CN113034574B - Commodity ground heap area calculation method and system based on target detection - Google Patents
Commodity ground heap area calculation method and system based on target detection Download PDFInfo
- Publication number
- CN113034574B CN113034574B CN202110568226.1A CN202110568226A CN113034574B CN 113034574 B CN113034574 B CN 113034574B CN 202110568226 A CN202110568226 A CN 202110568226A CN 113034574 B CN113034574 B CN 113034574B
- Authority
- CN
- China
- Prior art keywords
- projection
- scene
- calculating
- commodity
- ground
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
Abstract
The invention discloses a commodity ground heap area calculation method and a system based on target detection, wherein the method comprises the following steps: extracting a ground heap scene of the picture identification result, and calculating a projection edge of a ground heap bottom layer; judging the type of the ground heap scene according to the projection edge, and matching different methods for different types to calculate to obtain a layered projection line; and calculating the ground pile area according to the longest projection line in the layered projection lines. The commodity ground pile area calculating method based on the target detection overcomes the defects of large error and low efficiency in ground pile area calculation in the prior art, realizes quick and accurate calculation of the commodity ground pile area, and provides reliable basis for analysis of indexes such as whether a sales promotion product occupies gold positions.
Description
Technical Field
The invention relates to the technical field of computer vision, in particular to a commodity ground heap area calculation method and system based on target detection.
Background
The ground heap is a common display type sales promotion means, which not only requires novel theme and neat stacking, but also requires that corresponding sales promotion information be clear at a glance so as to achieve the purpose of quickly capturing consumers. In the past, whether ground push display of each shop terminal is reasonable mainly depends on manual statistics, so that a large amount of time is needed to check display and tally, and only sampling survey is often adopted, and complete and real commodity display information cannot be obtained.
In order to improve the efficiency of the ground-based display inspection work, in the prior art, an artificial intelligence algorithm is applied to commodity display identification and analysis, a worker acquires a commodity display diagram through a mobile device, identifies display scenes in the images based on a deep learning-based target detection method, such as common scenes of a goods shelf, an end frame, a freezer, a ground pile and the like, and then calculates information of the product, competitive products, the number of layers of the goods shelf, the number of layers of the commodity, vacancy information, the ground pile area and the like. However, for the calculation of the area of the commodity pile, the existing algorithm has the defects of low efficiency and inaccurate result. Therefore, how to provide a calculation method to quickly and accurately calculate the area of the commodity pile is one of the technical problems to be solved in the field.
Disclosure of Invention
The invention aims to provide a commodity ground heap area calculation method and system based on target detection, and the method can solve the technical problems of low efficiency and inaccurate result of the existing algorithm.
In order to overcome the defects in the prior art, the invention provides a commodity pile area calculation method based on target detection, which comprises the following steps:
extracting a ground heap scene of the picture identification result, and calculating a projection edge of a ground heap bottom layer;
judging the type of the ground heap scene according to the projection edge, and matching different methods for different types to calculate to obtain a layered projection line;
and calculating the ground pile area according to the longest projection line in the layered projection lines.
Further, the determining the type of the ground heap scene according to the projected edge includes:
judging whether the effective edges of the projection edges are 1; if yes, the scene is shot positively; if not, calculating the included angle of the projection edge;
judging whether the included angle meets a preset condition or not; if yes, the scene is shot positively; if not, the scene is shot laterally.
Further, the calculating the layered projection line for different types of matching different methods includes:
when the type is a side shooting scene, calculating the saturation of the projection edge;
if the saturation is smaller than a first preset threshold, fitting the current projection edge;
and calculating the length of the projection edge according to the actual size of the product on the projection edge after fitting, and obtaining all layered projection lines after iterative calculation.
Further, the calculating the layered projection line for different types of matching different methods further includes:
when the type is a positive shooting scene, layering is carried out in the direction vertical to the ground;
judging whether continuous products exist in each layer; if so, fitting the projection edge of the product;
if not, connecting the centers of the products which are farthest away in the same layer, and taking line segments obtained by connecting the lines as layered projection lines.
Further, fitting is performed using the least squares method.
Further, before the extracting the ground heap scene of the picture recognition result, the method includes:
identifying a tested commodity based on a deep learning target detection method, and carrying out scene segmentation and layering processing on the tested commodity;
and calculating the center coordinates of the layered tested commodity by using a matrix operation method, and matching the tested commodity with the corresponding scene and the layer according to the calculation result.
The invention also provides a commodity pile area calculation system based on target detection, which comprises:
the identification module is used for extracting a ground heap scene of the picture identification result and calculating a projection edge of a ground heap bottom layer;
the layered projection line acquisition module is used for judging the type of the ground heap scene according to the projection edge and calculating to obtain layered projection lines for different types of matching different methods;
and the ground heap area calculation module is used for calculating the ground heap area according to the longest projection line in the layered projection lines.
Further, the layered projection line module is further configured to:
judging whether the effective edges of the projection edges are 1; if yes, the scene is shot positively; if not, calculating the included angle of the projection edge;
judging whether the included angle meets a preset condition or not; if yes, the scene is shot positively; if not, the scene is shot laterally.
The present invention also provides a terminal device, comprising:
one or more processors;
a memory coupled to the processor for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a commodity heap area calculation method based on object detection as recited in any one of the above.
The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the method for calculating the area of a stack of goods based on object detection as described in any one of the above.
Compared with the prior art, the invention has the beneficial effects that:
1) the processing speed is high, the commodity detection and identification and the scene instance segmentation model are processed in parallel, and the reasoning calculation is quickly realized through the GPU acceleration.
2) The recognition precision is high, the precision of commodity detection recognition and scene instance segmentation reaches more than 93%, and reliable basis is provided for analysis of indexes such as fullness, purity, product arrangement area, ground heap commodity occupation area, gold position occupied by main push products and the like of the freezer, the goods shelf and the ground heap.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flowchart of a commodity pile area calculation method based on target detection according to an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of a ground push scenario in a side shot mode according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a ground push scene as a positive shot according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a commodity pile area calculation system based on object detection according to an embodiment of the present invention.
Detailed Description
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 only a part of the embodiments of the present invention, and not all of the embodiments. 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.
It should be understood that the step numbers used herein are for convenience of description only and are not intended as limitations on the order in which the steps are performed.
It is to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
The terms "comprises" and "comprising" indicate the presence of the described features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
The term "and/or" refers to and includes any and all possible combinations of one or more of the associated listed items.
In a first aspect:
referring to fig. 1, an embodiment of the present invention provides a method for calculating a commodity pile area based on target detection, including:
s10, extracting a ground heap scene of the picture recognition result, and calculating a projection edge of a ground heap bottom layer;
in this step, according to the recognition result, the product commodity (which is to be included in the ground dump scene) with the closest euclidean distance from the top point of the lower left corner of the image, the lowest point in the y-axis direction of the image, and the top point of the lower right corner of the image is found, and then the lower left corner point and the lowest point, the lower right corner point and the lowest point are connected respectively to obtain two projection side lengths of the ground dump, as shown in fig. 2. When the ground heap scene in the picture is the situation shown in fig. 3, that is, when the picture is shot in the front direction (the ground heap scene mainly includes two situations of shot in the front direction and shot in the side direction, and the projection lines of the two situations are obviously different), only one effective projection edge may exist (the effective projection edge is obtained when the head and tail vertexes of the edge are not overlapped).
S20, judging the type of the ground heap scene according to the projection edge, and calculating to obtain layered projection lines for different types by matching different methods;
in a specific embodiment, the determining the type of the heap scene according to the projected edge mainly includes the following steps:
judging whether the effective edges of the projection edges are 1; if yes, the scene is shot positively; if not, calculating the included angle of the projection edge;
judging whether the included angle meets a preset condition or not; if yes, the scene is shot positively; if not, the scene is shot laterally. It should be noted that the preset conditions are as follows: when the angle range is 178-180 degrees, the scene is regarded as a positive shooting scene; otherwise, it is considered as a side-shot scene. In practical applications, the preset condition may be selected from other angle ranges according to practical requirements or empirical values, and is not further limited herein.
In a specific embodiment, the calculating the layered projection line for different types of matching and different methods includes:
when the type is a side-shooting scene: firstly, calculating the saturation of the projection edge; if the saturation is smaller than a first preset threshold, fitting the current projection edge; and finally, calculating the length of the projection edge according to the actual size of the product on the projection edge after fitting, and obtaining all layered projection lines after iterative calculation.
Specifically, the present embodiment includes the following steps:
A) the saturation is mainly calculated by calculating the saturation of the left projection edge and the right projection edge under a side shooting scene:
wherein the content of the first and second substances,
respectively represent a left projection side and a right projection side,
representing projected edges
Length in the image;
representing the saturation of the projection;
representing projected edges
N products of the product are provided;
indicating product
Width in the image, for approximate substitution of the article
At the edge
Is measured.
Further, the size of the first preset threshold of the saturation is judged. Typically, the first predetermined threshold is selected to be 0.75, and when the saturation of the projected edge is less than 0.75, this indicates that there is a vacancy or misalignment in the line segment, and the line segment is of poor quality. At which time an attempt is made to re-fit the line segment. However, 0.75 is only a preferred way, and other angles can be selected according to actual needs or empirical values in practical operation, and are not further limited herein.
Further, the method for re-fitting the adjustment line segment comprises the following steps:
sorting the central coordinates of the products on the line segment from left to right according to an x axis, and determining that the distance between the x axis of two adjacent products is not more than half of the average width of the products, so that the products are in a continuous state; if at least 3 continuous products exist, extracting a longest continuous product set, and fitting a line segment by adopting a least square method; otherwise, no processing is performed.
B) Calculating the actual length of the projection edge according to the actual width and height of the product, and storing the product on the projection edge and the edge of the layer and the projection edge length
C) And (4) recalculating the projection edge of the bottommost layer of the ground pile from the rest of the products, and then repeating the process of the step A) until all ground pile layers and the projection edge length of each layer are calculated completely.
In a specific embodiment, the calculating the layered projection line for different types of matching and different methods further includes:
when the type is a positive shooting scene, layering is carried out in the direction vertical to the ground;
judging whether continuous products exist in each layer; if so, fitting the projection edge of the product;
if not, connecting the centers of the products which are farthest away in the same layer, and taking line segments obtained by connecting the lines as layered projection lines.
In this embodiment, since the ground pile belongs to the positive shooting condition, the side length of the bottom layer projection obtained in step a) is usually incomplete due to the inclination of the shooting angle, and there is a significant defect. At this point, the layering information and the heap area may be calculated iteratively as follows, as shown in FIG. 3.
1) Firstly, finding the commodity with the lowest center in the y-axis direction, then calculating the average height of the rest commodities, and classifying the commodities which are within the range of 1 average height from the commodity in the y-axis direction as the same layer; the above process is then repeated for the remaining items until all of the tiers have been calculated.
2) Traversing each layer, sequencing the product detection frames of each layer from left to right according to the central coordinates of the product detection frames, searching the longest continuous product set, and fitting the projection line segments of the layer by adopting a least square method; if no continuous product exists, the center of the product at the leftmost end is connected with the center of the product at the rightmost end to be used as the projection line segment of the layer, and then the actual length of the line segment of the layer is calculated and stored.
And S30, calculating the ground pile area according to the longest projection line in the layered projection lines.
In this step, the longest edge of all layered projection edges is found, and then the ground heap area is calculated, wherein the area formula is as follows:
in the formula (I), the compound is shown in the specification,
the ground push projection is approximately square, being the longest projected side.
The commodity ground pile area calculation method based on the target detection, provided by the embodiment of the invention, realizes the quick and accurate calculation of the commodity ground pile area, and provides a reliable basis for the analysis of indexes such as whether a sales promotion product occupies a gold position.
In one embodiment, before the extracting the ground heap scene of the picture recognition result, the method includes:
identifying a tested commodity based on a deep learning target detection method, and carrying out scene segmentation and layering processing on the tested commodity;
and calculating the center coordinates of the layered tested commodity by using a matrix operation method, and matching the tested commodity with the corresponding scene and the layer according to the calculation result.
In a second aspect:
referring to fig. 4, the present invention further provides a system for calculating a commodity pile area based on target detection, including:
the identification module 01 is used for extracting a ground heap scene of the picture identification result and calculating a projection edge of a ground heap bottom layer;
the layered projection line acquisition module 02 is used for judging the type of the ground heap scene according to the projection edge and calculating to obtain layered projection lines for different types of matching different methods;
and a ground heap area calculating module 03, configured to calculate a ground heap area according to a longest projection line of the layered projection lines.
The commodity ground pile area calculating system based on the target detection provided by the embodiment of the invention realizes the quick and accurate calculation of the commodity ground pile area and provides a reliable basis for the analysis of indexes such as whether the sale main pushing product occupies a gold position.
In a specific embodiment, the layered projection line module 02 is further configured to:
judging whether the effective edges of the projection edges are 1; if yes, the scene is shot positively; if not, calculating the included angle of the projection edge;
judging whether the included angle meets a preset condition or not; if yes, the scene is shot positively; if not, the scene is shot laterally.
In a third aspect:
an embodiment of the present invention further provides a terminal device, including:
one or more processors;
a memory coupled to the processor for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a commodity heap area calculation method based on object detection as described above.
The processor is used for controlling the overall operation of the terminal device so as to complete all or part of the steps of the commodity pile area calculation method based on the target detection. The memory is used to store various types of data to support operation at the terminal device, and these data may include, for example, instructions for any application or method operating on the terminal device, as well as application-related data. The Memory may be implemented by any type of volatile or non-volatile Memory device or combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk, or optical disk.
The terminal Device may be implemented by one or more Application Specific 1 integrated circuits (AS 1C), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a controller, a microcontroller, a microprocessor, or other electronic components, and is configured to perform the method for calculating the area of the commodity pile based on the target detection according to any of the embodiments, and achieve the technical effects consistent with the above method.
An embodiment of the present invention further provides a computer readable storage medium including program instructions, which when executed by a processor implement the steps of the commodity pile area calculation method based on object detection as described in any one of the above embodiments. For example, the computer readable storage medium may be the above memory including program instructions, which are executable by the processor of the terminal device to perform the commodity pile area calculation method based on object detection according to any one of the above embodiments, and achieve the technical effects consistent with the above method.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
Claims (8)
1. A commodity pile area calculation method based on target detection is characterized by comprising the following steps:
extracting a ground heap scene of the picture identification result, and calculating a projection edge of a ground heap bottom layer;
judging the type of the ground heap scene according to the projection edge, and matching different methods for different types to calculate to obtain a layered projection line; the judging the type of the ground heap scene according to the projection edge comprises:
judging whether the effective edges of the projection edges are 1; if yes, the scene is shot positively; if not, calculating the included angle of the projection edge;
judging whether the included angle meets a preset condition or not; if yes, the scene is shot positively; if not, the scene is shot laterally;
and calculating the ground pile area according to the longest projection line in the layered projection lines.
2. The method of claim 1, wherein the calculating layered projection lines for different types of matching different methods comprises:
when the type is a side shooting scene, calculating the saturation of the projection edge;
if the saturation is smaller than a first preset threshold, fitting the current projection edge;
and calculating the length of the projection edge according to the actual size of the product on the projection edge after fitting, and obtaining all layered projection lines after iterative calculation.
3. The method of claim 2, wherein the calculating of the commodity pile area based on the object detection for different types of matching different methods to obtain the layered projection line further comprises:
when the type is a positive shooting scene, layering is carried out in the direction vertical to the ground;
judging whether continuous products exist in each layer; if so, fitting the projection edge of the product;
if not, connecting the centers of the products which are farthest away in the same layer, and taking line segments obtained by connecting the lines as layered projection lines.
4. The commodity pile area calculation method based on target detection according to claim 2 or 3, wherein the fitting is performed by using a least square method.
5. The commodity ground heap area calculation method based on object detection as claimed in claim 1, wherein before the ground heap scene for extracting the picture recognition result, the method comprises:
identifying a tested commodity based on a deep learning target detection method, and carrying out scene segmentation and layering processing on the tested commodity;
and calculating the center coordinates of the layered tested commodity by using a matrix operation method, and matching the tested commodity with the corresponding scene and the layer according to the calculation result.
6. A commodity pile area calculation system based on object detection, comprising:
the identification module is used for extracting a ground heap scene of the picture identification result and calculating a projection edge of a ground heap bottom layer;
the layered projection line acquisition module is used for judging the type of the ground heap scene according to the projection edge and calculating to obtain layered projection lines for different types of matching different methods; the system is also used for judging whether the effective edges of the projection edges are 1; if yes, the scene is shot positively; if not, calculating the included angle of the projection edge; judging whether the included angle meets a preset condition or not; if yes, the scene is shot positively; if not, the scene is shot laterally;
and the ground heap area calculation module is used for calculating the ground heap area according to the longest projection line in the layered projection lines.
7. A terminal device, comprising:
one or more processors;
a memory coupled to the processor for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the method of commodity heap area calculation based on object detection of any one of claims 1 to 5.
8. A computer-readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the commodity pile area calculation method based on object detection according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110568226.1A CN113034574B (en) | 2021-05-25 | 2021-05-25 | Commodity ground heap area calculation method and system based on target detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110568226.1A CN113034574B (en) | 2021-05-25 | 2021-05-25 | Commodity ground heap area calculation method and system based on target detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113034574A CN113034574A (en) | 2021-06-25 |
| CN113034574B true CN113034574B (en) | 2021-09-14 |
Family
ID=76455725
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110568226.1A Active CN113034574B (en) | 2021-05-25 | 2021-05-25 | Commodity ground heap area calculation method and system based on target detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113034574B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114526709A (en) * | 2022-02-21 | 2022-05-24 | 中国科学技术大学先进技术研究院 | Area measurement method and device based on unmanned aerial vehicle and storage medium |
| CN115272446B (en) * | 2022-09-27 | 2023-01-24 | 南京掌控网络科技有限公司 | Method and system for calculating head-stacking occupied area |
| CN116311219B (en) * | 2023-01-29 | 2024-02-09 | 广州市玄武无线科技股份有限公司 | Ground pile article occupied area calculation method and device based on perspective transformation |
| CN116721338A (en) * | 2023-03-13 | 2023-09-08 | 广州市玄武无线科技股份有限公司 | Land pile product occupied area calculation method and device based on target detection |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW201043929A (en) * | 2009-06-09 | 2010-12-16 | Nat Univ Chung Hsing | System for estimating and monitoring the volume of object |
| CN112584116A (en) * | 2021-02-24 | 2021-03-30 | 深圳市火乐科技发展有限公司 | Projection correction method, projection correction device, storage medium and electronic equipment |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3757755B2 (en) * | 2000-05-22 | 2006-03-22 | スズキ株式会社 | Defect detection method and defect detection device for protrusions of articles formed with protrusions having the same shape at a predetermined pitch along an arc |
| CN101477685B (en) * | 2009-01-15 | 2011-06-01 | 西安交通大学 | Sub-pixel level image detection process with field part depth machining quality |
| US9220180B2 (en) * | 2010-12-09 | 2015-12-22 | Richard Anthony Dunn, JR. | System and methods for scalable parallel data processing and process control |
| CN109784172A (en) * | 2018-12-14 | 2019-05-21 | 上海扩博智能技术有限公司 | Ground heap commodity occupied area evaluation method, system, equipment and medium in market |
| CN112070769B (en) * | 2020-09-18 | 2022-06-03 | 福州大学 | Layered point cloud segmentation method based on DBSCAN |
| CN112364568A (en) * | 2020-11-19 | 2021-02-12 | 中国石油大学(华东) | Oven food volume and mass estimation algorithm based on computer vision |
-
2021
- 2021-05-25 CN CN202110568226.1A patent/CN113034574B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW201043929A (en) * | 2009-06-09 | 2010-12-16 | Nat Univ Chung Hsing | System for estimating and monitoring the volume of object |
| CN112584116A (en) * | 2021-02-24 | 2021-03-30 | 深圳市火乐科技发展有限公司 | Projection correction method, projection correction device, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113034574A (en) | 2021-06-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113034574B (en) | Commodity ground heap area calculation method and system based on target detection | |
| US11227405B2 (en) | Determining positions and orientations of objects | |
| US10783656B2 (en) | System and method of determining a location for placement of a package | |
| US7027651B2 (en) | Geometric hashing method for model-based recognition of an object | |
| US10217083B2 (en) | Apparatus, method, and program for managing articles | |
| CN111161346B (en) | Method and device for layering commodities in goods shelves and electronic equipment | |
| US10586321B2 (en) | Automatic detection, counting, and measurement of lumber boards using a handheld device | |
| CN108960238B (en) | Multi-camera-based commodity identification processing method and device | |
| CN111310706B (en) | Commodity price tag identification method and device, electronic equipment and storage medium | |
| CN111353540B (en) | Commodity category identification method and device, electronic equipment and storage medium | |
| CN115082394A (en) | Plug-in defect visual detection and identification method, readable storage medium and device | |
| CN112509011B (en) | Static commodity statistical method, terminal equipment and storage medium thereof | |
| US11216905B2 (en) | Automatic detection, counting, and measurement of lumber boards using a handheld device | |
| CN110570471A (en) | cubic object volume measurement method based on depth image | |
| CN111160450A (en) | Fruit and vegetable weighing method based on neural network, storage medium and device | |
| US9846949B2 (en) | Determine the shape of a representation of an object | |
| CN110728246A (en) | Cubic object identification method based on depth image | |
| CN110751640A (en) | Quadrangle detection method of depth image based on angular point pairing | |
| CN110766646A (en) | Display rack shielding detection method and device and storage medium | |
| CN110689568A (en) | Accurate calculation method for cubic object volume based on depth image | |
| CN114454168A (en) | Dynamic vision mechanical arm grabbing method and system and electronic equipment | |
| CN114140676A (en) | Shelf layer determining method, device and medium based on image recognition | |
| CN116311219B (en) | Ground pile article occupied area calculation method and device based on perspective transformation | |
| CN115546202B (en) | Tray detection and positioning method for unmanned forklift | |
| JP6746123B2 (en) | Image recognition system |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP02 | Change in the address of a patent holder | ||
| CP02 | Change in the address of a patent holder |
Address after: 510000 room 23bd, No. 109, TIYU West Road, Tianhe District, Guangzhou City, Guangdong Province Patentee after: GUANGZHOU XUANWU WIRELESS TECHNOLOGY Co.,Ltd. Address before: 32B, no.103b, TianLiHe Road, Guangzhou, 510000 Patentee before: GUANGZHOU XUANWU WIRELESS TECHNOLOGY Co.,Ltd. |