CN118279223A - Method and device for determining position of package and related equipment - Google Patents
Method and device for determining position of package and related equipment Download PDFInfo
- Publication number
- CN118279223A CN118279223A CN202211715810.6A CN202211715810A CN118279223A CN 118279223 A CN118279223 A CN 118279223A CN 202211715810 A CN202211715810 A CN 202211715810A CN 118279223 A CN118279223 A CN 118279223A
- Authority
- CN
- China
- Prior art keywords
- image
- package
- belt
- belt transmission
- transmission image
- 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
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- 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
-
- 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
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Control Of Conveyors (AREA)
- Sorting Of Articles (AREA)
- Image Analysis (AREA)
Abstract
The application provides a method and a device for determining the position of a package and related equipment, wherein the method comprises the following steps: when a parcel passes through a target area, acquiring a first belt transmission image of the target area shot by a preset industrial camera and waybill information of the parcel obtained by scanning by a preset scanning device; image quality judgment is carried out on the first belt transmission image, and a first judgment result is obtained; if the first judging result is that the first belt transmission image meets the first quality judging requirement of the image, dividing the belt area in the first belt transmission image to obtain a first belt division image; carrying out regression prediction on the position of the package in the first belt segmentation image to obtain a boundary frame for displaying the position of the package and coordinates of each corner point in the boundary frame; and determining the position of the package based on the coordinates of each corner point in the bounding box and the waybill information. The embodiment of the application improves the speed and accuracy of determining the package position.
Description
Technical Field
The application relates to the technical field of logistics sorting, in particular to a method and a device for determining the position of a package and related equipment thereof.
Background
Along with the rapid development of logistics, logistics sorting is gradually biased to intelligent development, so that manual operation can be effectively reduced, and cost is reduced. In the logistics sorting process, in many sorting steps, the wrapping position on the belt conveyor needs to be positioned first.
However, in the existing method, due to various adverse factors, the position of the package on the belt conveyor cannot be rapidly and accurately positioned.
Therefore, how to quickly and accurately determine the position of the package on the belt conveyor is a technical problem to be solved in the technical field of current logistics sorting.
Disclosure of Invention
The application provides a method and a device for determining the position of a package and related equipment, and aims to solve the technical problem of how to quickly and accurately determine the position of the package on a belt conveyor.
In one aspect, the present application provides a method of determining a location of a package, the method comprising:
When a parcel passes through a target area, acquiring a first belt transmission image shot by a preset industrial camera and waybill information of the parcel obtained by scanning by a preset scanning device;
image quality judgment is carried out on the first belt transmission image, and a first judgment result is obtained;
If the first judging result is that the first belt transmission image meets the first quality judging requirement of the image, dividing the belt area in the first belt transmission image to obtain a first belt division image, wherein the first quality judging requirement is that the first belt transmission image is a judging requirement of a non-overexposure image or a non-overdrising image;
Carrying out regression prediction on the position of the package in the first belt segmentation image to obtain a boundary frame for displaying the position of the package and coordinates of each corner point in the boundary frame;
and determining the position of the package based on the coordinates of each corner point in the boundary box and the waybill information.
In one possible implementation manner of the present application, the determining the image quality of the first belt transmission image to obtain a first determination result includes:
Based on a histogram statistical method, counting the pixel distribution of the first belt transmission image to obtain the number of target pixels with pixel values in a preset pixel value interval, wherein the preset pixel value interval is a corresponding pixel value interval in an overexposure state or a corresponding pixel value interval in an overdrising state;
Comparing the number of the target pixels with the total number of pixels of the first belt transmission image to obtain the duty ratio of the target pixels in the first belt transmission image;
Comparing the duty ratio with a preset threshold value to obtain a comparison result;
If the duty ratio is greater than or equal to the threshold value, determining that the first belt transmission image does not meet a first quality judgment requirement of the image;
And if the duty ratio is smaller than the threshold value, determining that the first belt transmission image meets the first quality judgment requirement of the image.
In one possible implementation manner of the present application, the regression prediction is performed on the position of the package in the first belt segmentation image to obtain a bounding box for displaying the position of the package, and coordinates of each corner point in the bounding box, including:
Performing image quality judgment on the first belt segmentation image to obtain a second judgment result;
And if the second judging result is that the first belt transmission image meets the second quality judging requirement of the image, carrying out regression prediction on the position of the package in the first belt segmentation image to obtain a boundary frame for displaying the position of the package and coordinates of each corner point in the boundary frame.
In one possible implementation manner of the present application, the determining the image quality of the first belt split image to obtain a second determination result includes:
And carrying out image quality judgment on the first belt segmentation image through a pre-trained image quality judgment model based on a deep learning algorithm to obtain a second judgment result.
In one possible implementation manner of the present application, the regression prediction is performed on the position of the package in the first belt segmentation image to obtain a bounding box for displaying the position of the package, and coordinates of each corner point in the bounding box, including:
And carrying out regression prediction on the position of the package in the first belt segmentation image through a pre-trained package detection model based on a deep learning algorithm to obtain a boundary box for displaying the position of the package and coordinates of each corner point in the boundary box.
In one possible implementation manner of the present application, before performing regression prediction on the position of the package in the first belt segmentation image through a pre-trained package detection model based on a deep learning algorithm to obtain a bounding box for displaying the position of the package and coordinates of each corner point in the bounding box, the method further includes:
and training the parcel detection model by adopting a semi-supervised learning algorithm.
In one possible implementation manner of the present application, after performing image quality determination on the first belt transmission image to obtain a first determination result, the method further includes:
If the first judging result is that the first belt transmission image does not meet the first quality judging requirement of the image, before the next package arrives at the target area, re-acquiring a second belt transmission image of the target area shot by the industrial camera;
Performing image quality judgment on the second belt transmission image to obtain a first judgment result;
If the first judging result is that the second belt transmission image meets the first quality judging requirement of the image, dividing the belt area in the second belt transmission image to obtain a second belt division image, wherein the first quality judging requirement is that the second belt transmission image is a judging requirement of a non-overexposure image or a non-overdrising image;
Carrying out regression prediction on the position of the package in the second belt transmission image to obtain a boundary frame for displaying the position of the package and coordinates of each corner point in the boundary frame;
and determining the position of the package based on the coordinates of each corner point in the boundary box and the waybill information.
In another aspect, the present application provides a location determining device for a package, the device comprising:
the first acquisition unit is used for acquiring a first belt transmission image shot by a preset industrial camera and waybill information corresponding to the package scanned by a preset scanning device when the package passes through a target area;
the first image quality judging unit is used for judging the image quality of the first belt transmission image to obtain a first judging result;
The first segmentation unit is used for segmenting a belt region in the first belt transmission image to obtain a belt segmentation image if the first judgment result is that the first belt transmission image meets a first quality judgment requirement of the image, wherein the first quality judgment requirement is that the first belt transmission image is a non-overexposure image or a non-overexposure image;
the first regression prediction unit is used for carrying out regression prediction on the position of the package in the first belt segmentation image to obtain a boundary frame for displaying the position of the package and coordinates of each corner point in the boundary frame;
and the first determining unit is used for determining the position of the package based on the coordinates of each corner point in the boundary box and the waybill information.
In one possible implementation manner of the present application, the first image quality determining unit is specifically configured to:
Based on a histogram statistical method, counting the pixel distribution of the first belt transmission image to obtain the number of target pixels with pixel values in a preset pixel value interval, wherein the preset pixel value interval is a corresponding pixel value interval in an overexposure state or a corresponding pixel value interval in an overdrising state;
Comparing the number of the target pixels with the total number of pixels of the first belt transmission image to obtain the duty ratio of the target pixels in the first belt transmission image;
Comparing the duty ratio with a preset threshold value to obtain a comparison result;
If the duty ratio is greater than or equal to the threshold value, determining that the first belt transmission image does not meet a first quality judgment requirement of the image;
And if the duty ratio is smaller than the threshold value, determining that the first belt transmission image meets the first quality judgment requirement of the image.
In one possible implementation manner of the present application, the first regression prediction unit specifically includes:
The second image quality judging unit is used for judging the image quality of the first belt segmentation image to obtain a second judging result;
and the second regression prediction unit is used for carrying out regression prediction on the position of the package in the first belt segmentation image if the second judgment result is that the first belt transmission image meets the second quality judgment requirement of the image, so as to obtain a boundary frame for displaying the position of the package and coordinates of each corner point in the boundary frame.
In one possible implementation manner of the present application, the image quality determination is performed on the first belt split image to obtain a second determination result, which is specifically configured to:
And carrying out image quality judgment on the first belt segmentation image through a pre-trained image quality judgment model based on a deep learning algorithm to obtain a second judgment result.
In one possible implementation manner of the present application, the second regression prediction unit is specifically configured to:
And carrying out regression prediction on the position of the package in the first belt segmentation image through a pre-trained package detection model based on a deep learning algorithm to obtain a boundary box for displaying the position of the package and coordinates of each corner point in the boundary box.
In one possible implementation manner of the present application, before performing regression prediction on the position of the package in the first belt segmentation image through a pre-trained package detection model based on a deep learning algorithm to obtain a bounding box for displaying the position of the package and coordinates of each corner point in the bounding box, the apparatus is further configured to:
and training the parcel detection model by adopting a semi-supervised learning algorithm.
In one possible implementation manner of the present application, after performing image quality determination on the first belt transmission image, the apparatus is further configured to:
If the first judging result is that the first belt transmission image does not meet the first quality judging requirement of the image, before the next package arrives at the target area, re-acquiring a second belt transmission image of the target area shot by the industrial camera;
Performing image quality judgment on the second belt transmission image to obtain a first judgment result;
If the first judging result is that the second belt transmission image meets the first quality judging requirement of the image, dividing the belt area in the second belt transmission image to obtain a second belt division image, wherein the first quality judging requirement is that the second belt transmission image is a judging requirement of a non-overexposure image or a non-overdrising image;
Carrying out regression prediction on the position of the package in the second belt transmission image to obtain a boundary frame for displaying the position of the package and coordinates of each corner point in the boundary frame;
and determining the position of the package based on the coordinates of each corner point in the boundary box and the waybill information.
In another aspect, the present application also provides a computer apparatus, including:
one or more processors;
A memory; and
One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the location determination method of the package.
In another aspect, the present application also provides a computer readable storage medium having stored thereon a computer program to be loaded by a processor for performing the steps of the method of determining the location of a package.
The method for determining the position of the parcel comprises the steps of acquiring a first belt transmission image of a target area shot by a preset industrial camera and waybill information of the parcel obtained by scanning by a preset scanning device when the parcel passes through the target area; image quality judgment is carried out on the first belt transmission image, and a first judgment result is obtained; if the first judging result is that the first belt transmission image meets the first quality judging requirement of the image, dividing the belt area in the first belt transmission image to obtain a first belt division image, wherein the first quality judging requirement is that the first belt transmission image is a judging requirement of a non-overexposure image or a non-darkness image; carrying out regression prediction on the position of the package in the first belt segmentation image to obtain a boundary frame for displaying the position of the package and coordinates of each corner point in the boundary frame; and determining the position of the package based on the coordinates of each corner point in the bounding box and the waybill information. According to the embodiment of the application, under the condition that the position of the package cannot be quickly and accurately determined by the existing method, the image quality judgment is carried out on the first belt transmission image, then the belt area in the first belt transmission image which accords with the image quality judgment is segmented, regression prediction is carried out on the position of the package in the first belt transmission image, and finally the position of the package is accurately determined according to the coordinates of each corner point in the boundary frame and the waybill information, so that the situation that the position of the package cannot be accurately determined due to the overexposure or the overdrising phenomenon of the image is avoided, and the speed and the accuracy for determining the position of the package are improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic illustration of a scenario of a location determination system for packages provided by an embodiment of the present application;
FIG. 2 is a flow diagram of one embodiment of a method of location determination of a package provided in an embodiment of the present application;
FIG. 3 is a schematic flow chart of one embodiment of acquiring a second belt transmission image provided in an embodiment of the present application;
FIG. 4 is a schematic illustration of a first belt transmission image provided in an embodiment of the present application that does not meet a first quality determination requirement;
FIG. 5 is a flow chart of an embodiment of a first belt transmission image provided in an embodiment of the present application that does not meet a second quality determination requirement;
FIG. 6 is a schematic structural view of one embodiment of a location determining device for packages provided in an embodiment of the present application;
FIG. 7 is a schematic diagram of an embodiment of a computer device provided in an embodiment of the application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to fall within the scope of the application.
In the description of the present application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. indicate orientations or positional relationships based on the drawings are merely for convenience in describing the present application and simplifying the description, and do not indicate or imply that the apparatus or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present application. Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more of the described features. In the description of the present application, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
In the present application, the term "exemplary" is used to mean "serving as an example, instance, or illustration. Any embodiment described as "exemplary" in this disclosure is not necessarily to be construed as preferred or advantageous over other embodiments. The following description is presented to enable any person skilled in the art to make and use the application. In the following description, details are set forth for purposes of explanation. It will be apparent to one of ordinary skill in the art that the present application may be practiced without these specific details. In other instances, well-known structures and processes have not been described in detail so as not to obscure the description of the application with unnecessary detail. Thus, the present application is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.
The embodiment of the application provides a method and a device for determining the position of a package and related equipment thereof, and the method and the device are respectively described in detail below.
As shown in fig. 1, fig. 1 is a schematic view of a scenario of a location determining system for a package according to an embodiment of the present application, where the location determining system for a package may include a computer device 100, and a location determining apparatus for the package is integrated in the computer device 100, such as the computer device 100 in fig. 1.
The computer device 100 in the embodiment of the application is mainly used for acquiring a first belt transmission image of a target area shot by a preset industrial camera and the waybill information of the package scanned by a preset scanning device when the package passes through the target area; image quality judgment is carried out on the first belt transmission image, and a first judgment result is obtained; if the first judging result is that the first belt transmission image meets the first quality judging requirement of the image, dividing the belt area in the first belt transmission image to obtain a first belt division image, wherein the first quality judging requirement is that the first belt transmission image is a judging requirement of a non-overexposure image or a non-darkness image; carrying out regression prediction on the position of the package in the first belt segmentation image to obtain a boundary frame for displaying the position of the package and coordinates of each corner point in the boundary frame; and determining the position of the package based on the coordinates of each corner point in the bounding box and the waybill information.
In the embodiment of the present application, the computer device 100 may be a terminal or a server, and when the computer device 100 is a server, it may be an independent server, or may be a server network or a server cluster formed by servers, for example, the computer device 100 described in the embodiment of the present application includes, but is not limited to, a computer, a network host, a single network server, a plurality of network server sets, or a plurality of servers to construct a cloud server. Wherein the Cloud server is built from a large number of computers or web servers based on Cloud Computing (Cloud Computing).
It will be appreciated that when the computer device 100 is a terminal in the embodiments of the present application, the terminal used may be a device that includes both receiving and transmitting hardware, i.e., a device having receiving and transmitting hardware capable of performing two-way communications over a two-way communications link. Such a device may include: a cellular or other communication device having a single-line display or a multi-line display or a cellular or other communication device without a multi-line display. The computer device 100 may be a desktop terminal or a mobile terminal, and the computer device 100 may be one of a mobile phone, a tablet computer, a notebook computer, a medical auxiliary instrument, and the like.
It will be appreciated by those skilled in the art that the application environment shown in fig. 1 is merely an application scenario of the present application, and is not intended to limit the application scenario of the present application, and that other application environments may include more or fewer computer devices than those shown in fig. 1, for example, only 1 computer device is shown in fig. 1, and that the location determining system of the package may further include one or more other computer devices, which is not limited in detail herein.
It will be appreciated by those skilled in the art that the application environment shown in fig. 1 is merely an application scenario of the present application, and is not intended to limit the application scenario of the present application, and that other application environments may include more or fewer computer devices than those shown in fig. 1, for example, only 1 computer device is shown in fig. 1, and that the location determining system of the package may further include one or more other computer devices, which is not limited in detail herein.
In addition, as shown in FIG. 1, the location determination system of the package may also include a memory 200 for storing data, such as belt transmission images and location determination data of the package, such as location determination data of the package when the location determination system of the package is in operation.
It should be noted that, the schematic view of the scenario of the location determining system of the package shown in fig. 1 is only an example, and the location determining system of the package and the scenario described in the embodiments of the present application are for more clearly describing the technical solution of the embodiments of the present application, and do not constitute a limitation on the technical solution provided by the embodiments of the present application, and as one of ordinary skill in the art can know, along with the evolution of the location determining system of the package and the appearance of a new service scenario, the technical solution provided by the embodiments of the present application is equally applicable to similar technical problems.
Next, a method for determining a location of a package according to an embodiment of the present application will be described.
In the embodiment of the method for determining the location of a package according to the present application, a location determining device of the package is used as an execution body, and for simplicity and convenience of description, the execution body will be omitted in the subsequent method embodiments, and the location determining device of the package is applied to a computer device, and the method includes: when a parcel passes through a target area, acquiring a first belt transmission image of the target area shot by a preset industrial camera and waybill information of the parcel obtained by scanning by a preset scanning device; image quality judgment is carried out on the first belt transmission image, and a first judgment result is obtained; if the first judging result is that the first belt transmission image meets the first quality judging requirement of the image, dividing the belt area in the first belt transmission image to obtain a first belt division image, wherein the first quality judging requirement is that the first belt transmission image is a judging requirement of a non-overexposure image or a non-darkness image; carrying out regression prediction on the position of the package in the first belt segmentation image to obtain a boundary frame for displaying the position of the package and coordinates of each corner point in the boundary frame; and determining the position of the package based on the coordinates of each corner point in the bounding box and the waybill information.
Referring to fig. 2 to 7, fig. 2 is a flowchart illustrating an embodiment of a method for determining a location of a package according to an embodiment of the present application, where the method for determining a location of a package includes:
201. When a parcel passes through a target area, acquiring a first belt transmission image of the target area shot by a preset industrial camera and waybill information of the parcel obtained by scanning by a preset scanning device;
the method comprises the steps that a target area is planned in advance, an industrial camera and a scanning device are preset near the target area, the industrial camera is used for shooting a first belt transmission image in the target area, and the scanning device is used for scanning and identifying waybill information of a package.
202. Image quality judgment is carried out on the first belt transmission image, and a first judgment result is obtained;
In some embodiments of the present application, the determining the image quality of the first belt transmission image to obtain a first determination result includes: based on a histogram statistical method, counting the pixel distribution of the first belt transmission image to obtain the number of target pixels with pixel values in a preset pixel value interval, wherein the preset pixel value interval is a corresponding pixel value interval in an overexposure state or a corresponding pixel value interval in an overdrising state; comparing the number of the target pixels with the total number of pixels of the first belt transmission image to obtain the duty ratio of the target pixels in the first belt transmission image; comparing the duty ratio with a preset threshold value to obtain a comparison result, wherein the threshold value can be set according to actual conditions, and the threshold value is preferably 0.5; if the duty ratio is greater than or equal to the threshold value, determining that the first belt transmission image does not meet a first quality judgment requirement of the image; and if the duty ratio is smaller than the threshold value, determining that the first belt transmission image meets the first quality judgment requirement of the image.
The embodiment of the application can accurately judge the image quality of the first belt transmission image by adopting the mode.
203. If the first judging result is that the first belt transmission image meets the first quality judging requirement of the image, dividing the belt area in the first belt transmission image to obtain a first belt division image, wherein the first quality judging requirement is that the first belt transmission image is a judging requirement of a non-overexposure image or a non-darkness image;
Specifically, the application segments the belt region in the first belt transmission image through a preset segmentation algorithm to obtain a first belt segmentation image, and the Mask R-CNN segmentation algorithm is optimized in the embodiment of the application. Before the segmentation algorithm is used, the belt conveyor position marking is carried out on the images returned by the industrial camera manually, four corner points of each image marking are connected into a trapezoid frame, the trapezoid frame is a target area, the belt area is arranged in the frame, and the background is arranged outside the frame. Marking data by adopting a Mask R-CNN model according to training data: verification data = 8:2.
204. Carrying out regression prediction on the position of the package in the first belt segmentation image to obtain a boundary frame for displaying the position of the package and coordinates of each corner point in the boundary frame;
In some embodiments of the present application, the regression predicting the position of the package in the first belt segmentation image, to obtain a bounding box for displaying the position of the package, and coordinates of each corner point in the bounding box, includes: performing image quality judgment on the first belt segmentation image to obtain a second judgment result; and if the second judging result is that the first belt transmission image meets the second quality judging requirement of the image, carrying out regression prediction on the position of the package in the first belt segmentation image to obtain a boundary frame for displaying the position of the package and coordinates of each corner point in the boundary frame.
In some embodiments of the present application, the second determination result may be that the first belt transmission image does not meet the second quality determination requirement of the image, as shown in fig. 5 below, and the first belt transmission image may be partially overexposed or too dark to avoid the first quality determination requirement, and may be detected after the second image quality determination.
In some embodiments of the present application, the performing image quality determination on the first belt split image to obtain a second determination result includes: performing image quality judgment on the first belt segmentation image through a pre-trained image quality judgment model based on a deep learning algorithm to obtain a second judgment result; specifically, the EFFICIENTNET-b3 model is preferably used as an image quality judging model, and the labeling data are according to training data: verification data = 8:2.
In some embodiments of the present application, the regression predicting the position of the package in the first belt segmentation image, to obtain a bounding box for displaying the position of the package, and coordinates of each corner point in the bounding box, includes: and carrying out regression prediction on the position of the package in the first belt segmentation image through a pre-trained package detection model based on a deep learning algorithm to obtain a boundary box for displaying the position of the package and coordinates of each corner point in the boundary box.
In some embodiments of the present application, before performing regression prediction on the position of the package in the first belt segmentation image through a pre-trained package detection model based on a deep learning algorithm to obtain a bounding box for displaying the position of the package, and coordinates of each corner point in the bounding box, the method further includes: training the package detection model by adopting a semi-supervised learning algorithm, specifically, firstly labeling a package boundary box (labeling box) on a belt segmentation image obtained by segmenting a package, and obtaining 1000 pieces of labeled data in total and about 3 pieces of unlabeled data in total (the volume ratio of labeled data can be changed according to actual conditions). Based on the data, a SoftTeacher method is adopted for semi-supervised training. It should be noted that the data category is marked as a box type during marking, and the smallest external rectangle marking mode is adopted to mark the marking box.
In the semi-supervised training process, marked data adopts a conventional supervised learning training mode, and loss is marked as L s; in SoftTeacher algorithm, the loss of the unsupervised image is calculated as the sum of class loss and frame regression loss, in the application, only the package position is required to be regressed, and the package class is "box", so the loss of the unsupervised image is simplified into frame regression loss, and is recorded asThe model uses the Faster R-CNN and is derived from a weight sliding average (EMA) of a predetermined weight model.
205. And determining the position of the package based on the coordinates of each corner point in the bounding box and the waybill information.
Specifically, the package can be scratched through the coordinates of each corner point in the boundary box, and then the scratch and the waybill information are bound, so that the position of the package can be rapidly and accurately determined.
The method for determining the position of the parcel comprises the steps of acquiring a first belt transmission image of a target area shot by a preset industrial camera and waybill information of the parcel obtained by scanning by a preset scanning device when the parcel passes through the target area; image quality judgment is carried out on the first belt transmission image, and a first judgment result is obtained; if the first judging result is that the first belt transmission image meets the first quality judging requirement of the image, dividing the belt area in the first belt transmission image to obtain a first belt division image, wherein the first quality judging requirement is that the first belt transmission image is a judging requirement of a non-overexposure image or a non-darkness image; carrying out regression prediction on the position of the package in the first belt segmentation image to obtain a boundary frame for displaying the position of the package and coordinates of each corner point in the boundary frame; and determining the position of the package based on the coordinates of each corner point in the bounding box and the waybill information. According to the embodiment of the application, under the condition that the position of the package cannot be quickly and accurately determined by the existing method, the image quality judgment is carried out on the first belt transmission image, then the belt area in the first belt transmission image which accords with the image quality judgment is segmented, regression prediction is carried out on the position of the package in the first belt transmission image, and finally the position of the package is accurately determined according to the coordinates of each corner point in the boundary frame and the waybill information, so that the situation that the position of the package cannot be accurately determined due to the overexposure or the overdrising phenomenon of the image is avoided, and the speed and the accuracy for determining the position of the package are improved.
In other embodiments of the present application, as shown in fig. 3, after performing image quality determination on the first belt transmission image to obtain a first determination result, the method further includes:
301. If the first judging result is that the first belt transmission image does not meet the first quality judging requirement of the image, re-acquiring a second belt transmission image of the target area shot by the industrial camera before the next package reaches the target area;
as shown in fig. 4, fig. 4 is a schematic diagram of a first belt transmission image according to an embodiment of the present application that does not meet a first quality determination requirement.
302. Image quality judgment is carried out on the second belt transmission image, and a first judgment result is obtained;
specifically, the image quality determination manner is the same as that adopted in the above embodiment, and will not be described herein.
303. If the first judging result is that the second belt transmission image meets the first quality judging requirement of the image, dividing the belt area in the second belt transmission image to obtain a second belt division image, wherein the first quality judging requirement is that the second belt transmission image is a judging requirement of a non-overexposure image or a non-darkness image;
specifically, the division manner is the same as that adopted in the above embodiment, and will not be described herein.
304. Carrying out regression prediction on the position of the package in the second belt transmission image to obtain a boundary frame for displaying the position of the package and coordinates of each corner point in the boundary frame;
specifically, the regression prediction method is the same as that adopted in the above embodiment, and will not be described herein.
305. And determining the position of the package based on the coordinates of each corner point in the bounding box and the waybill information.
Specifically, the location manner of the package is the same as that adopted in the above embodiment, and will not be described herein.
According to the embodiment of the application, under the condition that the first belt transmission image does not meet the first quality judgment requirement of the image, before the next package arrives at the target area, the second belt transmission image of the target area shot by the industrial camera is acquired again, so that the scheme accuracy is improved by avoiding special situations, such as the situation that the abnormal situation occurs in a short time due to the fact that a worker adjusts light.
In order to better implement the method for determining the location of the package in the embodiment of the present application, based on the method for determining the location of the package, the embodiment of the present application further provides a device for determining the location of the package, as shown in fig. 6, where the device 600 for determining the location of the package includes:
A first acquiring unit 601, configured to acquire, when a parcel passes through a target area, a first belt transmission image captured by a preset industrial camera and waybill information corresponding to the parcel scanned by a preset scanning device;
A first image quality determining unit 602, configured to perform image quality determination on the first belt transmission image, to obtain a first determination result;
A first dividing unit 603, configured to divide a belt area in the first belt transmission image to obtain a belt divided image if the first determination result indicates that the first belt transmission image meets a first quality determination requirement of an image, where the first quality determination requirement is a determination requirement that the first belt transmission image is a non-overexposed image or a non-excessively dark image;
A first regression prediction unit 604, configured to perform regression prediction on a location of a package in the first belt segmentation image, to obtain a bounding box for displaying the location of the package, and coordinates of each corner point in the bounding box;
a first determining unit 605 is configured to determine a location of the package based on coordinates of each corner point in the bounding box and the waybill information.
In one possible implementation manner of the present application, the first image quality determining unit 602 is specifically configured to:
Based on a histogram statistical method, counting the pixel distribution of the first belt transmission image to obtain the number of target pixels with pixel values in a preset pixel value interval, wherein the preset pixel value interval is a corresponding pixel value interval in an overexposure state or a corresponding pixel value interval in an overdrising state;
Comparing the number of the target pixels with the total number of pixels of the first belt transmission image to obtain the duty ratio of the target pixels in the first belt transmission image;
Comparing the duty ratio with a preset threshold value to obtain a comparison result;
If the duty ratio is greater than or equal to the threshold value, determining that the first belt transmission image does not meet a first quality judgment requirement of the image;
And if the duty ratio is smaller than the threshold value, determining that the first belt transmission image meets the first quality judgment requirement of the image.
In one possible implementation manner of the present application, the first regression prediction unit 604 specifically includes:
The second image quality judging unit is used for judging the image quality of the first belt segmentation image to obtain a second judging result;
and the second regression prediction unit is used for carrying out regression prediction on the position of the package in the first belt segmentation image if the second judgment result is that the first belt transmission image meets the second quality judgment requirement of the image, so as to obtain a boundary frame for displaying the position of the package and coordinates of each corner point in the boundary frame.
In one possible implementation manner of the present application, the image quality determination is performed on the first belt split image to obtain a second determination result, which is specifically configured to:
And carrying out image quality judgment on the first belt segmentation image through a pre-trained image quality judgment model based on a deep learning algorithm to obtain a second judgment result.
In one possible implementation manner of the present application, the second regression prediction unit is specifically configured to:
And carrying out regression prediction on the position of the package in the first belt segmentation image through a pre-trained package detection model based on a deep learning algorithm to obtain a boundary box for displaying the position of the package and coordinates of each corner point in the boundary box.
In one possible implementation manner of the present application, before performing regression prediction on the position of the package in the first belt segmentation image through a pre-trained package detection model based on a deep learning algorithm to obtain a bounding box for displaying the position of the package and coordinates of each corner point in the bounding box, the apparatus is further configured to:
and training the parcel detection model by adopting a semi-supervised learning algorithm.
In one possible implementation manner of the present application, after performing image quality determination on the first belt transmission image, the apparatus is further configured to:
If the first judging result is that the first belt transmission image does not meet the first quality judging requirement of the image, before the next package arrives at the target area, re-acquiring a second belt transmission image of the target area shot by the industrial camera;
Performing image quality judgment on the second belt transmission image to obtain a first judgment result;
If the first judging result is that the second belt transmission image meets the first quality judging requirement of the image, dividing the belt area in the second belt transmission image to obtain a second belt division image, wherein the first quality judging requirement is that the second belt transmission image is a judging requirement of a non-overexposure image or a non-overdrising image;
Carrying out regression prediction on the position of the package in the second belt transmission image to obtain a boundary frame for displaying the position of the package and coordinates of each corner point in the boundary frame;
and determining the position of the package based on the coordinates of each corner point in the boundary box and the waybill information.
The position determining device for the package provided by the application comprises a first obtaining unit 601, a second obtaining unit and a third obtaining unit, wherein the first obtaining unit is used for obtaining a first belt transmission image shot by a preset industrial camera and waybill information corresponding to the package scanned by a preset scanning device when the package passes through a target area; a first image quality determining unit 602, configured to perform image quality determination on the first belt transmission image, to obtain a first determination result; a first dividing unit 603, configured to divide a belt area in the first belt transmission image to obtain a belt divided image if the first determination result indicates that the first belt transmission image meets a first quality determination requirement of an image, where the first quality determination requirement is a determination requirement that the first belt transmission image is a non-overexposed image or a non-excessively dark image; a first regression prediction unit 604, configured to perform regression prediction on a location of a package in the first belt segmentation image, to obtain a bounding box for displaying the location of the package, and coordinates of each corner point in the bounding box; a first determining unit 605 is configured to determine a location of the package based on coordinates of each corner point in the bounding box and the waybill information. According to the embodiment of the application, under the condition that the position of the package cannot be quickly and accurately determined by the existing method, the image quality judgment is carried out on the first belt transmission image, then the belt area in the first belt transmission image which accords with the image quality judgment is segmented, regression prediction is carried out on the position of the package in the first belt transmission image, and finally the position of the package is accurately determined according to the coordinates of each corner point in the boundary frame and the waybill information, so that the situation that the position of the package cannot be accurately determined due to the overexposure or the overdrising phenomenon of the image is avoided, and the speed and the accuracy for determining the position of the package are improved.
In addition to the above-described method and apparatus for determining a location of a package, an embodiment of the present application further provides a computer device, which integrates any of the location determining apparatuses of a package provided in the embodiment of the present application, where the computer device includes:
one or more processors;
A memory; and
One or more applications, wherein the one or more applications are stored in the memory and configured to perform the operations of any of the methods described in any of the location determination method embodiments of the package described above by the processor.
The embodiment of the application also provides computer equipment which integrates the position determining device of any package provided by the embodiment of the application. As shown in fig. 7, a schematic structural diagram of a computer device according to an embodiment of the present application is shown, specifically:
The computer device may include one or more processors 701 of a processing core, a storage unit 702 of one or more computer readable storage media, a power supply 703, and an input unit 704, among other components. Those skilled in the art will appreciate that the computer device structure shown in FIG. 7 is not limiting of the computer device and may include more or fewer components than shown, or may be combined with certain components, or a different arrangement of components. Wherein:
The processor 701 is a control center of the computer device, connects respective portions of the entire computer device using various interfaces and lines, and performs various functions of the computer device and processes data by running or executing software programs and/or modules stored in the storage unit 702 and calling data stored in the storage unit 702, thereby performing overall monitoring of the computer device. Optionally, processor 701 may include one or more processing cores; preferably, the processor 701 may integrate an application processor and a modem processor, wherein the application processor primarily handles operating systems, user interfaces, applications, etc., and the modem processor primarily handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 701.
The storage unit 702 may be used to store software programs and modules, and the processor 701 performs various functional applications and data processing by executing the software programs and modules stored in the storage unit 702. The storage unit 702 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data created according to the use of the computer device, etc. In addition, the storage unit 702 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory unit 702 may also include a memory controller to provide access to the memory unit 702 by the processor 701.
The computer device further comprises a power supply 703 for powering the various components, preferably the power supply 703 is logically connected to the processor 701 by a power management system, whereby the functions of managing charging, discharging, and power consumption are performed by the power management system. The power supply 703 may also include one or more of any component, such as a direct current or alternating current power supply, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, etc.
The computer device may further comprise an input unit 704, which input unit 704 may be used for receiving input numerical or character information and generating keyboard, mouse, joystick, optical or trackball signal inputs in connection with user settings and function control.
Although not shown, the computer device may further include a display unit or the like, which is not described herein. In particular, in the embodiment of the present application, the processor 701 in the computer device loads executable files corresponding to the processes of one or more application programs into the storage unit 702 according to the following instructions, and the processor 701 executes the application programs stored in the storage unit 702, so as to implement various functions, as follows:
When a parcel passes through a target area, acquiring a first belt transmission image of the target area shot by a preset industrial camera and waybill information of the parcel obtained by scanning by a preset scanning device; image quality judgment is carried out on the first belt transmission image, and a first judgment result is obtained; if the first judging result is that the first belt transmission image meets the first quality judging requirement of the image, dividing the belt area in the first belt transmission image to obtain a first belt division image, wherein the first quality judging requirement is that the first belt transmission image is a judging requirement of a non-overexposure image or a non-darkness image; carrying out regression prediction on the position of the package in the first belt segmentation image to obtain a boundary frame for displaying the position of the package and coordinates of each corner point in the boundary frame; and determining the position of the package based on the coordinates of each corner point in the bounding box and the waybill information.
The method for determining the position of the parcel comprises the steps of acquiring a first belt transmission image of a target area shot by a preset industrial camera and waybill information of the parcel obtained by scanning by a preset scanning device when the parcel passes through the target area; image quality judgment is carried out on the first belt transmission image, and a first judgment result is obtained; if the first judging result is that the first belt transmission image meets the first quality judging requirement of the image, dividing the belt area in the first belt transmission image to obtain a first belt division image, wherein the first quality judging requirement is that the first belt transmission image is a judging requirement of a non-overexposure image or a non-darkness image; carrying out regression prediction on the position of the package in the first belt segmentation image to obtain a boundary frame for displaying the position of the package and coordinates of each corner point in the boundary frame; and determining the position of the package based on the coordinates of each corner point in the bounding box and the waybill information. According to the embodiment of the application, under the condition that the position of the package cannot be quickly and accurately determined by the existing method, the image quality judgment is carried out on the first belt transmission image, then the belt area in the first belt transmission image which accords with the image quality judgment is segmented, regression prediction is carried out on the position of the package in the first belt transmission image, and finally the position of the package is accurately determined according to the coordinates of each corner point in the boundary frame and the waybill information, so that the situation that the position of the package cannot be accurately determined due to the overexposure or the overdrising phenomenon of the image is avoided, and the speed and the accuracy for determining the position of the package are improved.
To this end, embodiments of the present application provide a computer-readable storage medium, which may include: read Only Memory (ROM), random access Memory (RAM, random Access Memory), magnetic or optical disk, and the like. The computer readable storage medium has stored therein a plurality of instructions that can be loaded by a processor to perform the steps of any of the parcel location determination methods provided by the embodiments of the present application. For example, the instructions may perform the steps of:
When a parcel passes through a target area, acquiring a first belt transmission image of the target area shot by a preset industrial camera and waybill information of the parcel obtained by scanning by a preset scanning device; image quality judgment is carried out on the first belt transmission image, and a first judgment result is obtained; if the first judging result is that the first belt transmission image meets the first quality judging requirement of the image, dividing the belt area in the first belt transmission image to obtain a first belt division image, wherein the first quality judging requirement is that the first belt transmission image is a judging requirement of a non-overexposure image or a non-darkness image; carrying out regression prediction on the position of the package in the first belt segmentation image to obtain a boundary frame for displaying the position of the package and coordinates of each corner point in the boundary frame; and determining the position of the package based on the coordinates of each corner point in the bounding box and the waybill information.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments.
The above description of the location determining method, apparatus and related devices for packages provided by the embodiments of the present application has been provided in detail, and specific examples are applied herein to illustrate the principles and embodiments of the present application, where the above description of the embodiments is only for helping to understand the method and core ideas of the present application; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in light of the ideas of the present application, the present description should not be construed as limiting the present application.
Claims (10)
1. A method of determining the location of a package, the method comprising:
When a parcel passes through a target area, acquiring a first belt transmission image shot by a preset industrial camera and waybill information of the parcel obtained by scanning by a preset scanning device;
image quality judgment is carried out on the first belt transmission image, and a first judgment result is obtained;
If the first judging result is that the first belt transmission image meets the first quality judging requirement of the image, dividing the belt area in the first belt transmission image to obtain a first belt division image, wherein the first quality judging requirement is that the first belt transmission image is a judging requirement of a non-overexposure image or a non-overdrising image;
Carrying out regression prediction on the position of the package in the first belt segmentation image to obtain a boundary frame for displaying the position of the package and coordinates of each corner point in the boundary frame;
and determining the position of the package based on the coordinates of each corner point in the boundary box and the waybill information.
2. The method of claim 1, wherein said determining the image quality of the first belt transmission image results in a first determination result, comprising:
Based on a histogram statistical method, counting the pixel distribution of the first belt transmission image to obtain the number of target pixels with pixel values in a preset pixel value interval, wherein the preset pixel value interval is a corresponding pixel value interval in an overexposure state or a corresponding pixel value interval in an overdrising state;
Comparing the number of the target pixels with the total number of pixels of the first belt transmission image to obtain the duty ratio of the target pixels in the first belt transmission image;
Comparing the duty ratio with a preset threshold value to obtain a comparison result;
If the duty ratio is greater than or equal to the threshold value, determining that the first belt transmission image does not meet a first quality judgment requirement of the image;
And if the duty ratio is smaller than the threshold value, determining that the first belt transmission image meets the first quality judgment requirement of the image.
3. The method for determining the position of a package according to claim 1, wherein regression predicting the position of the package in the first belt segment image obtains a bounding box for displaying the position of the package, and coordinates of each corner point in the bounding box, comprising:
Performing image quality judgment on the first belt segmentation image to obtain a second judgment result;
And if the second judging result is that the first belt transmission image meets the second quality judging requirement of the image, carrying out regression prediction on the position of the package in the first belt segmentation image to obtain a boundary frame for displaying the position of the package and coordinates of each corner point in the boundary frame.
4. A method of determining a location of a package according to claim 3, wherein said determining the image quality of said first belt segment image results in a second determination result comprising:
And carrying out image quality judgment on the first belt segmentation image through a pre-trained image quality judgment model based on a deep learning algorithm to obtain a second judgment result.
5. The method for determining the position of a package according to claim 3, wherein performing regression prediction on the position of the package in the first belt segment image to obtain a bounding box for displaying the position of the package, and coordinates of each corner point in the bounding box, comprises:
And carrying out regression prediction on the position of the package in the first belt segmentation image through a pre-trained package detection model based on a deep learning algorithm to obtain a boundary box for displaying the position of the package and coordinates of each corner point in the boundary box.
6. The method of claim 5, wherein prior to regression predicting the location of the parcel in the first belt segmentation image by a pre-trained deep learning algorithm based parcel detection model to obtain a bounding box for displaying the location of the parcel and coordinates of each corner point in the bounding box, the method further comprises:
and training the parcel detection model by adopting a semi-supervised learning algorithm.
7. The method of claim 1, wherein after determining the image quality of the first belt transmission image, the method further comprises:
If the first judging result is that the first belt transmission image does not meet the first quality judging requirement of the image, before the next package arrives at the target area, re-acquiring a second belt transmission image of the target area shot by the industrial camera;
Performing image quality judgment on the second belt transmission image to obtain a first judgment result;
If the first judging result is that the second belt transmission image meets the first quality judging requirement of the image, dividing the belt area in the second belt transmission image to obtain a second belt division image, wherein the first quality judging requirement is that the second belt transmission image is a judging requirement of a non-overexposure image or a non-overdrising image;
Carrying out regression prediction on the position of the package in the second belt transmission image to obtain a boundary frame for displaying the position of the package and coordinates of each corner point in the boundary frame;
and determining the position of the package based on the coordinates of each corner point in the boundary box and the waybill information.
8. A location determining device for a package, the device comprising:
the first acquisition unit is used for acquiring a first belt transmission image shot by a preset industrial camera and waybill information corresponding to the package scanned by a preset scanning device when the package passes through a target area;
the first image quality judging unit is used for judging the image quality of the first belt transmission image to obtain a first judging result;
The first segmentation unit is used for segmenting a belt region in the first belt transmission image to obtain a belt segmentation image if the first judgment result is that the first belt transmission image meets a first quality judgment requirement of the image, wherein the first quality judgment requirement is that the first belt transmission image is a non-overexposure image or a non-overexposure image;
the first regression prediction unit is used for carrying out regression prediction on the position of the package in the first belt segmentation image to obtain a boundary frame for displaying the position of the package and coordinates of each corner point in the boundary frame;
and the first determining unit is used for determining the position of the package based on the coordinates of each corner point in the boundary box and the waybill information.
9. A computer device, the computer device comprising:
one or more processors;
A memory; and
One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the location determination method of the package of any of claims 1 to 7.
10. A computer readable storage medium, having stored thereon a computer program, the computer program being loaded by a processor to perform the steps of the method of location determination of a package according to any of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211715810.6A CN118279223A (en) | 2022-12-29 | 2022-12-29 | Method and device for determining position of package and related equipment |
| PCT/CN2023/132825 WO2024139842A1 (en) | 2022-12-29 | 2023-11-21 | Method and apparatus for determining position of parcel, and related device thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211715810.6A CN118279223A (en) | 2022-12-29 | 2022-12-29 | Method and device for determining position of package and related equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118279223A true CN118279223A (en) | 2024-07-02 |
Family
ID=91643072
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211715810.6A Pending CN118279223A (en) | 2022-12-29 | 2022-12-29 | Method and device for determining position of package and related equipment |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN118279223A (en) |
| WO (1) | WO2024139842A1 (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118657947B (en) * | 2024-08-20 | 2024-11-22 | 湖南苏科智能科技有限公司 | Stacked package segmentation method, system, equipment and storage medium |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111709987B (en) * | 2020-06-11 | 2023-04-07 | 上海东普信息科技有限公司 | Package volume measuring method, device, equipment and storage medium |
| CN114255199A (en) * | 2020-09-10 | 2022-03-29 | 顺丰科技有限公司 | Package quantity detection method and device and storage medium |
| CN114529491A (en) * | 2020-10-30 | 2022-05-24 | 顺丰科技有限公司 | Image quality detection method, device, electronic equipment and storage medium |
| AU2021204581A1 (en) * | 2021-02-22 | 2022-09-08 | Sensetime International Pte. Ltd. | Methods, apparatuses, devices and storage media for predicting correlation between objects involved in image |
-
2022
- 2022-12-29 CN CN202211715810.6A patent/CN118279223A/en active Pending
-
2023
- 2023-11-21 WO PCT/CN2023/132825 patent/WO2024139842A1/en unknown
Also Published As
| Publication number | Publication date |
|---|---|
| WO2024139842A1 (en) | 2024-07-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110309824B (en) | Character detection method and device and terminal | |
| EP3620981A1 (en) | Object detection method, device, apparatus and computer-readable storage medium | |
| CN118279223A (en) | Method and device for determining position of package and related equipment | |
| CN113822144A (en) | Target detection method and device, computer equipment and storage medium | |
| CN114764821B (en) | Moving object detection method, moving object detection device, electronic equipment and storage medium | |
| CN114693946A (en) | Image anomaly detection method and device, computer equipment and storage medium | |
| CN112990189B (en) | Cargo congestion identification method and device, electronic equipment and storage medium | |
| CN114663340B (en) | Method and device for detecting package breakage, electronic equipment and storage medium | |
| CN114529843A (en) | Cargo congestion identification method and device, electronic equipment and storage medium | |
| CN118298205A (en) | Logistics sorting risk early warning method and device and related equipment | |
| CN114494406B (en) | Medical image processing method, device, terminal and computer readable storage medium | |
| CN114118114B (en) | Image detection method, device and storage medium thereof | |
| CN115861769A (en) | Training method of plastic shell defect detection model, and plastic shell defect detection method and device | |
| CN113538449B (en) | Image correction method, device, server and storage medium | |
| CN113065378B (en) | Method, device, server and storage medium for detecting article violation throw | |
| CN118279898A (en) | Automatic identification method and device for regular box body of express mail and related equipment thereof | |
| CN115272682A (en) | Target object detection method, target detection model training method and electronic equipment | |
| CN115619698A (en) | Method and device for detecting defects of circuit board and model training method | |
| CN114519793A (en) | Target object detection method and device, electronic equipment and storage medium | |
| CN112308100A (en) | Loading and unloading port state detection method, device, server and storage | |
| CN118230234A (en) | Method, device, computer equipment and storage medium for detecting carryover | |
| EP4332889A1 (en) | Method and apparatus for testing imaging consistency of system, and computer storage medium | |
| CN118279777A (en) | Video key frame identification method and device | |
| CN118247719A (en) | Early warning method and device for dumping cage vehicle and related equipment thereof | |
| CN118262203A (en) | Contraband detection method, device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |