CN117522269A - Large-view-field disk point calculation power saving method based on attention guide mechanism - Google Patents
Large-view-field disk point calculation power saving method based on attention guide mechanism Download PDFInfo
- Publication number
- CN117522269A CN117522269A CN202311523794.5A CN202311523794A CN117522269A CN 117522269 A CN117522269 A CN 117522269A CN 202311523794 A CN202311523794 A CN 202311523794A CN 117522269 A CN117522269 A CN 117522269A
- Authority
- CN
- China
- Prior art keywords
- target object
- storage area
- inventory
- area
- goods
- 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
- 238000000034 method Methods 0.000 title claims abstract description 47
- 230000007246 mechanism Effects 0.000 title claims abstract description 23
- 238000004364 calculation method Methods 0.000 title claims abstract description 20
- 238000003860 storage Methods 0.000 claims abstract description 74
- 238000013507 mapping Methods 0.000 claims abstract description 11
- 238000012544 monitoring process Methods 0.000 claims abstract description 8
- 238000004590 computer program Methods 0.000 claims description 10
- 239000011159 matrix material Substances 0.000 claims description 6
- 230000006735 deficit Effects 0.000 claims 1
- 230000008569 process Effects 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 8
- 239000000463 material Substances 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000000007 visual effect Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000007726 management method Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000013068 supply chain management Methods 0.000 description 1
- 238000010408 sweeping Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- 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
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Databases & Information Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Accounting & Taxation (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Quality & Reliability (AREA)
- Medical Informatics (AREA)
- Operations Research (AREA)
- Mathematical Physics (AREA)
- General Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Marketing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
Abstract
The invention discloses a large-view-field disk point calculation power saving method based on an attention guide mechanism, which comprises the steps that a global camera and an object identification camera are arranged in a warehouse, the global camera is used for monitoring and collecting global images in the warehouse, and the object identification camera is used for collecting goods images in a storage area of the warehouse; identifying a target object in the global image and acquiring position information; based on the relation mapping table of the acquisition area and the storage area, triggering an inventory event of the corresponding storage area when the target object leaves the acquisition area; counting cargos in the storage area based on the acquired cargo images to acquire the information of the acquired cargos; in the process, only the target object leaves the storage area to trigger the inventory system to carry out local judgment on the corresponding storage area, and the inventory system is in an idle state at other moments, so that the repeated ineffective inventory of the inventory system is avoided, the calculation force of the control system is greatly saved, and the inventory efficiency of goods is further improved.
Description
Technical Field
The invention discloses a large-view-field inventory calculation force saving method based on an attention guide mechanism, which can be applied to the field of visual inventory of warehouse goods.
Background
Along with the development of information technology, various warehouse transportation management systems and automation equipment facilities are integrated into logistics supply chain management, so that warehouse logistics enterprises enter an information age, and the information system can be built to solve the information flow problem of the warehouse logistics enterprises. In the past, when checking the storage information, the storage position of a container, the weight of the container and the number of goods are checked by manual checking, and the checked information is counted on a table for a customer to check, but because a great deal of manpower is consumed in the checking process, the automatic and intelligent checking of the goods is a trend;
a method for realizing automatic inventory of warehouse and store goods according to the present chinese patent CN107506968A, comprising: the goods enter a warehouse to be delivered to a warehouse-in and boxing assembly line, firstly, a container RFID label is scanned, and the system automatically binds the RFID label information of the container with the goods in the container; the goods which are delivered out of the warehouse arrive at a sales store through logistics distribution, an RFID reader-writer is arranged at the sales store entrance, the RFID tag information of a container is read at the store entrance, the warehouse management system automatically performs verification and check with a to-be-checked bill, if the verification is consistent, the warehouse reduces the inventory, and the store increases the inventory; meanwhile, the batch of commodities are put on shelves in a store and are simultaneously unbound with the container; automatic inventory is achieved at warehouses and sales shops through handheld RFID terminals. The method for realizing automatic inventory of commodities in warehouses and shops has the advantages of high accuracy and high efficiency, can shorten the time for warehousing and delivering commodities, simultaneously reduces the labor cost and creates better economic benefit;
in the prior art, a plurality of intelligent inventory systems are presented, such as bar code technology, visual inventory technology, RFID technology and intelligent positioning technology, wherein the visual inventory technology is a method for realizing inventory and management by utilizing computer vision and image processing technology, and has the characteristics of rapidness, accuracy, wide application range and the like. The application of bar codes, RFID and intelligent locators is different from the application of the technology Jing Huiyou, and bar codes, RFID or intelligent locators need to be attached to each item, and these bar codes are often lost during use. When warehouse area is great, under the more circumstances of goods shelves, in order to realize quick lending and returning and real-time check business, vision check technique can be more advantageous, need not any automation equipment and go to remove the sign indicating number operation of sweeping, and the required equipment of vision check technique is mainly static camera of installation and the power calculation server that is used for visual identification. However, the visual inventory technique has the disadvantage that under the condition of not saving calculation force, for example, 0.1s is needed for inventory one shelf and 5s is needed for inventory 50 shelves, so that the service requirement of all materials for real-time inventory under the scene of material acquisition and return of a warehouse cannot be met.
Disclosure of Invention
The invention provides a large-view-field disk counting power saving method based on an attention guide mechanism, which solves the problem that in the prior art, the whole warehouse is too low in counting efficiency due to large warehouse area and large storage area and the problem of insufficient bandwidth and calculation power of a calculation power server.
In order to solve the problems, the invention adopts the following technical scheme:
the invention provides a large-view-field disk point calculation power saving method based on an attention guide mechanism, which comprises the following steps of:
s1, arranging a global camera and an article identification camera in a warehouse, wherein the global camera is used for monitoring and collecting global images in the warehouse, and the article identification camera is used for collecting cargo images in a storage area of the warehouse;
s2, identifying a moving target object in the global image and acquiring position information;
s3, based on a relation mapping table of the acquisition area and the storage area, triggering an inventory event of the corresponding storage area when the target object leaves the acquisition area;
s4, checking the cargoes in the storage area based on the acquired cargoes images to acquire the information of the acquired cargoes.
Preferably, the warehouse is divided into a storage area and a collection area, and the storage area is a goods shelf for storing articles; the collection area is a standing area when a receiving person receives goods from the storage area.
Preferably, the method for identifying the target object in the global image and acquiring the position information comprises the following steps:
marking an acquisition area in the global image;
acquiring a global image of a global camera in real time, inputting the global image into a yolov5 identification model, and outputting a target object identification frame A by the yolov5 identification model, wherein the target object identification frame A is a human body identification frame or a transport vehicle identification frame;
and judging whether the target object identification frame A is overlapped with the acquisition region, and judging that the target object is positioned in front of the storage region when the target object identification frame A is overlapped with the acquisition region.
Preferably, the method for judging that the target object identification frame A overlaps with the acquisition area comprises the following steps:
converting the global image containing the target object identification frame A and the acquisition area into a mask binarization map M1 and a mask binarization map M2 with the same size respectively;
setting the pixel value in the target object identification frame A in the mask binarization map M1 to be 1, and setting the pixel value outside the target object identification frame A in the mask binarization map M1 to be 0; setting the pixel value in the acquisition area in the mask binarization map M2 as 1, and setting the pixel value outside the acquisition area in the mask binarization map M2 as 0;
and adding the mask binarization map M1 and the mask binarization map M2 into a matrix, setting a pixel with a value of 2 in the matrix as an intersection area, calculating the intersection ratio of the acquisition area and the target object recognition frame A based on the intersection area, and outputting a judging result that the target object recognition frame A overlaps with the acquisition area when the intersection ratio is larger than a set threshold value Q.
Preferably, the method for judging that the target object leaves the acquisition area comprises the following steps:
when the target object enters the acquisition area, recording a time stamp of the target object in the acquisition area; and if the difference value between the current system time and the last time stamp of the target object in the acquisition area is larger than the preset value T1 and smaller than the preset value T2, judging that the target object leaves the acquisition area.
Preferably, the method for checking the goods in the storage area to obtain the information of the received goods includes:
the goods recognition camera acquires a goods image of the storage area and marks the goods image as an image B:
inputting the image B into a goods identification model to obtain the quantity Tk of goods on a storage area, marking the quantity Tk as the current stock, checking when the target object does not enter the warehouse in the same way, and marking the stock as Tk -1 :
The number Tk of goods recorded by the k-1 th inventory -1 And subtracting the cargo quantity Tk recorded by the kth inventory to calculate the quantity of the received cargoes.
The invention also provides a large-view-field disk point computing power saving system based on the attention guiding mechanism, which is a system used by the large-view-field disk point computing power saving method based on the attention guiding mechanism, and specifically comprises the following steps:
the acquisition module is used for controlling the global camera to monitor and acquire global images in the warehouse and controlling the article identification camera to acquire the images of the articles in the storage area of the warehouse;
the identification module is used for identifying and positioning the target object in the global image to obtain position information;
the triggering control module is used for determining an inventory system of the corresponding storage area based on a preset mapping table and position information and triggering the inventory system to inventory;
and the inventory control module is used for controlling the inventory system to inventory the goods in the storage area to acquire the information of the acquired goods.
Preferably, the global camera number is less than the item identification cameras.
The invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the steps of a large field disk calculation power saving method based on an attention guiding mechanism.
Compared with the prior art, the invention has the following beneficial effects:
(1) According to the invention, the global camera and the object identification camera are arranged in the warehouse, the global camera is used for monitoring and collecting global images in the warehouse, and the object identification camera is used for collecting goods images in a storage area of the warehouse; identifying a target object in the global image and acquiring position information; based on the relation mapping table of the acquisition area and the storage area, triggering an inventory event of the corresponding storage area when the target object leaves the acquisition area; and checking the cargos in the storage area based on the acquired cargo images to acquire the information of the acquired cargos. In the process, only the target object leaves the storage area to trigger the inventory system to carry out local judgment on the corresponding storage area, and the inventory system is in an idle state at other moments, so that the repeated ineffective inventory of the inventory system is avoided, the calculation force of the control system is greatly saved, and the inventory efficiency of goods is further improved.
(2) The coverage area of the global camera is wide, one global camera can completely cover a walkway with indoor distance less than 30 meters, and only a small amount of global cameras can cover the whole warehouse station area.
(3) The expandability is good, and a new global camera is not required to be added as long as a storage area is added in the coverage range of the existing camera.
Drawings
FIG. 1 is a flow chart of a large field disk point calculation power saving method based on an attention guiding mechanism according to embodiment 1 of the present invention;
FIG. 2 is a schematic diagram of a first state provided in embodiment 1 of the present invention;
FIG. 3 is a schematic diagram of a second state provided in embodiment 1 of the present invention;
Detailed Description
The following description of the embodiments of the present invention 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 invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
As shown in fig. 1 to 3, an embodiment of the present invention provides a large field disk calculation force saving method based on an attention guiding mechanism, the method includes the following steps:
s1, arranging a global camera and an article identification camera in a warehouse, wherein the global camera is used for monitoring and collecting global images in the warehouse, and the article identification camera is used for collecting cargo images in a storage area of the warehouse.
Specifically, the global camera is arranged at the top of a warehouse or on a wall surface and is used for monitoring a walkway of the whole warehouse station and monitoring the position information of a target object in the warehouse station in real time; the object identification camera is a camera which is used for storing all coverage of materials for a storage area and is used for checking the materials. Meanwhile, according to the coverage condition of the global camera in the warehouse, the warehouse is divided into a storage area and a collection area; the storage area is a goods shelf for storing articles; the collection area is a standing area when a receiving person receives goods from the storage area; each storage area corresponds to an acquisition area. The global camera is arranged for providing the personal information of the target object, and the corresponding storage area is searched according to the acquisition area where the target object is located, so that the material inventory of the corresponding storage area is triggered.
S2, identifying a moving target object in the global image and acquiring position information;
specifically, the method for identifying the target object in the global image and acquiring the position information comprises the following steps:
the method for calibrating the acquisition region in the global image comprises the following steps: selecting 4 coordinate points before storing an area on the global image, wherein an area surrounded by the 4 coordinate points is an acquisition area;
acquiring a global image of a global camera in real time, inputting the global image into a yolov5 identification model, and outputting a target object identification frame A by the yolov5 identification model, wherein the target object identification frame A is a human body identification frame or a transport vehicle identification frame;
and judging whether the target object identification frame A is overlapped with the acquisition region, and judging that the target object is positioned in front of the storage region when the target object identification frame A is overlapped with the acquisition region.
Preferably, the method for judging that the target object identification frame A overlaps with the acquisition area comprises the following steps:
converting the global image containing the target object identification frame A and the acquisition area into a mask binarization map M1 and a mask binarization map M2 with the same size respectively;
setting the pixel value in the target object identification frame A in the mask binarization map M1 to be 1, and setting the pixel value outside the target object identification frame A in the mask binarization map M1 to be 0; setting the pixel value in the acquisition area in the mask binarization map M2 as 1, and setting the pixel value outside the acquisition area in the mask binarization map M2 as 0;
and adding the mask binarization map M1 and the mask binarization map M2 into a matrix, setting a pixel with a value of 2 in the matrix as an intersection area, calculating the intersection ratio of the acquisition area and the target object recognition frame A based on the intersection area, and outputting a judging result that the target object recognition frame A overlaps with the acquisition area when the intersection ratio is larger than a set threshold value Q.
S3, based on a relation mapping table of the acquisition area and the storage area, triggering an inventory event of the corresponding storage area when the target object leaves the acquisition area;
the relation mapping table of the acquisition area and the storage area is a preset table, and the relation mapping table is a relation table of the acquisition area and the storage area, and the corresponding storage area can be inquired through the acquisition area based on the relation table. The method for judging that the target object leaves the acquisition area comprises the following steps:
when the target object enters the acquisition area, recording a time stamp of the target object in the acquisition area; and if the difference value between the current system time and the last time stamp of the target object in the acquisition area is larger than the preset value T1 and smaller than the preset value T2, judging that the target object leaves the acquisition area.
S4, checking the cargoes in the storage area based on the acquired cargoes images to acquire the information of the acquired cargoes.
Specifically, the method for checking the goods in the storage area to acquire the information of the received goods comprises the following steps:
the goods recognition camera acquires a goods image of the storage area and marks the goods image as an image B:
inputting the image B into the goods identification model to obtain the quantity T of goods on the storage area k ,T k Recording as current stock, checking when the target object does not enter the warehouse in the same way, and recording as T k-1 :
The number T of goods recorded by k-1 time of inventory k-1 Subtracting the number T of cargoes recorded by the kth inventory k Calculating to obtain the quantity of the received goods;
taking T1 as 1s and T2 as 2 seconds as an example, when the time difference is less than 1s, the target object can be considered to be still in the acquisition area; if the time difference is greater than 2s, the target object is considered to be already away from the acquisition area; when the time difference is greater than 1s and less than 2 seconds, the target object is considered to be just separated, and the optimal time for triggering inventory is the time.
According to the invention, the global camera and the object identification camera are arranged in the warehouse, the global camera is used for monitoring and collecting global images in the warehouse, and the object identification camera is used for collecting goods images in a storage area of the warehouse; identifying a target object in the global image and acquiring position information; based on the relation mapping table of the acquisition area and the storage area, triggering an inventory event of the corresponding storage area when the target object leaves the acquisition area; and checking the cargos in the storage area based on the acquired cargo images to acquire the information of the acquired cargos. In the process, only the target object leaves the storage area to trigger the inventory system to carry out local judgment on the corresponding storage area, and the inventory system is in an idle state at other moments, so that the repeated ineffective inventory of the inventory system is avoided, the calculation force of the control system is greatly saved, and the inventory efficiency of goods is further improved.
Example 2
The invention also provides a large-view-field disk point calculation power saving system based on the attention guiding mechanism, which is a system used in the embodiment 1, and specifically comprises:
the acquisition module is used for controlling the global camera to monitor and acquire global images in the warehouse and controlling the article identification camera to acquire the images of the articles in the storage area of the warehouse;
the identification module is used for identifying and positioning the target object in the global image to obtain position information;
the triggering control module is used for determining an inventory system of the corresponding storage area based on a preset mapping table and position information and triggering the inventory system to inventory;
and the inventory control module is used for controlling the inventory system to inventory the goods in the storage area to acquire the information of the acquired goods.
The global camera number is less than the item identification cameras.
Example 3
An embodiment of the present invention provides an electronic device including a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor executing the steps of a large field-of-view disk computing power saving method based on an attention-directing mechanism in embodiment 1.
It should be noted that, unless explicitly stated herein, the steps are not strictly limited to the order of execution, and the steps may be executed in other orders. Moreover, at least a portion of the steps may include a plurality of steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor does the order in which the steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of the steps or stages in other steps or other steps.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks. These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The foregoing is merely a preferred embodiment of the present invention, and it should be noted that modifications and variations could be made by those skilled in the art without departing from the technical principles of the present invention, and such modifications and variations should also be regarded as being within the scope of the invention.
Claims (9)
1. A large field-of-view disk calculation power saving method based on an attention guiding mechanism, characterized in that the method comprises the following steps:
s1, arranging a global camera and an article identification camera in a warehouse, wherein the global camera is used for monitoring and collecting global images in the warehouse, and the article identification camera is used for collecting cargo images in a storage area of the warehouse;
s2, identifying a moving target object in the global image and acquiring position information;
s3, based on a relation mapping table of the acquisition area and the storage area, triggering an inventory event of the corresponding storage area when the target object leaves the acquisition area;
s4, checking the cargoes in the storage area based on the acquired cargoes images to acquire the information of the acquired cargoes.
2. The large field dish computing power saving method based on the attention guiding mechanism as recited in claim 1, wherein the warehouse is divided into a storage area and an acquisition area, and the storage area is a shelf for storing articles; the collection area is a standing area when a receiving person receives goods from the storage area.
3. The method for saving large-field disk computing power based on an attention guiding mechanism as recited in claim 1, wherein the method for identifying moving target objects in a global image and acquiring position information comprises:
marking an acquisition area in the global image;
acquiring a global image of a global camera in real time, inputting the global image into a yolov5 identification model, and outputting a target object identification frame A by the yolov5 identification model, wherein the target object identification frame A is a human body identification frame or a transport vehicle identification frame;
and judging whether the target object identification frame A is overlapped with the acquisition region, and judging that the target object is positioned in front of the storage region when the target object identification frame A is overlapped with the acquisition region.
4. A large field disk calculation power saving method based on an attention guiding mechanism as claimed in claim 3, wherein the method for judging that the target object recognition frame a overlaps with the acquisition area comprises:
converting the global image containing the target object identification frame A and the acquisition area into a mask binarization map M1 and a mask binarization map M2 with the same size respectively;
setting the pixel value in the target object identification frame A in the mask binarization map M1 to be 1, and setting the pixel value outside the target object identification frame A in the mask binarization map M1 to be 0; setting the pixel value in the acquisition area in the mask binarization map M2 as 1, and setting the pixel value outside the acquisition area in the mask binarization map M2 as 0;
and adding the mask binarization map M1 and the mask binarization map M2 into a matrix, setting a pixel with a value of 2 in the matrix as an intersection area, calculating the intersection ratio of the acquisition area and the target object recognition frame A based on the intersection area, and outputting a judging result that the target object recognition frame A overlaps with the acquisition area when the intersection ratio is larger than a set threshold value Q.
5. The method for saving large field of view disk computing power based on an attention guide mechanism as recited in claim 1, wherein the method for determining that the target object leaves the acquisition region comprises:
when the target object enters the acquisition area, recording a time stamp of the target object in the acquisition area; and if the difference value between the current system time and the last time stamp of the target object in the acquisition area is larger than the preset value T1 and smaller than the preset value T2, judging that the target object leaves the acquisition area.
6. The method for saving large-field inventory computing power based on an attention guidance mechanism according to claim 1, wherein the method for inventory of the goods in the storage area to obtain the information of the received goods comprises the following steps:
the goods recognition camera acquires a goods image of the storage area and marks the goods image as an image B:
inputting the image B into the goods identification model to obtain the quantity T of goods on the storage area k ,T k Recording as current stock, checking when the target object does not enter the warehouse in the same way, and recording as T k-1 :
The number T of goods recorded by k-1 time of inventory k-1 Subtracting the number T of cargoes recorded by the kth inventory k And calculating to obtain the quantity of the received goods.
7. A large field disk calculation force saving system based on an attention guiding mechanism, characterized in that the system used for a large field disk calculation force saving method based on an attention guiding mechanism as set forth in any one of claims 1 to 6 specifically comprises:
the acquisition module is used for controlling the global camera to monitor and acquire global images in the warehouse and controlling the article identification camera to acquire the images of the articles in the storage area of the warehouse;
the identification module is used for identifying and positioning the target object in the global image to obtain position information;
the triggering control module is used for determining an inventory system of the corresponding storage area based on a preset mapping table and position information and triggering the inventory system to inventory;
and the inventory control module is used for controlling the inventory system to inventory the goods in the storage area to acquire the information of the acquired goods.
8. The large field of view disk spot computing power saving system based on an attention deficit mechanism of claim 7, wherein the global camera number is less than the item identification cameras.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor performing the steps of a large field-of-view disk computing power saving method based on an attention-directing mechanism as claimed in any one of claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311523794.5A CN117522269A (en) | 2023-11-16 | 2023-11-16 | Large-view-field disk point calculation power saving method based on attention guide mechanism |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311523794.5A CN117522269A (en) | 2023-11-16 | 2023-11-16 | Large-view-field disk point calculation power saving method based on attention guide mechanism |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117522269A true CN117522269A (en) | 2024-02-06 |
Family
ID=89743315
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311523794.5A Pending CN117522269A (en) | 2023-11-16 | 2023-11-16 | Large-view-field disk point calculation power saving method based on attention guide mechanism |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117522269A (en) |
-
2023
- 2023-11-16 CN CN202311523794.5A patent/CN117522269A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110414638B (en) | Three-dimensional warehouse management system and management method based on RFID | |
CN108846621B (en) | Inventory management system based on strategy module | |
US10607182B2 (en) | Method for tracking stock level within a store | |
CN109117824B (en) | Commodity management method and device, electronic equipment and storage medium | |
US20180285813A1 (en) | Concepts for locating assets utilizing light detection and ranging | |
CN112085446A (en) | Multi-module unmanned cabin and intelligent management system | |
CN113859847B (en) | Storage checking method and storage system | |
CN106203928A (en) | A kind of warehouse management system based on RFID technique | |
US20180293535A1 (en) | Rfid system and method for tracking assets | |
WO2019075911A1 (en) | Merchandise sorting system and sorting method | |
US20150066550A1 (en) | Flow line data analysis device, system, non-transitory computer readable medium and method | |
CN213024481U (en) | Multi-module unmanned cabin and intelligent management system | |
CN108629318B (en) | Shelf display identification method, device and system based on image identification technology | |
CN109118150B (en) | Commodity volume estimation method and device, computer equipment and storage medium | |
US20180282063A1 (en) | Movement path management system, movement path management method, and non-transitory computer-readable medium | |
CN112824990A (en) | Cargo information detection method and system, robot and processing terminal | |
RU2730112C1 (en) | System and method of identifying objects in composite object | |
Zadorozhnyi et al. | Innovation management and automated accounting in the chaotic storage logistics | |
CN115439070A (en) | Method for realizing self-service material receiving based on storage digitization | |
CN114444997A (en) | Intelligent warehousing system based on supply chain management | |
US20210133674A1 (en) | Picking work assistance device and computer-readable recording medium having stored thereon picking work assistance program | |
CN115376242B (en) | Automatic goods distribution method for intelligent storage rack of vending machine | |
CN115796732B (en) | Regional logistics delivery and entry distribution management method based on e-commerce platform commodity | |
CN117522269A (en) | Large-view-field disk point calculation power saving method based on attention guide mechanism | |
CN111145224A (en) | Human body tracking 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 |