside is the same as UB θ Each pixel point at a preset position inside is the same.

[0161] H550. According to UC and UD, determine the space area occupied by the current piece of luggage on the luggage cart.

[0162] Further, step H550 may include the following steps:

[0163] H551. Traverse UC and UD. If |UC θ - UD θ | > SG, then determine UC θ as the target first image region to be compared, and determine UD θ as the target second image region to be compared; where SG is a preset target height difference threshold.

[0164] In this embodiment, if |UC θ - UD θ | > SG, it means that the Z-axis coordinates of the pixel points at the preset positions inside UA θ and UB θ change greatly. It can be determined that there is newly stacked luggage in the luggage cart area corresponding to UC θ ; thus, the areas where there is no newly stacked luggage can be filtered out completely; when filtering out most of the areas where there is no newly stacked luggage, only some pixel points are used, and the calculation amount is extremely small, so the image processing efficiency can be greatly improved.

[0165] H552. Obtain each pixel point in each target first image region to be compared to obtain a first pixel point list JC = (JC 1 , JC 2 , …, JC ε , …, JC σ ), ε = 1, 2, …, σ; where JC ε is the ε-th pixel point in the overall region corresponding to all the target first image regions to be compared, and σ is the number of pixel points in the overall region corresponding to all the target first image regions to be compared.

[0166] H553. Obtain each pixel point in each target second image region to be compared to obtain a second pixel point list JD = (JD 1 , JD 2 , …, JD ε , …, JD σ ); where JD ε is the ε-th pixel point in the overall region corresponding to all the target second image regions to be compared; JC ε and JD ε correspond to the same position on the luggage cart.

[0167] H554, if |JC ε _Z - JD ε _Z| > UZ, then JD ε is determined as the target pixel point; where JC ε _Z is the Z - axis coordinate of JC ε and JD ε _Z is the Z - axis coordinate of JD ε ; UZ is the preset threshold of the Z - axis coordinate difference of pixel points.

[0168] Through the above steps, all pixel points with large changes in the Z - axis coordinate can be determined.

[0169] H555, the spatial region formed by all target pixel points is determined as the spatial region occupied by the current luggage on the luggage cart.

[0170] In this embodiment, it is judged whether there is luggage on the luggage cart; if there is no luggage on the luggage cart, the first luggage cart image corresponding to the luggage cart is obtained; the current luggage is coded to the origin position of the luggage cart, and the second luggage cart image of the luggage cart is obtained; the coordinates of each pixel point corresponding to the first luggage cart image and the coordinates of each pixel point corresponding to the second luggage cart image are obtained; according to the coordinates of each pixel point corresponding to the first luggage cart image and the coordinates of each pixel point corresponding to the second luggage cart image, the spatial region occupied by the current luggage on the luggage cart is determined; in the present invention, when identifying the spatial region of the luggage, the two - dimensional image corresponding to the luggage cart is used, and only the coordinates of the pixels in the two - dimensional image are processed, so the calculation amount is small, and the recognition efficiency and accuracy of the luggage region are relatively high.

[0171] In addition, although the steps of the methods in the present disclosure are described in a specific order in the drawings, this does not require or imply that these steps must be executed in that specific order, or that all the steps shown must be executed to achieve the desired result. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step for execution, and / or one step may be decomposed into multiple steps for execution, etc.

[0172] An embodiment of the present invention also provides a non - transitory computer - readable storage medium, which can be set in an electronic device to store at least one instruction or at least one program related to a method in the method embodiment. The at least one instruction or the at least one program is loaded and executed by the processor to implement the method provided in the above embodiment.

[0173] The program product may adopt any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. The readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the readable storage medium (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0174] The computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries the readable program code. Such a propagated data signal may take various forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The readable signal medium may also be any readable medium other than the readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device.

[0175] The program code contained on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination of the above.

[0176] The program code for performing the operations of the present application may be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and also including conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computing device, partially on the user's device, executed as a stand-alone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (for example, by using an Internet service provider to connect through the Internet).

[0177] Embodiments of the present invention also provide an electronic device, including a processor and the aforementioned non-transitory computer-readable storage medium.

[0178] The electronic device is merely an example and should not impose any limitation on the functions and usage scope of the embodiments of the present application.

[0179] The electronic device is presented in the form of a general-purpose computing device. The components of the electronic device may include, but are not limited to: the at least one processor described above, the at least one memory described above, and a bus connecting different system components (including the memory and the processor).

[0180] Wherein, the memory stores program code, and the program code can be executed by the processor, so that the processor executes the steps in various embodiments described in this specification.

[0181] The memory may include a readable medium in the form of volatile memory, such as random access memory (RAM) and / or cache memory, and may further include read-only memory (ROM).

[0182] The memory may also include a program / utilities having a set (at least one) of program modules. Such program modules include, but are not limited to: an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include the implementation of a network environment.

[0183] The bus may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus structures.

[0184] The electronic device may also communicate with one or more external devices (such as a keyboard, a pointing device, a Bluetooth device, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device, and / or communicate with any device that enables the electronic device to communicate with one or more other computing devices (such as a router, a modem, etc.). Such communication may be through an input / output (I / O) interface. And, the electronic device may also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter. The network adapter communicates with other modules of the electronic device through the bus. It should be understood that although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0185] Through the description of the above embodiments, those skilled in the art can easily understand that the exemplary embodiments described herein can be implemented by software or by a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (such as a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

[0186] An embodiment of the present invention also provides a computer program product, which includes program code. When the program product runs on an electronic device, the program code is used to cause the electronic device to execute the steps in the method according to various exemplary embodiments of the present invention described above in this specification.

[0187] Although some specific embodiments of the present invention have been described in detail by way of examples, those skilled in the art should understand that the above examples are only for illustration and not for limiting the scope of the present invention. Those skilled in the art should also understand that various modifications can be made to the embodiments without departing from the scope and spirit of the present invention.

Claims

1. A baggage area identification method, characterized in that: The method comprises the following steps: S100, obtaining the initial point cloud coordinates of each initial point in the point cloud image corresponding to the luggage trolley parking area, so as to obtain an initial point coordinate list A=(A1, A2, ..., A i , …, A n ), i=1, 2,...,n; where, A i is the initial point coordinate of the i-th initial point corresponding to the luggage trolley parking area, and n is the number of initial points in the point cloud image corresponding to the luggage trolley parking area; S200, according to the coordinates of the preset luggage cart area, determine each intermediate point from all the initial points to obtain an intermediate point coordinate list B = (B1, B2, ..., B j , …, B m ), j = 1, 2, ..., m; where B j is the jth intermediate point determined, m is the number of intermediate points determined; B j =(B j，x , B j，y , B j，z );B j，x is the X-axis coordinate of the jth midpoint, B j，y is the Y-axis coordinate of the j-th midpoint, B j，z is the Z-axis coordinate of the jth midpoint; S300, traverse B, if YZ min <|B j，z -PB z |<YZ max , then B j Determine as the target point to obtain the target point list C = (C1, C2, ..., C p , …, C q ), p = 1, 2, ..., q; where C p is the determined p target points, q is the number of determined target points; PB z is the height of the preset luggage trolley floor, YZ min is the preset first height difference threshold, YZ max is a preset second height difference threshold; S400, according to C, determine the luggage area.

2. The baggage area identification method according to claim 1, characterized in that: Step S200 includes the following steps: S210, obtaining the maximum X-axis coordinate PB of the preset luggage cart area x，max , minimum X-axis coordinate PB x，min , maximum Y-axis coordinate PB y，max and the minimum Y-axis coordinate PB y，min ; S220, if PB x，min ≤B j，x ≤PB x，max And PB y，min ≤B j，y ≤PB y，max , then B j Determine the midpoint.

3. The baggage area identification method according to claim 1, characterized in that: Step S400 includes the following steps: S410, clustering the target points in C using a preset clustering algorithm to obtain a cluster list D = (D1, D2, ..., D a , …, D b ), a=1, 2, …, b; where D a is the ath cluster obtained by clustering the target points in C, and b is the number of clusters obtained by clustering the target points in C; S420, obtaining the volume of the point cloud corresponding to all target points in each cluster in D, so as to obtain a point cloud volume list DA = (DA1, DA2, ..., DA a , …, DA b ), where DA a D a The volume of the point cloud corresponding to all target points within; S430, if DA a <QA, then D a All destination points within are deleted; where QA is the preset minimum baggage volume threshold; S440: Determine the point cloud area corresponding to the remaining target points in C as the luggage area.

4. The baggage area identification method according to claim 3, characterized in that: The preset clustering algorithm includes the DBSCAN clustering algorithm.

5. The baggage area identification method according to claim 1, characterized in that: The point cloud image corresponding to the luggage cart parking area is acquired through a laser radar or a depth camera.

6. The baggage area identification method according to claim 1, characterized in that: PB z Determine by following these steps: S310, obtaining the initial height of each luggage cart to obtain a luggage cart initial height list CA = (CA1, CA2, ..., CA c , …, C.A. d ), c = 1, 2, ..., d; where CA c is the initial height of the cth luggage cart, and d is the number of luggage carts; S320, according to CA, determine the initial height volatility μ corresponding to CA = (1 / d) × ∑ d c＝1 (C.A. c -((1 / d)×∑ d c＝ 1CA c )) 2 ; S330, if μ<μ', then determine PB z =(1 / d)×∑ d c＝1 CA c .

7. The baggage area identification method according to claim 6, characterized in that: After step S330, the method further includes the following steps: S340, if μ≥μ', then the largest initial heights of several luggage carts and the smallest initial heights of several luggage carts in CA are deleted; S350, determining the average of the initial heights of the remaining luggage carts in CA as PB z .

8. A non-transitory computer-readable storage medium, wherein at least one instruction or at least one program is stored in the storage medium, characterized in that: The at least one instruction or the at least one program is loaded and executed by the processor to implement the baggage area identification method according to any one of claims 1 to 7.

9. An electronic device, characterized in that: Includes a processor and the non-transitory computer-readable storage medium of claim 8.

Images