CN115456930A - Parcel detection method and parcel processing apparatus - Google Patents
Parcel detection method and parcel processing apparatus Download PDFInfo
- Publication number
- CN115456930A CN115456930A CN202110632466.3A CN202110632466A CN115456930A CN 115456930 A CN115456930 A CN 115456930A CN 202110632466 A CN202110632466 A CN 202110632466A CN 115456930 A CN115456930 A CN 115456930A
- Authority
- CN
- China
- Prior art keywords
- virtual
- packages
- package
- parcel
- conveying surface
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 71
- 238000000034 method Methods 0.000 claims abstract description 23
- 230000007246 mechanism Effects 0.000 claims description 33
- 238000007689 inspection Methods 0.000 claims description 4
- 239000000126 substance Substances 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 abstract description 21
- 230000008569 process Effects 0.000 abstract description 8
- 230000009286 beneficial effect Effects 0.000 abstract description 4
- 230000008030 elimination Effects 0.000 abstract description 3
- 238000003379 elimination reaction Methods 0.000 abstract description 3
- 239000011159 matrix material Substances 0.000 description 11
- 238000010586 diagram Methods 0.000 description 10
- 230000009466 transformation Effects 0.000 description 8
- 238000006243 chemical reaction Methods 0.000 description 4
- 238000000926 separation method Methods 0.000 description 4
- 230000001174 ascending effect Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
- B07C5/342—Sorting according to other particular properties according to optical properties, e.g. colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/32—Indexing scheme for image data processing or generation, in general involving image mosaicing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Image Processing (AREA)
Abstract
The application provides a parcel detection method and parcel processing equipment, and relates to the technical field of logistics. In the package detection method, virtual package detection is performed based on a single image acquired by each camera, and the virtual packages are subjected to duplication elimination to obtain reference virtual packages in one-to-one correspondence with the entity packages on the conveying surface, so that the entity packages on the conveying surface are determined according to the reference virtual packages. The method can save the process of splicing a plurality of images, and the parcel detection method can reduce the data calculation amount during parcel detection and shorten the calculation time consumption of parcel detection, thereby improving the parcel detection efficiency and further improving the accuracy of parcel detection and sorting. The parcel processing equipment provided by the application can realize the parcel detection method, and therefore has corresponding beneficial effects.
Description
Technical Field
The application relates to the technical field of logistics, in particular to a parcel detection method and parcel processing equipment.
Background
At present, in the domestic logistics industry, along with the increase of parcel volume, more and more logistics company deploys the automatic sorting system in the letter sorting place, and the automatic sorting system includes conveying mechanism and identification mechanism, and conveying mechanism carries the parcel according to the tactics of setting for according to the parcel information that identification mechanism discerned in order to accomplish the automatic sorting of parcel, for traditional manual sorting mode, uses the automatic sorting system to carry out parcel letter sorting and has improved letter sorting efficiency greatly, has reduced logistics company's human cost.
In an automated sorting system, accurate detection of the location of a package is critical to the proper sorting of the package. In the automatic sorting system in the prior art, a camera is usually arranged above the conveying mechanism, and the position of the package conveyed by the conveying mechanism is detected by using an image shot by the camera. The related art discloses a method for detecting parcel positions by using images of cameras in an automatic sorting system, which comprises the steps of splicing parcel images acquired by a plurality of cameras; and detecting the position information of the package according to the spliced images. Because the data calculation amount of the parcel detection process in the mode is very large, the calculation time is relatively long, and the finally detected parcel position may not accord with the actual position of the current parcel, so that the parcel sorting accuracy may be influenced. Therefore, the parcel position detection method of the automatic sorting system in the related art has the problems that the parcel position detection is inaccurate, and the parcel sorting accuracy is influenced.
Disclosure of Invention
The object of the application includes providing a parcel detection method and a parcel processing apparatus which can accurately detect the position of a parcel, thereby improving the accuracy of parcel sorting.
The embodiment of the application can be realized as follows:
in a first aspect, the present application provides a package detection method applied to a package processing device, where the package processing device includes a conveying mechanism and a plurality of cameras disposed above the conveying mechanism, the conveying mechanism has a conveying surface for conveying packages, the conveying surface includes a plurality of sub-regions, the plurality of cameras are in one-to-one correspondence with the plurality of sub-regions of the conveying surface, each camera is used for capturing an image of the corresponding sub-region, two adjacent sub-regions are partially overlapped, and the package detection method includes:
acquiring a plurality of images of a plurality of cameras at the same moment, detecting each image, and determining a virtual package in each image;
determining a second coordinate position of each virtual package in a world coordinate system according to a first coordinate position of each virtual package in a corresponding image coordinate system, wherein the image coordinate system is used for describing the position of a pixel point in an image, and the world coordinate system is used for describing the position of an object on a conveying surface;
carrying out duplicate removal processing on the virtual packages according to the second coordinate position of each virtual package to obtain reference virtual packages which correspond to the entity packages on the conveying surface one by one;
the physical package on the conveying surface is determined from the reference virtual package.
In an optional embodiment, the deduplication processing is performed on the virtual packages according to the second coordinate position of each virtual package, so as to obtain reference virtual packages in one-to-one correspondence with the entity packages on the conveying surface, specifically including:
counting the virtual packages falling into an overlapping area and the virtual packages falling into a non-overlapping area according to the second coordinate position of each virtual package, wherein the overlapping area is an area on the conveying surface which at least belongs to two sub-areas, and the non-overlapping area is an area on the conveying surface which only belongs to one sub-area;
and performing deduplication processing on the virtual packages in each overlapping area, and determining the virtual packages remaining after the deduplication processing in each overlapping area and the virtual packages falling into the non-overlapping area as reference virtual packages.
In an alternative embodiment, the overlapping area and the non-overlapping area are determined according to the following steps:
shooting images of marked samples which are arranged on a conveying surface in advance by using a plurality of cameras, wherein a plurality of detection units which are arranged in multiple rows and multiple columns are arranged in the marked samples;
determining a repeatedly photographed area and an area not repeatedly photographed on the conveying surface from the image photographed by each camera;
the region repeatedly photographed is determined as an overlapping region, and the region not repeatedly photographed is determined as a non-overlapping region.
In an optional embodiment, the performing deduplication processing on the virtual package in each overlapping area specifically includes:
step S01, determining multiple combinations of a plurality of virtual packages in an overlapping area, wherein each combination comprises two virtual packages;
s02, determining a target combination from a plurality of combinations according to a set sequence;
step S03, processing the target combination to judge whether the two virtual packages in the target combination can be matched, if the two virtual packages can be matched, executing step S04, otherwise, executing step S05;
step S04, deleting one virtual package in the two virtual packages, and then executing the step S05;
step S05, judging whether an unprocessed combination exists; when it is determined that there is an unprocessed combination, step S02 is executed again, otherwise, the flow ends.
In an alternative embodiment, step S04 further includes:
after deleting one of the two virtual packages, all combinations in which the deleted virtual package is located are deleted.
In an alternative embodiment, determining multiple combinations of virtual parcels in the overlap region comprises:
and determining N combinations of the virtual packages corresponding to each other based on the counted virtual packages falling into the overlapping area.
In an alternative embodiment, multiple combinations of virtual packages in the overlap region are determined, including:
dividing the counted virtual packages falling into the overlapping area into P groups according to the corresponding relation between the virtual packages and the cameras, wherein each group of virtual packages corresponds to one camera;
q combinations of the P groups of virtual packages are determined, wherein each combination comprises two virtual packages, and the two virtual packages in each combination belong to different groups.
In an alternative embodiment, deleting one of the two virtual packages comprises:
acquiring the occupied area of each virtual package in the corresponding overlapping area, and comparing the occupied areas of the two virtual packages in the corresponding overlapping areas;
and deleting the virtual package with smaller occupied area.
In an alternative embodiment, processing the target combination to determine whether two virtual packages in the target combination can be matched includes:
determining a reference virtual package from the two virtual packages of the target combination;
judging whether the reference virtual package is positioned on the boundary of the overlapping area;
when the reference virtual package is positioned on the boundary of the overlapping area, calculating the matching degree of the two virtual packages in the target combination by using a first formula, and when the reference virtual package is not positioned on the boundary of the overlapping area, calculating the matching degree of the two virtual packages in the target combination by using a second formula;
judging whether the matching degree of the two virtual packages in the target combination is greater than a preset value, if so, judging that the two virtual packages in the target combination can be matched, otherwise, judging that the two virtual packages in the target combination cannot be matched;
wherein the content of the first and second substances,
first formulaComprises the following steps:
the second formula is:
th is the matching degree of two virtual packages, x 1 、y 1 Coordinate value, x, in world coordinate system for first virtual package 2 、y 2 Coordinate values, w, in the world coordinate system for the second virtual package 1 Is the width, w, of the first virtual parcel 2 For the width of the second virtual package,/ 1 Is the length of the first virtual package, l 2 The length of the second virtual package.
In a second aspect, the present application provides a parcel processing apparatus, the parcel processing apparatus includes a control device, a conveying mechanism and a plurality of cameras arranged above the conveying mechanism, the conveying mechanism has a conveying surface for conveying parcels, the conveying surface includes a plurality of sub-regions, the plurality of cameras are in one-to-one correspondence with the plurality of sub-regions of the conveying surface, each camera is used for shooting images of the corresponding sub-region, two adjacent sub-regions are partially overlapped, the plurality of cameras are electrically connected with the control device, and the control device is configured to:
acquiring a plurality of images of a plurality of cameras at the same moment, detecting each image, and determining a virtual package in each image;
determining a second coordinate position of each virtual package in a world coordinate system according to the first coordinate position of each virtual package in the corresponding image coordinate system, wherein the image coordinate system is used for describing the position of a pixel point in an image, and the world coordinate system is used for describing the position of an object on a conveying surface;
carrying out duplicate removal processing on the virtual packages according to the second coordinate position of each virtual package to obtain reference virtual packages which correspond to the entity packages on the conveying surface one by one;
the physical package on the conveying surface is determined from the reference virtual package.
The beneficial effects of the embodiment of the application include:
in the package detection method provided by the embodiment of the application, virtual package detection is performed based on a single image acquired by each camera, a first coordinate position of each virtual package acquired by the single image is uniformly converted into a second coordinate position in a world coordinate system, and the virtual package is subjected to duplication elimination processing based on the second coordinate position of each virtual package to obtain reference virtual packages which are in one-to-one correspondence with entity packages on a conveying surface, so that the entity packages on the conveying surface are determined according to the reference virtual packages, and further, the position information of the entity packages on the conveying surface is determined. The parcel detection method can save the process of splicing a plurality of images, and compared with the spliced images obtained after splicing the plurality of images, the single image obtained by a single camera is small in size and low in data quantity, so that the data calculation quantity when detecting the parcel from the single image is far smaller than the data calculation quantity when detecting the parcel from the spliced images, and the data calculation quantity when removing the weight of the virtual parcel is far smaller than the data calculation quantity when fusing the images of the overlapped area of the plurality of images.
The parcel processing equipment provided by the embodiment of the application can realize the parcel detection method, and therefore, the parcel processing equipment also has corresponding beneficial effects.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
FIG. 1 is a block diagram of the components of a package processing facility according to one embodiment of the subject application;
FIG. 2 is a flow chart of a package inspection method according to an embodiment of the present application;
FIG. 3 is a flowchart of step S300 in the embodiment of FIG. 2;
FIG. 4 is a schematic illustration of a marked proof in one embodiment of the present application;
FIG. 5 is a flowchart of a process for de-duplicating a virtual package in each overlapping area in one embodiment of the present application;
FIGS. 6a to 6e are schematic diagrams illustrating how virtual packages are combined in different quantities;
FIG. 7 is a diagram illustrating grouping and grouping of all virtual parcels that fall within an overlap region, according to one embodiment of the present application;
FIG. 8 is a block diagram of a package processing device in one embodiment of the present application.
Icon: 010-parcel handling equipment; 100-a conveying mechanism; 200-a camera; 300-a control device; 400-bus; 500-a memory; 020-virtual package.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present application, as presented in the figures, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined or explained in subsequent figures.
Furthermore, the appearances of the terms "first," "second," and the like, if any, are used solely to distinguish one from another and are not to be construed as indicating or implying relative importance.
It should be noted that the features of the embodiments of the present application may be combined with each other without conflict.
Currently, in an automatic sorting system, a camera is generally disposed above a conveying mechanism, and the position of a package conveyed by the conveying mechanism is detected by using an image taken by the camera. However, in general, the automatic sorting system includes a plurality of different devices, such as a stack separating device, a single separating device, a sorting device, and the like, and a plurality of cameras are disposed above a conveying mechanism of each device, and when the position of a package is detected by using the related art method, in a case where the number of cameras is large (for example, the number of cameras is tens, or even hundreds), data of a stitched image obtained by stitching images of a plurality of cameras is often very large, so that an amount of data calculation for detecting the package from the stitched image is very large, time consumed for calculation is relatively long, and a timeliness requirement for detecting the package position in the automatic sorting system is high, and when the time consumed for calculating the package position detection is long, the finally detected package position may not coincide with an actual position of the current package, which may affect the accuracy of package sorting.
In order to solve the problem that package position detection is inaccurate and package sorting accuracy is affected in the related art, embodiments of the present application provide a package detection method, where a first coordinate position of each virtual package obtained from a single image is uniformly converted into a second coordinate position in a world coordinate system, and the virtual package is subjected to deduplication processing based on the second coordinate position of each virtual package to obtain reference virtual packages corresponding to entity packages on a conveying surface one to one, so that the entity packages on the conveying surface are determined according to the reference virtual packages, and further, position information of the entity packages on the conveying surface is determined. According to the embodiment of the application, the data operation amount during package detection is reduced, the operation time of package detection is shortened, the package detection efficiency is improved, and the package detection and sorting accuracy can be improved.
The parcel detection method provided by the embodiment of the application is applied to parcel processing equipment. Fig. 1 is a block diagram showing the components of a package processing apparatus 010 according to an embodiment of the present application. As shown in fig. 1, the package processing apparatus 010 includes a control device 300, a conveying mechanism 100, and a plurality of cameras 200 disposed above the conveying mechanism 100, wherein the conveying mechanism 100 has a conveying surface for conveying packages, the conveying surface includes a plurality of sub-regions, the plurality of cameras 200 are in one-to-one correspondence with the plurality of sub-regions of the conveying surface, each camera 200 is used for capturing an image of a corresponding sub-region, and two adjacent sub-regions are partially overlapped. The conveying mechanism 100 and the plurality of cameras 200 are electrically connected to the control device 300. It should be understood that the conveying mechanism 100 may include a variety of mechanisms capable of performing a conveying function, such as a stack separation mechanism, a single piece separation mechanism, a sorting mechanism, and the like.
In the embodiment of the present application, the control device 300 is configured to:
acquiring a plurality of images of the plurality of cameras 200 at the same moment, detecting each image, and determining a virtual package in each image; determining a second coordinate position of each virtual package in a world coordinate system according to a first coordinate position of each virtual package in a corresponding image coordinate system, wherein the image coordinate system is used for describing the position of a pixel point in an image, and the world coordinate system is used for describing the position of an object on a conveying surface; and performing duplicate removal processing on the virtual packages according to the second coordinate position of each virtual package to obtain reference virtual packages which correspond to the entity packages on the conveying surface one by one, and determining the entity packages on the conveying surface according to the reference virtual packages. The method comprises the steps of determining the entity packages on the conveying surface, wherein the step of determining the entity packages on the conveying surface specifically comprises the step of determining information of the entity packages on the conveying surface, and the information of the entity packages comprises the position, the outline, the size, the state and the like of the entity packages.
FIG. 2 is a flow chart of a package inspection method according to an embodiment of the present application. The detection method can be realized by the control device of the parcel processing equipment provided by the embodiment of the application. As shown in fig. 2, a package detection method provided in an embodiment of the present application includes:
step S100, acquiring a plurality of images of a plurality of cameras based on the same moment, detecting each image, and determining a virtual package in each image.
Taking the package processing apparatus 010 provided by the present application as an example, the control device 300 acquires images of a plurality of sub-areas on the conveying mechanism 100 through a plurality of cameras 200. Optionally, the control device 300 of the package processing apparatus 010 controls each camera 200 to capture an image of a corresponding sub-area at set time intervals (e.g., 1ms, 2 ms), and obtains an image captured by each camera 200 at a set time based on the set time, so as to obtain a plurality of images captured by the plurality of cameras 200 at the same time. In the embodiment of the present application, for each image, the image may be processed by using a method known in the art (e.g., a deep learning method, a background modeling method), and a virtual parcel existing in the image is detected, where the virtual parcel is represented in the image as a figure with a certain outline.
And S200, determining a second coordinate position of each virtual package in a world coordinate system according to the first coordinate position of each virtual package in a corresponding image coordinate system, wherein the image coordinate system is used for describing the position of a pixel point in an image, and the world coordinate system is used for describing the position of an object on a conveying surface.
Taking the package processing device 010 provided by the present application as an example, a first coordinate position of each virtual package in an image coordinate system corresponding to an image in which the virtual package is located can be determined by using a method known in the art. In the present embodiment, each image has a corresponding image coordinate system, and the image coordinate system is a coordinate system established by referring to the image captured by the camera 200 and used for describing the positions of the pixels in the image. Optionally, the image coordinate system is a two-dimensional coordinate system, the set point in the image is taken as a coordinate origin, and two mutually perpendicular directions set in the image are taken as an x-axis direction and a y-axis direction. For example, the image captured by the camera 200 is rectangular, and the image coordinate system may be selected to use the central point of the image as the origin of coordinates and the extending directions of two adjacent sides of the image as the x-axis direction and the y-axis direction, respectively. Of course, in case the camera 200 is a 3D camera, the image coordinate system may also be a three-dimensional coordinate system. After detecting the virtual package in the image, the control device 300 calculates information of each detected virtual package, wherein the information of the virtual package includes information of a first coordinate position of the virtual package in the image coordinate system, an outline of the virtual package, a size of the virtual package, and the like. Optionally, the first coordinate position of the virtual package in the image coordinate system may be described by using the center point of the virtual package, or may also be described by using the coordinate value of the set vertex in the image coordinate system, for example, a coordinate position where the minimum x coordinate value of the virtual package is located is taken as the first coordinate position of the virtual package.
After the first coordinate position of the virtual parcel in the corresponding image coordinate system is determined, calculation is carried out according to the first coordinate position, and the second coordinate position of the virtual parcel in a world coordinate system is determined, wherein the world coordinate system is an absolute coordinate system established by taking the conveying surface of the conveying mechanism 100 as a reference and used for describing the position of the object on the conveying surface. Optionally, the world coordinate system is a two-dimensional coordinate system, the set point on the conveying surface is taken as a coordinate origin, and two mutually perpendicular directions set on the conveying surface are taken as an x-axis direction and a y-axis direction, for example, the world coordinate system takes one set point on the conveying surface as the coordinate origin, the parcel conveying direction is taken as the x-axis direction, and the width direction of the conveying surface is taken as the y-axis direction. Of course, when the camera 200 is a 3D camera and the image coordinate system is a three-dimensional coordinate system, the world coordinate system may be a three-dimensional coordinate system.
Optionally, determining a second coordinate position of each virtual package in the world coordinate system according to the first coordinate position of the virtual package in the corresponding image coordinate system includes: acquiring a coordinate conversion matrix corresponding to the image coordinate system, wherein the coordinate conversion matrix is used for converting coordinate values in the image coordinate system into coordinate values in a world coordinate system; and calculating according to the first coordinate position of the virtual parcel in the corresponding image coordinate system and the coordinate conversion matrix to obtain a second coordinate position of the virtual parcel in the world coordinate system.
Optionally, in this embodiment, each camera 200 corresponds to one coordinate transformation matrix, the memory 500 of the package processing device 010 stores the coordinate transformation matrix corresponding to each camera 200 in advance, and the image captured by each camera 200 performs conversion calculation of a coordinate value by using the coordinate transformation matrix corresponding to the camera 200, so as to obtain the second coordinate position of the virtual package according to the first coordinate position of the virtual package. The coordinate transformation matrix corresponding to the camera 200 is related to the position of the sub-area corresponding to the camera 200 on the conveying surface and the shooting angle. Optionally, the package detection method of this embodiment further includes: the image captured by each camera 200 is calibrated in advance by using a preset checkerboard, so as to obtain a coordinate transformation matrix corresponding to the camera 200. For example, a predetermined checkerboard is set in a sub-region corresponding to one camera 200 on the conveying surface, a coordinate value of each of a plurality of corner points in the checkerboard in a world coordinate system is measured, an image of the sub-region is captured by the camera 200, a coordinate value of each corner point in the image coordinate system is detected, a coordinate mapping relationship of each corner point is obtained by coordinate values of each corner point in two coordinate systems, and a coordinate transformation matrix corresponding to the camera 200 is obtained by calculation using the coordinate mapping relationship of the plurality of corner points. Wherein, the corner point is a pixel point which has larger difference with enough pixel points in the surrounding neighborhood.
And step S300, carrying out duplicate removal processing on the virtual packages according to the second coordinate position of each virtual package to obtain reference virtual packages which correspond to the entity packages on the conveying surface one by one.
Optionally, after determining the second coordinate position of the virtual parcel in the world coordinate system, the embodiment of the present application further calculates the outline and the size of the virtual parcel in the world coordinate system according to the outline and the size of the virtual parcel in the image and the coordinate transformation matrix, and performs deduplication processing on the virtual parcel based on the position and the outline of each virtual parcel in the world coordinate system, so as to obtain the reference virtual parcels corresponding to the physical parcels on the conveying surface one to one.
And step S400, determining the entity packages on the conveying surface according to the reference virtual packages.
After the reference virtual packages which are in one-to-one correspondence with the entity packages on the conveying surface are obtained, the information of the entity packages corresponding to the reference virtual packages on the conveying surface can be obtained according to the information of each reference virtual package. The information of the entity package comprises the position, the outline, the size, the state and the like of the entity package. Specifically, the position of the corresponding entity package on the conveying surface is determined according to the second coordinate position of the reference virtual package in the world coordinate system, the outline and the size of the corresponding entity package are determined according to the outline and the size of the reference virtual package in the corresponding image and the scaling corresponding to the image, and the state of the corresponding entity package is determined according to the state of the reference virtual package, optionally, the state of the package includes whether the package is delivered in an overlapping manner, whether the package is inclined relative to the conveying surface, and the like.
Optionally, in this embodiment, the information of the entity parcels on the conveying surface is recorded by using a parcel queue, after the entity parcels on the conveying surface are determined, the information of each entity parcel is added to the parcel queue, and the control device 300 subsequently performs processing such as state detection, stack separation, and piece separation on the parcels based on the information of the entity parcels recorded in the parcel queue.
In the package detection method according to the embodiment of the application, virtual package detection is performed based on a single image acquired by each camera 200, a first coordinate position of each virtual package acquired through the single image is uniformly converted into a second coordinate position in a world coordinate system, and the virtual package is subjected to duplication elimination processing based on the second coordinate position of each virtual package to obtain reference virtual packages corresponding to the entity packages on the conveying surface one by one, so that the entity packages on the conveying surface are determined according to the reference virtual packages, and further, the position information of the entity packages on the conveying surface is determined. According to the embodiment of the application, the process of splicing a plurality of images can be omitted, and compared with the spliced image obtained after splicing the plurality of images, the single image obtained by the single camera 200 is small in size and low in data volume, so that the data operation amount when detecting the parcel from the single image is far smaller than the data operation amount when detecting the parcel from the spliced image, and the data operation amount when performing de-duplication processing on the virtual parcel is also far smaller than the data operation amount when performing image fusion on the overlapping region of the plurality of images because the data amount of the parcel is far smaller than the data amount of the image. Therefore, by the method and the device, the data operation amount during parcel detection can be reduced, the time consumption of operation of parcel detection is shortened, the parcel detection efficiency is improved, and the accuracy of parcel detection and sorting can be improved.
Further, fig. 3 is a flowchart of step S300 in the embodiment of fig. 2. As shown in fig. 3, step S300 in the embodiment of the present application may specifically include:
step S310, counting the virtual packages falling into an overlapping area and the virtual packages falling into a non-overlapping area according to the second coordinate position of each virtual package, wherein the overlapping area is an area on the conveying surface which at least belongs to two sub-areas, and the non-overlapping area is an area on the conveying surface which only belongs to one sub-area;
step S320, performing deduplication processing on the virtual packages in each overlapping area, and determining the virtual packages remaining after the deduplication processing in each overlapping area and the virtual packages falling into the non-overlapping area as reference virtual packages.
In the embodiment of the present application, the memory 500 of the package processing apparatus 010 stores in advance a coordinate range of each overlapping area in the world coordinate system and a coordinate range of each non-overlapping area in the world coordinate system, and after obtaining the second coordinate position of the virtual package in the world coordinate system, it is determined that the virtual package falls into the overlapping area or the non-overlapping area according to the second coordinate position of each virtual package, the outline of the virtual package, and the coordinate ranges of each overlapping area and the non-overlapping area. Optionally, when it is determined that a part of the virtual package is located in the overlapping area and a part of the virtual package is located in the non-overlapping area according to the outline of the virtual package, the virtual package is considered to fall into the overlapping area.
In this embodiment, the virtual packages in each overlapping area are subjected to deduplication processing, so that the reference virtual packages remaining after the deduplication processing in each overlapping area respectively correspond to different entity packages on the conveying surface; and for virtual packages falling into the non-overlapping area, directly determining the virtual packages as reference virtual packages corresponding to the physical packages on the conveying surface. Because this embodiment will carry the regional division on the face for overlap region and non-overlap region, and only carry out the deduplication processing to the virtual parcel that falls into the overlap region, will fall into the virtual parcel direct determination of non-overlap region for the reference virtual parcel with a plurality of entity parcel one-to-one, so, can significantly reduce the data operand of carrying out the deduplication processing to virtual parcel to the operation that has further shortened parcel detection is consuming time, has improved the efficiency that parcel detected.
In an alternative embodiment of the present application, the overlapping area and the non-overlapping area are determined according to the following steps:
shooting images of marked samples which are arranged on a conveying surface in advance by using a plurality of cameras 200, wherein a plurality of detection units which are arranged in multiple rows and multiple columns are arranged in the marked samples; determining repeatedly photographed areas and areas not repeatedly photographed on the conveying surface from the images photographed by each camera 200; the region repeatedly photographed is determined as an overlapping region, and the region not repeatedly photographed is determined as a non-overlapping region.
FIG. 4 is a schematic diagram of a marked proof in one embodiment of the present application. The marked sample sheet may adopt a preset checkerboard as shown in fig. 4, the preset checkerboard includes a plurality of squares arranged in M rows and N columns, and each detection unit is one square in the preset checkerboard. Optionally, in this embodiment, each detection unit for marking the proof is provided with a unique identifier, and the marked proof can cover multiple sub-areas of the conveying surface, for example, the marked proof can cover the entire conveying surface. After the images of the marked exemplars are captured using the plurality of cameras 200, the repeatedly captured detection units and the detection units that are not repeatedly captured in the preset checkerboard are determined according to the number and the identification of the detection units included in the images captured by each camera 200, the region where the repeatedly captured detection units are located is determined as an overlapping region, and the region where the repeatedly captured detection units are not located is determined as a non-overlapping region. In other schemes, the detection unit for marking the proof divides the conveying surface into a plurality of square basic units without setting a mark, the marking proof is a checkerboard with the same area as the basic units, the marking proof is sequentially arranged on each basic unit, the plurality of cameras 200 are controlled to shoot images simultaneously, if the images shot by the plurality of cameras 200 all contain the marking proof, the basic unit where the marking proof is located is an overlapping region or a part of the overlapping region, if only one image shot by one camera 200 contains the marking proof, the basic unit corresponding to the marking proof is a part of a non-overlapping region or a non-overlapping region, after traversing all the basic units, the plurality of basic units which are mutually communicated and belong to the overlapping region are used as an overlapping region, and the plurality of basic units which are mutually communicated and belong to the non-overlapping region are used as a non-overlapping region.
FIG. 5 is a flow diagram of a process for de-duplicating virtual packages in each overlapping region in an embodiment of the present application. As shown in FIG. 5, the process of performing deduplication processing on the virtual packages in each overlapping area comprises the following steps:
step S01, determining multiple combinations of a plurality of virtual packages in an overlapping area, wherein each combination comprises two virtual packages;
step S02, determining a target combination from a plurality of combinations according to a set sequence;
step S03, processing the target combination to judge whether two virtual parcels in the target combination can be matched, if the two virtual parcels can be matched, executing step S04, otherwise, executing step S05;
step S04, deleting one virtual package in the two virtual packages, and then executing step S05;
step S05, judging whether an unprocessed combination exists; when it is determined that there is an unprocessed combination, step S02 is executed again, otherwise, the flow ends.
In this embodiment, the virtual packages in each overlapping area are combined pairwise, whether the two virtual packages in each combination can be matched is determined, and when it is determined that the two virtual packages can be matched, it is indicated that the two virtual packages correspond to one entity package in the overlapping area, and therefore, in this case, one of the virtual packages is deleted, so that the remaining virtual packages in each overlapping area are not matched with each other after deduplication processing, and the remaining virtual packages in each overlapping area are reference virtual packages corresponding to the entity packages actually existing in the overlapping area one to one.
Optionally, in this embodiment, a plurality of virtual packages in each overlapping area are numbered, after a plurality of combinations of the plurality of virtual packages in one overlapping area are determined, one virtual package is selected as a target virtual package according to an ascending order or a descending order of virtual package numbers, and a combination where the target virtual package is located is sequentially determined as a target combination, for example, first, the number 1 virtual package is determined as the target virtual package, then all combinations including the number 1 virtual package are sequentially determined as the target combination, then the number 2 virtual package is determined as the target package, and then all combinations including the number 2 virtual package are sequentially determined as the target combination without being processed to determine whether two virtual packages are matched. So, can investigate in proper order whether every virtual parcel can match with other virtual parcels according to the serial number of virtual parcel, avoid because the parcel that the virtual parcel is omitted and lead to detects inaccurately.
Further, in step S04, the method may further include: after deleting one of the two virtual packages, all combinations in which the deleted virtual package is located are deleted.
In this embodiment, when two virtual packages in one combination can be matched, not only one of the virtual packages is deleted, but also all combinations related to the deleted virtual package are deleted, so that it is not necessary to subsequently determine whether two virtual packages in the deleted combination are matched, and repeated determination or invalid determination which may occur when two virtual packages in all determined combinations are matched is avoided. Therefore, the calculation amount of the deduplication processing of the virtual packages in the overlapping area can be greatly reduced through the embodiment, the time occupied by the deduplication processing of the virtual packages is shortened, and the package detection efficiency is improved.
In an optional embodiment, the determining, in step S01, multiple combinations of multiple virtual packages in the overlapping area may specifically include: and correspondingly determining N combinations of the virtual packages in pairs based on the counted virtual packages falling into the overlapping area. Wherein N = M (M-1)/2, M is the counted number of virtual packages falling into the overlapping area, and M is an integer greater than or equal to 2. It is understood that the N combinations determined in the above steps are N combinations of two virtual packages among all the virtual packages falling into the overlapping area. Fig. 6a to 6e are schematic diagrams illustrating how virtual parcels 020 are combined in different quantities. In fig. 6 a-6 e, one box represents one virtual package 020 falling into the overlap region, and each line connecting two boxes represents a combination. As shown in fig. 6 a-6 e, if the number of virtual packages 020 falling into the overlap region is 2, then there is only one combination, namely, the two virtual packages 020 are combined together; if the number of virtual packages 020 falling into the overlap region is 3, then there are three combinations; if the number of virtual packages 020 falling into the overlap region is 4, then there are six combinations; if the number of virtual packages 020 falling into the overlap region is 5, then there are ten combinations; if the number of virtual packages 020 falling into the overlap region is 6, then there are fifteen combinations. Thus, the number of combinations N can be calculated according to the combination formula C (M, 2), which means the number of ways to select 2 virtual packages 020 from the M virtual packages 020 to form a combination, and C (M, 2) is equal to M! /[ (M-2)! *2! I.e., M (M-1)/2.
The above-described method of determining multiple combinations of virtual packages 020 in an overlap region combines two virtual packages 020 that fall into the overlap region, so that there are some combinations where two virtual packages 020 are actually captured by the same camera 200, i.e., exist in the same image. Then the two virtual packages 020 are not likely to be virtual packages 020 corresponding to the same physical package, and if the two virtual packages 020 in the combination are compared to determine whether the two virtual packages match, some amount of computation is wasted. Thus, in alternative embodiments, determining multiple combinations of virtual packages 020 in an overlap region can include:
dividing the virtual parcels 020 which are counted and fall into the overlapping area into P groups according to the corresponding relation between the virtual parcels 020 and the camera 200, wherein each group of virtual parcels 020 corresponds to one camera 200;
q combinations of P groups of virtual packages 020 are determined, wherein each combination includes two virtual packages 020, and the two virtual packages 020 in each combination belong to different groups.
It will be appreciated that the number of combinations described above
c j Is the number, c, of the jth group of virtual packages 020 k The number of the k-th group of virtual parcels 020 is P, Q, j and k are positive integers, and P is more than or equal to 2.
FIG. 7 is a diagram illustrating grouping and recombining all virtual packages 020 that fall within an overlap region in an embodiment of the present application. Three images taken by three cameras 200 are shown in fig. 7, wherein two virtual parcels 020 in each image fall into an overlapping area (more virtual parcels may be in practical cases), and the virtual parcels 020 that each camera 200 respectively shoots fall into the overlapping area are divided into a group of virtual parcels 020 (not a combination), so that three groups of virtual parcels 020 are shared, in other words, the above-mentioned P value is 3. One virtual package 020 in each group of virtual packages 020 is in a combined relationship with the virtual packages 020 in other groups only, namely, one combination is formed. It can be seen that there are also six virtual packages 020 that fall into the overlap region, but in the way the combinations are established provided by this embodiment, only 12 combinations are eventually established, which is 3 less than the way the combinations are established in the embodiment of fig. 6 e. It can be understood that only when two virtual packages 020 in a combination belong to two different images, the two virtual packages 020 are likely to correspond to the same physical package, and it is only necessary to determine whether deduplication processing is required, and it is not likely that two different virtual packages 020 in the same image correspond to the same physical package. That is, there are only two virtual packagesThe parcel 020 is shot by two different cameras 200, and it is necessary to compare and determine whether matching is possible. Thus, in the present embodiment, virtual packages 020 are first grouped according to their correspondence with camera 200, and the combination of virtual packages 020 is determined by associating each virtual package 020 in one group of virtual packages 020 with each virtual package 020 in the other group. In this way, the virtual parcels 020 in the same group do not need to be combined, the number of the determined combinations of the virtual parcels 020 can be reduced, the data calculation amount when the virtual parcels 020 in the overlapping area are subjected to de-duplication processing is reduced, the data calculation time is shortened, the calculation efficiency is improved, and the parcel detection efficiency is further improved. It can be appreciated that the number of combinations Q is reduced compared to the number of combinations N of the previous embodiment
The number of seed groups is also reduced
The number of combinations.
Further, deleting one of the two virtual packages, comprising: acquiring the area occupied by each virtual package in the corresponding overlapping area, and comparing the sizes of the areas occupied by the two virtual packages in the corresponding overlapping areas; and deleting the virtual package with smaller occupied area.
In this embodiment, when it is determined that two virtual packages can be matched, the area occupied by each virtual package in the overlapping area is obtained, and one virtual package with a smaller area is deleted, that is, one virtual package with a larger area is reserved. Since the occupied area of the virtual parcel corresponds to the size of the entity parcel corresponding to the virtual parcel, when the occupied area of the virtual parcel is larger, the information indicating the parcel contained in the image in which the virtual parcel is located is more accurate, and when the occupied area of the virtual parcel is smaller, only a partial image of the entity parcel on the conveying surface may be contained in the image in which the virtual parcel is located, for example, one part of the entity parcel is in an overlapping region, and the other part of the entity parcel is in a non-overlapping region. One camera 200 may only capture a part of the image of the entity package located in the overlapping region when capturing the image, and at this time, if the entity package is determined according to the virtual package falling into the overlapping region, the information of the entity package finally obtained will be incomplete, so that the virtual package with a smaller occupied area is deleted in the present embodiment, and the virtual package with a larger occupied area is retained, so as to improve the accuracy of entity package detection, provide more accurate information for subsequent package processing, and facilitate improvement of the accuracy of package processing.
In this embodiment of the present application, optionally, the processing the target combination to determine whether two virtual packages in the target combination can be matched includes:
determining a reference virtual package from the two virtual packages of the target combination; judging whether the reference virtual package is positioned on the boundary of the overlapping area; when the reference virtual package is positioned on the boundary of the overlapping area, calculating the matching degree of the two virtual packages in the target combination by using a first formula, and when the reference virtual package is not positioned on the boundary of the overlapping area, calculating the matching degree of the two virtual packages in the target combination by using a second formula;
judging whether the matching degree of the two virtual packages in the target combination is greater than a preset value, if so, judging that the two virtual packages in the target combination can be matched, otherwise, judging that the two virtual packages in the target combination cannot be matched;
wherein the content of the first and second substances,
the first formula is:
the second formula is:
th is the matching degree of two virtual packages, x 1 、y 1 Coordinate value, x, in world coordinate system for first virtual package 2 、y 2 For the second virtual package inCoordinate values in the world coordinate system, w 1 Is the width, w, of the first virtual parcel 2 For the width of the second virtual package,/ 1 Is the length of the first virtual package, l 2 Is the length of the second virtual package. It can be seen that the larger the difference between the coordinate values of the two virtual packages is and the larger the difference between the coordinate values of the two virtual packages is, the lower the calculated value of the matching degree th is.
Optionally, the coordinate value of the virtual package is described by using a coordinate value of a center point of the virtual package or a coordinate value of a set vertex of the virtual package. When the virtual package is located on the boundary of the overlap region, a part of the physical package corresponding to the virtual package may be in the overlap region, and a part of the physical package may be in the non-overlap region, that is, although the physical package corresponding to the virtual package is simultaneously captured by the plurality of cameras 200, some cameras 200 may capture a complete image of the physical package, and some cameras 200 may not capture a complete image of the physical package. For a camera 200 that cannot capture a complete image of a physical package, the size of the virtual package determined from the image of the camera 200 does not match the size of the physical package, so in this case, the matching degree of two virtual packages is calculated using only the coordinate positions of the virtual packages; and when the entity parcel is all located in the overlapping area, the plurality of cameras 200 can acquire the complete image of the entity parcel, so that in this case, the size parameters such as the width and the length of the virtual parcel are introduced when the matching degree of the two virtual parcels is calculated, and the accuracy of judging whether the virtual parcels are matched or not can be improved.
Optionally, the reference virtual package is a virtual package according to which the target combination is determined, for example, in this embodiment, a plurality of virtual packages in the overlapping area are numbered, after a plurality of combinations of the plurality of virtual packages are determined, one virtual package is selected as the target virtual package according to an ascending order or a descending order of numbers of the virtual packages, and a combination where the target virtual package is located is sequentially determined as the target combination, and when a matching degree of two virtual packages in the target combination is calculated, the reference virtual package is the target virtual package, for example, the number 1 virtual package is determined as the target virtual package first, then all combinations including the number 1 virtual package are sequentially determined as the target combination, when a matching degree of two virtual packages in the target combination is calculated, the reference virtual package is the number 1 virtual package, then the number 2 virtual package is determined as the target virtual package, then all combinations including the number 2 virtual packages which have not been processed are sequentially determined as the target combination, and when a matching degree of two virtual packages in the target combination is calculated, the virtual package is the number 2 virtual package.
In the embodiment of the present application, the control device 300 of the package processing device 010 can execute an executable program to implement the package detection method in the above-described embodiment of the present application. Fig. 8 is a block diagram of a package handling device 010 according to an embodiment of the present application. As shown in fig. 8, the package processing device 010 further includes a bus 400 and a memory 500, the control device 300 is communicatively connected to the memory 500 through the bus 400, and the memory 500 may store an executable program for the control device 300 to call to implement the package detection method. The memory 500 may further store related data for implementing the above package detection method, for example, the memory 500 stores a coordinate transformation matrix corresponding to each camera 200, a coordinate range of each overlapping area in the world coordinate system, a coordinate range of each non-overlapping area in the world coordinate system, and the like. The Memory 500 may be a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and various media capable of storing program codes. In some embodiments, the memory 500 may also be integrated with the control device 300.
In summary, in the package detection method provided in the embodiment of the present application, virtual package detection is performed based on a single image acquired by each camera, a first coordinate position of each virtual package acquired through the single image is uniformly converted into a second coordinate position in a world coordinate system, and deduplication processing is performed on the virtual package based on the second coordinate position of each virtual package, so as to obtain reference virtual packages corresponding to the entity packages on the conveying surface one by one, and thus the entity packages on the conveying surface are determined according to the reference virtual packages, and further, the position information of the entity packages on the conveying surface is determined. The parcel detection method can save the process of splicing a plurality of images, and compared with the spliced images obtained after splicing the plurality of images, the single image obtained by a single camera is small in size and low in data quantity, so that the data calculation quantity when detecting the parcel from the single image is far smaller than the data calculation quantity when detecting the parcel from the spliced images, and the data calculation quantity when removing the weight of the virtual parcel is far smaller than the data calculation quantity when fusing the images of the overlapped area of the plurality of images. The parcel processing equipment provided by the embodiment of the application can realize the parcel detection method, and therefore, the parcel processing equipment also has corresponding beneficial effects.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present application should be covered within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A package detection method is applied to a package processing device and is characterized in that the package processing device comprises a conveying mechanism and a plurality of cameras arranged above the conveying mechanism, the conveying mechanism is provided with a conveying surface used for conveying packages, the conveying surface comprises a plurality of sub-regions, the plurality of cameras are in one-to-one correspondence with the plurality of sub-regions of the conveying surface, each camera is used for shooting images of the corresponding sub-region, and two adjacent sub-regions are partially overlapped, the package detection method comprises the following steps:
acquiring a plurality of images of a plurality of cameras at the same moment, detecting each image, and determining a virtual package in each image;
determining a second coordinate position of each virtual parcel in a world coordinate system according to a first coordinate position of each virtual parcel in a corresponding image coordinate system, wherein the image coordinate system is used for describing the position of a pixel point in the image, and the world coordinate system is used for describing the position of an object on the conveying surface;
carrying out duplicate removal processing on the virtual packages according to the second coordinate position of each virtual package to obtain reference virtual packages which correspond to the entity packages on the conveying surface one by one;
determining physical parcels on the conveying surface according to the reference virtual parcel.
2. The package detection method according to claim 1, wherein the deduplication processing is performed on the virtual packages according to the second coordinate position of each virtual package, so as to obtain reference virtual packages corresponding to the physical packages on the conveying surface one to one, specifically including:
counting virtual packages falling into an overlapping area and virtual packages falling into a non-overlapping area according to the second coordinate position of each virtual package, wherein the overlapping area is an area on the conveying surface which at least belongs to two sub-areas, and the non-overlapping area is an area on the conveying surface which only belongs to one sub-area;
and performing the deduplication processing on the virtual packages in each overlapping area, and determining the virtual packages remaining after the deduplication processing in each overlapping area and the virtual packages falling into the non-overlapping area as reference virtual packages.
3. The package inspection method of claim 2, wherein the overlapping area and the non-overlapping area are determined according to the following steps:
shooting images of marked samples preset on the conveying surface by using a plurality of cameras, wherein a plurality of detection units arranged in a plurality of rows and a plurality of columns are arranged in the marked samples;
determining repeatedly photographed areas and areas which are not repeatedly photographed on the conveying surface according to the images photographed by each camera;
and determining the repeatedly shot area as the overlapping area, and determining the area which is not repeatedly shot as the non-overlapping area.
4. The package detection method according to claim 2, wherein performing the deduplication processing on the virtual package in each of the overlapping areas specifically includes:
step S01, determining a plurality of combinations of the virtual packages in the overlapping area, wherein each combination comprises two virtual packages;
step S02, determining a target combination from the multiple combinations according to a set sequence;
step S03, processing the target combination to judge whether two virtual parcels in the target combination can be matched, if the two virtual parcels can be matched, executing step S04, otherwise, executing step S05;
step S04, deleting one virtual package in the two virtual packages, and then executing step S05;
step S05, judging whether unprocessed combinations exist or not; when it is determined that there is an unprocessed combination, step S02 is executed again, otherwise, the flow ends.
5. The package inspection method according to claim 4, wherein the step S04 further comprises:
deleting all combinations in which the deleted virtual packages are located after deleting one of the two virtual packages.
6. The package detection method of claim 4, wherein determining a plurality of combinations of the plurality of virtual packages in the overlap region comprises:
and determining N combinations of the virtual packages in a pairwise correspondence manner based on the counted virtual packages falling into the overlapping area.
7. The package detection method of claim 4, wherein determining a plurality of combinations of the virtual packages in the overlap region comprises:
dividing the counted virtual parcels falling into the overlapping area into P groups according to the corresponding relation between the virtual parcels and the cameras, wherein each group of virtual parcels corresponds to one camera;
q combinations of P groups of virtual packages are determined, wherein each combination comprises two of the virtual packages, and the two virtual packages in each combination belong to different groups.
8. The package detection method of claim 4, wherein deleting one of the two virtual packages comprises:
acquiring the occupied area of each virtual package in the corresponding overlapping area, and comparing the occupied areas of the two virtual packages in the corresponding overlapping areas;
and deleting the virtual package with smaller occupied area.
9. The package detection method of claim 4, wherein processing the target combination to determine whether two virtual packages in the target combination can be matched comprises:
determining a reference virtual package from the two virtual packages of the target combination;
judging whether the reference virtual package is positioned on the boundary of the overlapping area;
when the reference virtual package is positioned on the boundary of the overlapping area, calculating the matching degree of the two virtual packages in the target combination by using a first formula, and when the reference virtual package is not positioned on the boundary of the overlapping area, calculating the matching degree of the two virtual packages in the target combination by using a second formula;
judging whether the matching degree of the two virtual packages in the target combination is greater than a preset value, if so, judging that the two virtual packages in the target combination can be matched, otherwise, judging that the two virtual packages in the target combination cannot be matched;
wherein the content of the first and second substances,
the first formula is:
the second formula is:
th is the matching degree, x, of the two virtual packages 1 、y 1 Coordinate value, x, in the world coordinate system for the first virtual package 2 、y 2 Coordinate values, w, in the world coordinate system for a second virtual package 1 Is the width, w, of the first virtual package 2 Is the width of the second virtual package,/ 1 Is the length of the first virtual package,/ 2 Is the length of the second virtual package.
10. A parcel processing apparatus comprising control means, a conveying mechanism and a plurality of cameras disposed above the conveying mechanism, the conveying mechanism having a conveying surface for conveying parcels, the conveying surface comprising a plurality of sub-regions, the plurality of cameras corresponding one-to-one to the plurality of sub-regions of the conveying surface, each camera being for taking an image of the corresponding sub-region, two adjacent sub-regions being partially overlapped, the plurality of cameras all being electrically connected to the control means, the control means being arranged to:
acquiring a plurality of images of a plurality of cameras at the same moment, detecting each image, and determining a virtual package in each image;
determining a second coordinate position of each virtual package in a world coordinate system according to a first coordinate position of each virtual package in a corresponding image coordinate system, wherein the image coordinate system is used for describing the position of a pixel point in the image, and the world coordinate system is used for describing the position of an object on the conveying surface;
carrying out duplicate removal processing on the virtual packages according to the second coordinate position of each virtual package to obtain reference virtual packages which correspond to the entity packages on the conveying surface one by one;
determining physical parcels on the conveying surface according to the reference virtual parcel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110632466.3A CN115456930A (en) | 2021-06-07 | 2021-06-07 | Parcel detection method and parcel processing apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110632466.3A CN115456930A (en) | 2021-06-07 | 2021-06-07 | Parcel detection method and parcel processing apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115456930A true CN115456930A (en) | 2022-12-09 |
Family
ID=84295022
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110632466.3A Pending CN115456930A (en) | 2021-06-07 | 2021-06-07 | Parcel detection method and parcel processing apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115456930A (en) |
-
2021
- 2021-06-07 CN CN202110632466.3A patent/CN115456930A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP3124296B2 (en) | How to detect the position and direction of the fiducial mark | |
| JP2024023692A (en) | Automated package registration system, device, and method | |
| WO2019189661A1 (en) | Learning dataset creation method and device | |
| CN111179358A (en) | Calibration method, device, equipment and storage medium | |
| JPS5959397A (en) | Labeller for characteristic point | |
| CN105184765A (en) | Inspection Apparatus, Inspection Method, And Program | |
| JP5773436B2 (en) | Information terminal equipment | |
| CN108120391A (en) | Information processing equipment and method, storage medium and article manufacturing method | |
| CN113449532B (en) | Method, device, computing equipment, logistics system and storage medium for detecting packages | |
| CN109911481B (en) | Cabin frame target visual identification and positioning method and system for metallurgical robot plugging | |
| CN110926330B (en) | Image processing apparatus, image processing method, and program | |
| CN112254633B (en) | Object size measuring method, device and equipment | |
| JPWO2014030400A1 (en) | Object identification device, object identification method, and program | |
| CN110142230A (en) | A kind of method and device detecting open defect | |
| CN114820781A (en) | Intelligent carrying method, device and system based on machine vision and storage medium | |
| RU2727858C2 (en) | Training device, paper sheet identification device and paper sheet identification method | |
| CN115456930A (en) | Parcel detection method and parcel processing apparatus | |
| CN114638888B (en) | Position determination method and device, electronic equipment and readable storage medium | |
| CN111739106B (en) | Corner point coding method, calibration method, device, electronic equipment and storage medium | |
| Song et al. | Automatic calibration method based on improved camera calibration template | |
| Sidor et al. | The impact of the implementation of edge detection methods on the accuracy of automatic voltage reading | |
| CN210030534U (en) | Packing adhesive tape and packing box | |
| CN112102292A (en) | Method, device and equipment for detecting laminating precision of 3D image | |
| CN113409297A (en) | Aggregate volume calculation method, particle form grading data generation method, system and equipment | |
| CN115922738B (en) | Electronic component grabbing method, device, equipment and medium in stacking scene |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |