CN113345015A - Package position detection method, device and equipment and readable storage medium - Google Patents
Package position detection method, device and equipment and readable storage medium Download PDFInfo
- Publication number
- CN113345015A CN113345015A CN202110893704.6A CN202110893704A CN113345015A CN 113345015 A CN113345015 A CN 113345015A CN 202110893704 A CN202110893704 A CN 202110893704A CN 113345015 A CN113345015 A CN 113345015A
- Authority
- CN
- China
- Prior art keywords
- point
- pixel
- pixel value
- determining
- segmentation
- 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
Images
Classifications
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a parcel position detection method, a parcel position detection device, parcel position detection equipment and a readable storage medium. According to the method, a depth map is generated according to height information of package point clouds, binarization processing is carried out on the depth map according to a foreground target to obtain a foreground area map, first pixel points corresponding to the foreground target in the depth map are traversed, a maximum pixel value and a minimum pixel value in a specified area with the current first pixel point as a center are determined, image segmentation points are determined according to the maximum pixel value, the minimum pixel value, a first specified pixel threshold value and the pixel value of the current first pixel point, the foreground area map is segmented according to the image segmentation points to obtain a first segmentation map, so that packages which are adhered in the height direction can be segmented into a plurality of independent packages, position information of each package can be obtained, and the probability of missing detection of package positions can be reduced.
Description
Technical Field
The application relates to the technical field of logistics intelligent sorting, in particular to a parcel position detection method, a parcel position detection device, parcel position detection equipment and a readable storage medium.
Background
In the logistics package sorting link, a package sorting device is provided, a large number of packages entering the package sorting device can be sorted into ordered packages with consistent distances from front to back, and the follow-up device is guaranteed to acquire information of the single packages. One of the core technologies in the parcel sorting equipment is to position a single parcel position, and then realize parcel separation by controlling the movement of different motors.
At present, the package position is mainly detected by extracting edges of an image, then obtaining a plurality of groups of candidate frames according to the extracted edges, and then filtering the candidate frames according to a plurality of specified rules to finally obtain a package position positioning result. However, in the method for detecting the package position, when the packages are adhered, the adhered packages cannot be divided into a plurality of packages, and the package position is missed to be detected.
Disclosure of Invention
In view of the above, embodiments of the present invention provide a method, an apparatus, a device and a readable storage medium for detecting a package position, so as to solve the problem in the prior art that when a package is adhered, the adhered package cannot be divided into a plurality of packages, which results in missed detection of the package position.
In order to solve the above problem, in a first aspect, an embodiment of the present invention provides a package position detection method, including: acquiring a parcel point cloud; generating a depth map according to the height information of the parcel point cloud; determining a foreground target in the depth map; carrying out binarization processing on the depth map according to the foreground target to obtain a foreground area map; traversing each first pixel point corresponding to a foreground target in the depth map, determining a maximum pixel value and a minimum pixel value in a specified region with the current first pixel point as a center, and determining an image segmentation point according to the maximum pixel value, the minimum pixel value, a first specified pixel threshold value and the pixel value of the current first pixel point; segmenting the foreground region image according to each image segmentation point to obtain a first segmentation image, wherein the first segmentation image comprises a plurality of first connected regions; and determining the position information of the first communication area as the position information of the corresponding package, wherein the position information of the first communication area comprises the coordinate information of each second pixel point in the first communication area.
Optionally, determining a foreground object in the depth map includes: identifying each first pixel point of the depth map with the pixel value greater than or equal to a second specified pixel threshold value; and determining a first pixel point sequence formed by each first pixel point as a foreground target.
Optionally, determining an image segmentation point according to the maximum pixel value, the minimum pixel value, the first specified pixel threshold, and the pixel value of the current first pixel point includes: and determining the current first pixel point as an image segmentation point when the difference value between the maximum pixel value and the minimum pixel value is judged to be larger than a first specified pixel threshold value, and the pixel value of the current first pixel point is smaller than the average value of the maximum pixel value and the minimum pixel value.
Optionally, segmenting the foreground object in the foreground region map according to each image segmentation point to obtain a first segmentation map, including: searching each third pixel point corresponding to the position of each image segmentation point in a foreground target in the foreground region image; and setting the pixel value of each third pixel point to be 0 to obtain a first segmentation graph.
Optionally, after segmenting the foreground region map according to each image segmentation point to obtain a first segmentation map, the method for detecting the parcel position further includes: for each first communication region: acquiring the outline of the current first communication area; carrying out pit detection on the contour; dividing the first communication area according to the concave points of the outline; determining each second connected region in the first segmentation graph after the first connected region is segmented; and determining the position information of the second communication area as the position information of the corresponding parcel.
Optionally, between acquiring the current contour of the first connected region and performing pit detection on the contour, the method for detecting the package position further includes: and performing polygon approximation processing on the outline.
Optionally, segmenting the first communication region according to the concave points of the contour includes: in the case of a contour having pits, for each pit: searching a reverse pit closest to the pit, wherein the included angle of the pit is opposite to that of the reverse pit; determining a segmentation path according to the pits and the reverse pits; and dividing the first communication area according to the dividing path.
Optionally, determining a segmentation path according to the pit and the reverse pit includes: determining a dividing path according to the shortest connecting path of the pit and the reverse pit under the condition that the reverse pit is confirmed to exist; and determining a boundary point closest to the concave point under the condition that the reverse concave point does not exist and the included angle of the concave point is an acute angle, wherein the included angle of the boundary point and the concave point is reverse, the boundary point is positioned on the polygon, and a segmentation path is determined according to the connection path of the concave point and the boundary point.
Optionally, before searching for a reverse pit closest to the pit, the method for detecting a package position further includes: searching holes of the first communication area; determining a salient point of the hole under the condition that the first communication area is confirmed to have the hole; confirming that a target convex point with the same position as the concave point exists in the convex point, removing the concave point corresponding to the target convex point, and returning to the step of detecting the concave point of the contour.
In a second aspect, an embodiment of the present invention provides a package position detection apparatus, including: the acquisition unit is used for acquiring the parcel point cloud; the generating unit is used for generating a depth map according to the height information of the parcel point cloud; a first determining unit, configured to determine a foreground object in the depth map; the processing unit is used for carrying out binarization processing on the depth map according to the foreground target to obtain a foreground area map; the second determining unit is used for traversing each first pixel point corresponding to the foreground target in the depth map, determining the maximum pixel value and the minimum pixel value in the specified region with the current first pixel point as the center, and determining the image segmentation point according to the maximum pixel value, the minimum pixel value, the first specified pixel threshold value and the pixel value of the current first pixel point; the segmentation unit is used for segmenting the foreground region image according to each image segmentation point to obtain a first segmentation image, and the first segmentation image comprises a plurality of first connected regions; and the third determining unit is used for determining the position information of the first communication area as the position information of the corresponding package, and the position information of the first communication area comprises the coordinate information of each second pixel point in the first communication area.
In a third aspect, an embodiment of the present invention provides an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to perform a package location detection method as in the first aspect or any embodiment of the first aspect.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, where computer instructions are stored, and the computer instructions are configured to cause a computer to execute the package location detection method according to the first aspect or any implementation manner of the first aspect.
The embodiment of the invention generates the depth map according to the height information of the parcel point cloud through the provided parcel position detection method, device, equipment and readable storage medium, so that the pixel value of each pixel point in the foreground target in the depth map is the height of the parcel point in the Z-axis direction, and the difference value between the maximum pixel value and the minimum pixel value in the adhesion area is larger than the first specified pixel threshold value due to the adhesive parcel in the height direction, thereby further determining the maximum pixel value and the minimum pixel value in the specified area taking the current first pixel point as the center by traversing each first pixel point corresponding to the foreground target in the depth map, determining the image segmentation point according to the maximum pixel value, the minimum pixel value, the first specified pixel threshold value and the pixel value of the current first pixel point, and further simply, quickly and accurately obtaining the image segmentation point, therefore, the foreground region graph is segmented according to the image segmentation points, the adhered packages can be segmented into a plurality of independent packages, the adhered packages in the height direction can be segmented, the position information of each package is obtained, and the probability of missed detection of the package position is reduced.
The foregoing description is only an overview of the technical solutions of the present application, and the present application can be implemented according to the content of the description in order to make the technical means of the present application more clearly understood, and the following detailed description of the present application is given in order to make the above and other objects, features, and advantages of the present application more clearly understandable.
Drawings
FIG. 1 is a schematic flow chart illustrating a method for detecting a package location according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a depth map according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a first segmentation in accordance with an embodiment of the present invention;
FIG. 4 is a schematic view of a dimple in a first land area according to an embodiment of the present invention;
FIG. 5 is a schematic view of a bump of a hole in a first via area according to an embodiment of the present disclosure;
FIG. 6 is a diagram illustrating a first communication area after a pit is updated in accordance with an embodiment of the present invention;
FIG. 7 is a diagram illustrating a segmentation path according to an embodiment of the present invention;
FIG. 8 is a schematic diagram of an image after segmentation of a first communication region according to an embodiment of the present invention;
FIG. 9 is a schematic diagram of a package position detection device according to an embodiment of the present invention;
fig. 10 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. 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 invention.
An embodiment of the present invention provides a method for detecting a parcel location, as shown in fig. 1, including:
s101, acquiring a parcel point cloud; specifically, an image of a parcel entering the parcel sorting apparatus may be acquired by a 3D camera, thereby obtaining a parcel point cloud. The parcel point cloud is a collection of all pixel points that make up the parcel. The parcel point cloud can be obtained by denoising and smoothing the point cloud of the parcel area, or can be directly obtained by denoising the point cloud of the parcel area.
S102, generating a depth map according to the height information of the wrapped point cloud; specifically, the parcel point cloud may be projected to a specified reference plane according to a normal direction of the specified reference plane, so as to obtain a depth map. The reference plane is an XOY plane and is a two-dimensional plane, and the process of projecting the parcel point cloud to the specified reference plane according to the normal direction of the specified reference plane is to project the three-dimensional coordinates of the parcel to the two-dimensional plane, wherein the height of the parcel in the Z-axis direction is the depth of the parcel in the depth map, that is, the pixel value of the parcel, and the obtained depth map is shown in fig. 2.
S103, determining a foreground target in the depth map; specifically, the foreground object in the depth map may be determined by a foreground object detection model, or may be determined by setting a second specified pixel threshold.
S104, carrying out binarization processing on the depth map according to the foreground target to obtain a foreground area map; specifically, after determining the foreground target in the depth, the pixel values of all first pixel points corresponding to the foreground target may be set to 255, and the pixel values of other pixel points in the depth map may be set to 0, so as to implement binarization processing on the depth map, and obtain the foreground region map. In the foreground region map, a region having a pixel value of 255 is a parcel region.
And S105, traversing each first pixel point corresponding to the foreground target in the depth map, determining a maximum pixel value and a minimum pixel value in a specified region with the current first pixel point as a center, and determining an image segmentation point according to the maximum pixel value, the minimum pixel value, a first specified pixel threshold value and the pixel value of the current first pixel point.
Specifically, the depth map can be processed by setting a first specified pixel threshold, and the adhesion points of the adhesion packages with height differences, namely the image segmentation points, are identified. For a designated area centered on a current pixel point, if there is no stuck parcel in the height direction, the difference between the maximum pixel value and the minimum pixel value in the designated area should be less than or equal to a first designated pixel threshold. For the current pixel point, if the pixel value is smaller than the average value of the maximum pixel value and the minimum pixel value, the current pixel point is an adhesion point, namely an image segmentation point. Therefore, by traversing each pixel point in the depth map, after the maximum pixel value and the minimum pixel value in the specified region with the current first pixel point as the center are determined, the image segmentation point can be determined according to the maximum pixel value, the minimum pixel value, the first specified pixel threshold value and the pixel value of the current first pixel point. In specific implementation, only the first pixel points corresponding to the foreground object in the depth map may be traversed. Because the foreground target in the depth map is the wrapping area, only the first pixel points corresponding to the foreground target in the depth map are traversed, and the calculation amount and the calculation time for determining the image segmentation point can be reduced.
And S106, segmenting the foreground region image according to each image segmentation point to obtain a first segmentation image, wherein the first segmentation image comprises a plurality of first communication regions.
Specifically, the specific steps of segmenting the foreground region map, that is, setting the third pixel point corresponding to the image segmentation point position in the foreground region map as a part of the background, so as to segment the foreground region map according to each image segmentation point in an optional embodiment, and obtaining the first segmentation map include: searching each third pixel point corresponding to the position of each image segmentation point in a foreground target in the foreground region image; the pixel value of each third pixel point is set to 0 to obtain a first segmentation map, and the obtained first segmentation map is shown in fig. 3. The pixel value of each third pixel point corresponding to the position of each image segmentation point is set to be 0, so that the color of each third pixel point is black, and is consistent with the color of the background, the foreground region graph can be segmented, and the parcels with adhesion in the foreground region graph are segmented into independent parcels.
And S107, determining the position information of the first communication area as the position information of the corresponding package, wherein the position information of the first communication area comprises the coordinate information of each second pixel point in the first communication area.
Specifically, the length, width, and height of each connected region may be calculated according to the coordinate information of each second pixel point in the first connected region, so as to obtain the position information of the corresponding package.
The parcel position detection method provided by the embodiment of the invention generates the depth map according to the height information of the parcel point cloud, so that the pixel value of each pixel point in the foreground target in the depth map is the height of the parcel point in the Z-axis direction, and because the parcel is adhered in the height direction, the difference value between the maximum pixel value and the minimum pixel value in the adhered area is larger than the first appointed pixel threshold value, so that the embodiment of the invention further determines the maximum pixel value and the minimum pixel value in the appointed area by traversing each first pixel point corresponding to the foreground target in the depth map and centering on the current first pixel point, determines the image segmentation point according to the maximum pixel value, the minimum pixel value, the first appointed pixel threshold value and the pixel value of the current first pixel point, thereby obtaining the image segmentation point simply, quickly and accurately, and segmenting the foreground area map according to the image segmentation point, the method can divide the adhered packages into a plurality of independent packages, so that the adhered packages in the height direction can be divided, the position information of each package is obtained, and the probability of missing detection of the package positions is reduced.
In an optional embodiment, step S103, determining a foreground object in the depth map includes: identifying each first pixel point of the depth map with the pixel value greater than or equal to a second specified pixel threshold value; and determining a first pixel point sequence formed by each first pixel point as a foreground target.
Specifically, all pixel points in the depth map are divided into foreground points and background points through a second specified pixel threshold, the foreground points are first pixel points with pixel values larger than or equal to the second specified pixel threshold, and the background points are fourth pixel points with pixel values smaller than the second specified pixel threshold. The set of all foreground points is the foreground target.
In the embodiment of the invention, the foreground target in the depth map is determined by setting the second designated pixel threshold, so that the foreground target in the depth map can be simply and quickly identified.
In an optional embodiment, in step S105, determining an image segmentation point according to the maximum pixel value, the minimum pixel value, the first specified pixel threshold, and the pixel value of the current first pixel point includes: and determining the current first pixel point as an image segmentation point when the difference value between the maximum pixel value and the minimum pixel value is judged to be larger than a first specified pixel threshold value, and the pixel value of the current first pixel point is smaller than the average value of the maximum pixel value and the minimum pixel value.
Specifically, since the pixel value in the depth map corresponds to the package depth, for a designated area centered on the current pixel point, if there is no sticky package in the height direction, the difference between the maximum pixel value and the minimum pixel value in the designated area should be less than or equal to the first designated pixel threshold. The first instruction pixel threshold may be set according to the height of the parcel. Therefore, whether the adhered packages exist in the current first pixel point range can be judged by judging the difference value between the maximum pixel value and the minimum pixel value and the size of the first appointed pixel threshold value. If the difference between the maximum pixel value and the minimum pixel value is greater than a first specified pixel threshold, it is indicated that a stuck parcel is present. The pixel value of the current first pixel point can be further compared with the average value of the maximum pixel value and the minimum pixel value, so that whether the current first pixel point is an adhesion point or not is judged, and if the pixel value of the current first pixel point is smaller than the average value of the maximum pixel value and the minimum pixel value, the current first pixel point is an adhesion point, namely an image segmentation point.
In the embodiment of the invention, when the difference value between the maximum pixel value and the minimum pixel value is judged to be larger than the first appointed pixel threshold value and the pixel value of the current first pixel point is smaller than the average value of the maximum pixel value and the minimum pixel value, the current first pixel point is determined to be the image segmentation point, so that the image segmentation point can be quickly found.
Since the determined image segmentation points can only segment the packages adhered in the height direction, in order to further improve the segmentation effect of the adhered packages, in an optional embodiment, in step S106, the foreground region map is segmented according to each image segmentation point, and after the first segmentation map is obtained, the package position detection method further includes: for each first communication region: acquiring the outline of the current first communication area; carrying out pit detection on the contour; dividing the first communication area according to the concave points of the outline; determining each second connected region in the first segmentation graph after the first connected region is segmented; and determining the position information of the second communication area as the position information of the corresponding parcel.
In particular, since the parcel generally does not have a pit, the stuck parcel can be further divided according to the pits of the single first communication area by detecting the shape of the single first communication area. As shown in fig. 4, the profile of the first connected region has a plurality of concave points. The first communication area is divided according to the concave points of the outline, the adhered packages can be further divided, and the probability of missing detection of package positions is further reduced.
In an alternative embodiment, as shown in fig. 4, polygon approximation processing is also required to be performed on the contour between the acquisition of the contour of the current first connected region and the pit detection performed on the contour. The polygon approximation processing is carried out on the outline, so that the false detection probability of the concave points can be reduced.
In an alternative embodiment, the segmenting the first communication region according to the concave points of the contour includes: in the case of a contour having pits, for each pit: searching a reverse pit closest to the pit, wherein the included angle of the pit is opposite to that of the reverse pit; determining a segmentation path according to the pits and the reverse pits; and dividing the first communication area according to the dividing path.
Specifically, before searching for a reverse pit closest to the pit, the method for detecting a package position further includes: searching holes of the first communication area; in the case where it is confirmed that the first communicating region has the hole, as shown in fig. 5, a bump of the hole is determined; confirming that a target bump with the same position as the pit exists in the bump, removing the pit corresponding to the target bump, namely, drilling a hole, and then returning to the step of detecting the pit of the contour so as to update the pit of the contour, wherein the updated pit is shown in fig. 6.
Then, the reverse pit closest to the pit is searched, and the included angle of the pit is opposite to that of the reverse pit.
Then, in the case where the presence of a reverse pit is confirmed, a dividing path can be determined from the shortest connecting path of the pit and the reverse pit, as shown in fig. 7. And determining a boundary point closest to the concave point under the condition that the reverse concave point does not exist and the included angle of the concave point is an acute angle, wherein the included angle of the boundary point and the concave point is reverse, the boundary point is positioned on the polygon, and a segmentation path is determined according to the connection path of the concave point and the boundary point.
The first connected region may then be segmented according to the segmentation path, and the segmented image of the first connected region is shown in fig. 8.
In the embodiment of the invention, the reverse concave point closest to the concave point is searched, the included angle of the concave point is opposite to the included angle of the reverse concave point, the segmentation path is determined according to the concave point and the reverse concave point, the first communication area is segmented according to the segmentation path, the segmentation path is determined based on the characteristics of the concave point, the segmentation path can be rapidly determined, and the segmentation of the adhered packages is realized.
An embodiment of the present invention further provides a package position detection apparatus, as shown in fig. 9, including:
an acquisition unit 21 configured to acquire a parcel point cloud; the detailed description of the specific implementation manner is given in step S101 of the above method embodiment, and is not repeated herein.
The generating unit 22 is used for generating a depth map according to the height information of the parcel point cloud; the detailed description of the specific implementation manner is given in step S102 of the above method embodiment, and is not repeated herein.
A first determining unit 23, configured to determine a foreground object in the depth map; the detailed description of the specific implementation manner is given in step S103 of the above method embodiment, and is not repeated herein.
The processing unit 24 is configured to perform binarization processing on the depth map according to the foreground object to obtain a foreground area map; the detailed description of the specific implementation manner is given in step S104 of the above method embodiment, and is not repeated herein.
The second determining unit 25 is configured to traverse each first pixel point corresponding to the foreground target in the depth map, determine a maximum pixel value and a minimum pixel value in an assigned region with the current first pixel point as a center, and determine an image segmentation point according to the maximum pixel value, the minimum pixel value, a first assigned pixel threshold value, and a pixel value of the current first pixel point; the detailed description of the specific implementation manner is given in step S105 of the above method embodiment, and is not repeated herein.
A segmentation unit 26, configured to segment the foreground region map according to each image segmentation point to obtain a first segmentation map, where the first segmentation map includes a plurality of first connected regions; the detailed description of the specific implementation manner is given in step S106 of the above method embodiment, and is not repeated herein.
The third determining unit 27 is configured to determine that the position information of the first connected region is the position information of the corresponding package, where the position information of the first connected region includes coordinate information of each second pixel point in the first connected region. The detailed description of the specific implementation manner is given in step S107 of the above method embodiment, and is not repeated herein.
The parcel position detection device provided by the embodiment of the invention generates the depth map according to the height information of the parcel point cloud, so that the pixel value of each pixel point in the foreground target in the depth map is the height of the parcel point in the Z-axis direction, and because the parcel is adhered in the height direction, the difference value between the maximum pixel value and the minimum pixel value in the adhered area is larger than the first appointed pixel threshold value, so that the embodiment of the invention further determines the maximum pixel value and the minimum pixel value in the appointed area by traversing each first pixel point corresponding to the foreground target in the depth map and centering on the current first pixel point, determines the image segmentation point according to the maximum pixel value, the minimum pixel value, the first appointed pixel threshold value and the pixel value of the current first pixel point, thereby obtaining the image segmentation point simply, quickly and accurately, and segmenting the foreground area map according to the image segmentation point, the method can divide the adhered packages into a plurality of independent packages, so that the adhered packages in the height direction can be divided, the position information of each package is obtained, and the probability of missing detection of the package positions is reduced.
Based on the same inventive concept as the parcel location detection method in the foregoing embodiment, an embodiment of the present invention further provides an electronic device, as shown in fig. 10, including: a processor 31 and a memory 32, wherein the processor 31 and the memory 32 may be connected by a bus or other means, and the connection by the bus is illustrated in fig. 10 as an example.
The processor 31 may be a Central Processing Unit (CPU). The Processor 31 may also be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, or combinations thereof.
The memory 32, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules corresponding to the parcel location detection method in embodiments of the present invention. The processor 31 executes various functional applications and data processing of the processor by executing the non-transitory software programs, instructions and modules stored in the memory 32, namely, implements the package location detection method in the above-described method embodiment.
The memory 32 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created by the processor 31, and the like. Further, the memory 32 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 32 may optionally include memory located remotely from the processor 31, and these remote memories may be connected to the processor 31 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
One or more of the modules described above are stored in the memory 32 and, when executed by the processor 31, perform the package location detection method in the embodiment shown in fig. 1.
The details of the electronic device may be understood with reference to the corresponding related description and effects in the embodiment shown in fig. 1, and are not described herein again.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory (Flash Memory), a Hard Disk (Hard Disk Drive, abbreviated as HDD), a Solid State Drive (SSD), or the like; the storage medium may also comprise a combination of memories of the kind described above.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable information processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable information processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable information processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable information processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (12)
1. A method of parcel location detection, comprising:
acquiring a parcel point cloud;
generating a depth map according to the height information of the parcel point cloud;
determining a foreground target in the depth map;
carrying out binarization processing on the depth map according to the foreground target to obtain a foreground area map;
traversing each first pixel point corresponding to a foreground target in the depth map, determining a maximum pixel value and a minimum pixel value in a specified region with the current first pixel point as a center, and determining an image segmentation point according to the maximum pixel value, the minimum pixel value, a first specified pixel threshold value and the pixel value of the current first pixel point;
segmenting the foreground region map according to each image segmentation point to obtain a first segmentation map, wherein the first segmentation map comprises a plurality of first connected regions;
and determining that the position information of the first communication area is the position information of the corresponding package, wherein the position information of the first communication area comprises the coordinate information of each second pixel point in the first communication area.
2. The parcel location detection method of claim 1, wherein said determining foreground objects in the depth map comprises:
identifying first pixel points in the depth map having pixel values greater than or equal to a second specified pixel threshold;
and determining a first pixel point sequence formed by each first pixel point as a foreground target.
3. The parcel location detection method of claim 1, wherein said determining an image segmentation point from the maximum pixel value, the minimum pixel value, a first specified pixel threshold and the pixel value of the current first pixel point comprises:
and determining the current first pixel point as an image segmentation point when the difference value between the maximum pixel value and the minimum pixel value is judged to be larger than a first specified pixel threshold value, and the pixel value of the current first pixel point is smaller than the average value of the maximum pixel value and the minimum pixel value.
4. The method according to claim 1, wherein the segmenting the foreground object in the foreground region map according to each image segmentation point to obtain a first segmentation map comprises:
searching each third pixel point corresponding to the position of each image segmentation point in a foreground target in the foreground region image;
and setting the pixel value of each third pixel point to be 0 to obtain a first segmentation graph.
5. The method according to claim 1, wherein after the segmenting the foreground region map according to each of the image segmentation points to obtain a first segmentation map, the method further comprises:
for each of the first communication regions: acquiring the outline of the current first communication area; carrying out pit detection on the contour; dividing the first communication area according to the concave points of the outline;
determining each second connected region in the first segmentation graph after the first connected region is segmented;
and determining the position information of the second communication area as the position information of the corresponding parcel.
6. The parcel location detection method according to claim 5, wherein between said acquiring the profile of the current first communication area and said pit detection on said profile, further comprising:
and carrying out polygon approximation processing on the outline.
7. The parcel location detection method of claim 6, wherein said segmenting the first communication area according to the concave points of the outline comprises:
in the case where the contour has pits, for each pit:
searching a reverse pit closest to the pit, wherein the included angle of the pit is opposite to that of the reverse pit;
determining a segmentation path according to the pit and the reverse pit;
and segmenting the first communication area according to the segmentation path.
8. The method of claim 7, wherein determining a segmentation path based on the pit and the reverse pit comprises:
determining a dividing path according to the shortest connecting path of the pit and the reverse pit under the condition that the reverse pit is confirmed to exist;
and determining a boundary point closest to the concave point under the condition that the reverse concave point does not exist and the included angle of the concave point is an acute angle, wherein the included angle of the boundary point and the concave point is reverse, the boundary point is positioned on the polygon, and a segmentation path is determined according to the connection path of the concave point and the boundary point.
9. The parcel location detection method of claim 7, wherein prior to said finding the nearest reverse pit to the pit, further comprising:
searching holes of the first communication area;
determining a salient point of the hole under the condition that the first communication area is confirmed to have the hole;
confirming that a target convex point with the same position as the concave point exists in the convex point, removing the concave point corresponding to the target convex point, and returning to the step of detecting the concave point of the contour.
10. A package position detection device, comprising:
the acquisition unit is used for acquiring the parcel point cloud;
the generating unit is used for generating a depth map according to the height information of the parcel point cloud;
a first determining unit, configured to determine a foreground target in the depth map;
the processing unit is used for carrying out binarization processing on the depth map according to the foreground target to obtain a foreground area map;
the second determining unit is used for traversing each first pixel point corresponding to the foreground target in the depth map, determining a maximum pixel value and a minimum pixel value in a specified region with the current first pixel point as a center, and determining an image segmentation point according to the maximum pixel value, the minimum pixel value, a first specified pixel threshold value and the pixel value of the current first pixel point;
the segmentation unit is used for segmenting the foreground region map according to each image segmentation point to obtain a first segmentation map, and the first segmentation map comprises a plurality of first connected regions;
and a third determining unit, configured to determine that the location information of the first communication area is location information of a corresponding parcel, where the location information of the first communication area includes coordinate information of each second pixel point in the first communication area.
11. An electronic device, comprising:
at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to perform the package location detection method of any one of claims 1-9.
12. A computer-readable storage medium having stored thereon computer instructions for causing a computer to perform the method for package location detection according to any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110893704.6A CN113345015A (en) | 2021-08-05 | 2021-08-05 | Package position detection method, device and equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110893704.6A CN113345015A (en) | 2021-08-05 | 2021-08-05 | Package position detection method, device and equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113345015A true CN113345015A (en) | 2021-09-03 |
Family
ID=77480698
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110893704.6A Pending CN113345015A (en) | 2021-08-05 | 2021-08-05 | Package position detection method, device and equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113345015A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115100280A (en) * | 2022-06-13 | 2022-09-23 | 北京京东乾石科技有限公司 | Article placement method and apparatus |
| CN115439543A (en) * | 2022-09-02 | 2022-12-06 | 北京百度网讯科技有限公司 | Method for determining hole position and method for generating three-dimensional model in metauniverse |
| CN117830389A (en) * | 2023-11-28 | 2024-04-05 | 中科微至科技股份有限公司 | RGBD camera-based real-time position detection method for single-piece separation package |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104657988A (en) * | 2015-02-04 | 2015-05-27 | 中国矿业大学 | Image segmentation method for micro-fine cohesive core particles based on angular point and curvature detection |
| CN106651938A (en) * | 2017-01-17 | 2017-05-10 | 湖南优象科技有限公司 | Depth map enhancement method blending high-resolution color image |
| US20180061068A1 (en) * | 2015-05-06 | 2018-03-01 | Peking University Shenzhen Graduate School | Depth/Disparity Map Post-processing Method and Device |
| CN111353985A (en) * | 2020-03-02 | 2020-06-30 | 电子科技大学 | Airport self-service consignment luggage detection method based on depth camera |
-
2021
- 2021-08-05 CN CN202110893704.6A patent/CN113345015A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104657988A (en) * | 2015-02-04 | 2015-05-27 | 中国矿业大学 | Image segmentation method for micro-fine cohesive core particles based on angular point and curvature detection |
| US20180061068A1 (en) * | 2015-05-06 | 2018-03-01 | Peking University Shenzhen Graduate School | Depth/Disparity Map Post-processing Method and Device |
| CN106651938A (en) * | 2017-01-17 | 2017-05-10 | 湖南优象科技有限公司 | Depth map enhancement method blending high-resolution color image |
| CN111353985A (en) * | 2020-03-02 | 2020-06-30 | 电子科技大学 | Airport self-service consignment luggage detection method based on depth camera |
Non-Patent Citations (1)
| Title |
|---|
| 涂秉宇 等: "岩石铸体薄片图像的喉道分割算法", 《图形图像》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115100280A (en) * | 2022-06-13 | 2022-09-23 | 北京京东乾石科技有限公司 | Article placement method and apparatus |
| CN115439543A (en) * | 2022-09-02 | 2022-12-06 | 北京百度网讯科技有限公司 | Method for determining hole position and method for generating three-dimensional model in metauniverse |
| CN115439543B (en) * | 2022-09-02 | 2023-11-10 | 北京百度网讯科技有限公司 | Method for determining hole position and method for generating three-dimensional model in meta universe |
| CN117830389A (en) * | 2023-11-28 | 2024-04-05 | 中科微至科技股份有限公司 | RGBD camera-based real-time position detection method for single-piece separation package |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109658454B (en) | Pose information determination method, related device and storage medium | |
| CN110674705B (en) | Small-sized obstacle detection method and device based on multi-line laser radar | |
| US20170103258A1 (en) | Object detection method and object detection apparatus | |
| CN113345015A (en) | Package position detection method, device and equipment and readable storage medium | |
| US11189032B2 (en) | Method and apparatus for extracting a satellite image-based building footprint | |
| US9792507B2 (en) | Method and system for ground truth determination in lane departure warning | |
| CN109583393B (en) | Lane line end point identification method and device, equipment and medium | |
| US11772271B2 (en) | Method and computing system for object recognition or object registration based on image classification | |
| US20230381971A1 (en) | Method and computing system for object registration based on image classification | |
| JP2016505185A (en) | Image processor having edge selection function | |
| CN111191557B (en) | Mark identification positioning method, mark identification positioning device and intelligent equipment | |
| CN109492639A (en) | " loaded " position three-dimensional coordinate acquisition methods, system and image recognition apparatus | |
| CN110207702B (en) | Target positioning method and device | |
| CN111369611B (en) | Image pixel depth value optimization method, device, equipment and storage medium thereof | |
| CN113128346B (en) | Target identification method, system and device for crane construction site and storage medium | |
| CN113569812A (en) | Unknown obstacle identification method and device and electronic equipment | |
| CN114639159A (en) | Moving pedestrian detection method, electronic device and robot | |
| CN110490865B (en) | Stud point cloud segmentation method based on high light reflection characteristic of stud | |
| CN109409247B (en) | Traffic sign identification method and device | |
| CN113269806A (en) | Method, device and processor for measuring blood flow inside blood vessel | |
| CN110705479A (en) | Model training method, target recognition method, device, equipment and medium | |
| CN114581890B (en) | Method and device for determining lane line, electronic equipment and storage medium | |
| CN112258602B (en) | Stop line generation method and device, electronic equipment and storage medium | |
| CN115937454B (en) | Method and device for automatically placing tree models in large-scale city scene | |
| CN117372988B (en) | Road boundary detection method, device, electronic equipment and storage medium |
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 |