CN114708631A - Material management method and device, electronic equipment and computer readable storage medium - Google Patents
Material management method and device, electronic equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN114708631A CN114708631A CN202210307861.9A CN202210307861A CN114708631A CN 114708631 A CN114708631 A CN 114708631A CN 202210307861 A CN202210307861 A CN 202210307861A CN 114708631 A CN114708631 A CN 114708631A
- Authority
- CN
- China
- Prior art keywords
- determining
- target
- target object
- image
- monitoring 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
Images
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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30241—Trajectory
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Multimedia (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Image Analysis (AREA)
Abstract
The application discloses a material management method, a material management device, electronic equipment and a computer-readable storage medium. The method comprises the following steps: acquiring material distribution information of a target area and a monitoring image of the target area; determining a target object in the monitoring image; and determining the material use condition of the target area according to the target object and the material distribution information. Above-mentioned scheme can determine the goods and materials in service behavior, and then is convenient for carry out reasonable management to the goods and materials, promotes the managerial efficiency of goods and materials.
Description
Technical Field
The present application relates to the field of material management technologies, and in particular, to a material management method, an apparatus, an electronic device, and a computer-readable storage medium.
Background
For a conglomerated enterprise, there are typically many office areas. Corresponding materials are usually delivered in corresponding areas for the convenience of the employees of the enterprise. For example, a printer is provided in order to provide printing services. An office supply reception area is arranged to provide self-service reception of office supplies.
The defects are that consumables in the materials, such as paper in a printer, are usually manually put in, and if the consumables are not put in time, the consumables can not be used.
Disclosure of Invention
The application at least provides a material management method, a material management device, electronic equipment and a computer readable storage medium.
The application provides a material management method in a first aspect, and the method comprises the following steps: acquiring material distribution information of a target area and a monitoring image of the target area; determining a target object in the monitoring image; and determining the material use condition of the target area according to the target object and the material distribution information.
Therefore, the target object in the monitoring image is determined by utilizing the monitoring image, and then the material use condition of the target area is determined according to the target object and the material distribution information, so that the material use condition can be determined, the material is conveniently and reasonably managed, and the management efficiency of the material is improved.
Wherein, confirm the target object in the monitoring image, including: and identifying the monitoring image by using a target identification network, and determining a target object in the monitoring image.
Consequently, utilize image recognition technology to carry out the target object discernment, can be convenient for discern the target object of goods and materials zone range within, and then determine the goods and materials in service behavior, and then be convenient for carry out reasonable management to goods and materials, promote the managerial efficiency of goods and materials.
Wherein, according to target object and material distribution information, confirm the material use condition of the target area, including: determining a plurality of first position information of a target object in a monitoring image; determining the track of the target object according to a plurality of first position information of the target object in the monitoring image; and determining the material use condition of the target area according to the track and the material distribution information.
Therefore, a plurality of first position information of the target object in the monitoring image is determined by utilizing an image recognition technology; according to the target object at a plurality of first position information of monitoring image, and then determine each target object's orbit, according to orbit and material distribution information, confirm the goods and materials in target area behavior, can determine the orbit of target object according to position information, and then according to orbit and goods and materials distribution information, determine the goods and materials behavior, and then be convenient for carry out reasonable management to the goods and materials, promote the managerial efficiency of goods and materials.
Wherein the target object comprises a person object; determining a target object in a monitored image, comprising: identifying the monitored image by using a face identification network, and determining a face image in the monitored image; determining a plurality of first position information of the target object in the monitored image according to the target object in the monitored image, wherein the method comprises the following steps: clustering face images in multiple frame monitoring images to determine multiple face images of at least one person object; and determining a plurality of pieces of first position information of the at least one person object in the monitoring image according to a plurality of face images of the at least one person object.
Therefore, utilize image recognition technology to carry out face identification to multiframe image, and then confirm at least one personnel object at a plurality of first positional information of surveillance image, can make statistics of the personnel object in the surveillance image, be convenient for follow-up quantity according to personnel object determines the goods and materials in service behavior, is convenient for carry out reasonable management to the goods and materials, promotes the managerial efficiency of goods and materials.
Wherein the target object comprises a person object; determining a target object in a monitored image, comprising: identifying the monitored image by using a human face and human body identification network, and determining a human face image and a human body image in the monitored image; determining a plurality of first position information of the target object in the monitoring image according to the target object in the monitoring image, wherein the method comprises the following steps: clustering the face images and the human body images in the multi-frame monitoring images respectively to determine a plurality of face images of at least one person object and a plurality of human body images of at least one person object; determining the association relation between a plurality of face images and a plurality of human body images; and determining a plurality of first position information of the at least one person object in the monitoring image according to the plurality of face images of the at least one person object, the plurality of human body images of the at least one person object and the incidence relation between the plurality of face images and the plurality of human body images.
Therefore, utilize image recognition technology to carry out face identification and human body recognition to multiframe image, and then confirm a plurality of first positional information of at least one personnel object at the surveillance image, can make statistics of the personnel object in the surveillance image, be convenient for follow-up quantity according to personnel object determines the goods and materials in service behavior, be convenient for carry out reasonable management to the goods and materials, promote the managerial efficiency of goods and materials, and furthermore, utilize the fixed unchangeable characteristics of human body characteristic, can be associated face image and human image, can improve the accuracy of discernment personnel discernment and clustering.
The method for determining the track of the target object according to the first position information of the target object in the monitoring image comprises the following steps: determining a plurality of second position information of the target object in the target space according to a plurality of first position information of the target object in the monitoring image and a predetermined mapping relation between the position information of the monitoring image and the target space describing material distribution information; and determining the track of the target object according to the second position information.
Therefore, the mapping relation is utilized to convert the first position information into the second position information, the track of the target object is determined according to the second position information, the use condition of the materials can be determined by utilizing the track, the materials are conveniently and reasonably managed, and the management efficiency of the materials is improved.
Wherein, according to track and material distribution information, confirm the material in target area and use the condition, include: and when the track of any person object is detected to be located in the range of any target material, determining that any person object uses the target material.
Therefore, the track is utilized to determine the use condition of the materials, the materials are conveniently and reasonably managed, and the management efficiency of the materials is improved.
Wherein, according to track and material distribution information, confirm the material in target area and use the condition, still include: and counting the material use condition of the target material in a specified time period.
Therefore, through the material service condition of the statistical target material in the appointed time period, the reasonable management of the material is facilitated, and the management efficiency of the material is improved.
This application second aspect provides a material management device, and this material management device includes: the acquisition module is used for acquiring material distribution information of a target area and a monitoring image of the target area; the determining module is used for determining a target object in the monitoring image; and the processing module is used for determining the material use condition of the target area according to the target object and the material distribution information.
A third aspect of the present application provides an electronic device comprising a processor and a memory coupled to the processor; the memory stores a computer program, and the processor is configured to execute the computer program to implement the material management method in the first aspect.
A fourth aspect of the present application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the material management method of the first aspect.
Above-mentioned scheme, consequently, through utilizing the surveillance image to determine target object in the surveillance image, and then according to target object and goods and materials distribution information, confirm the mode of the goods and materials in target area behavior, can determine the goods and materials behavior, and then be convenient for carry out reasonable management to the goods and materials, promote the managerial efficiency of goods and materials.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the application.
FIG. 1 is a schematic flow chart of a material management method according to a first embodiment of the present disclosure;
FIG. 2 is a schematic illustration of a material distribution diagram provided herein;
FIG. 3 is a schematic view of a surveillance image provided herein;
FIG. 4 is a schematic view of a monitoring image superimposed with material distribution information provided by the present application;
FIG. 5 is a schematic flow chart illustrating a material management method according to a second embodiment of the present disclosure;
FIG. 6 is a schematic flow chart diagram illustrating one embodiment of step 54 provided herein;
FIG. 7 is a schematic flow chart of a material management method according to a third embodiment of the present application;
FIG. 8 is a schematic flow chart diagram illustrating one embodiment of step 106 provided herein;
FIG. 9 is a schematic flow chart diagram illustrating a material management method according to a fourth embodiment of the present application;
FIG. 10 is a schematic flow chart diagram illustrating an embodiment of step 93 provided herein;
FIG. 11 is a schematic flow chart diagram illustrating another embodiment of step 93 provided herein;
FIG. 12 is a schematic flow chart diagram illustrating one embodiment of step 94 provided herein;
FIG. 13 is a schematic flow chart diagram illustrating a material management method according to a fifth embodiment of the present application;
FIG. 14 is a schematic structural diagram of an embodiment of a material management apparatus provided in the present application;
FIG. 15 is a schematic structural diagram of an embodiment of an electronic device provided herein;
FIG. 16 is a schematic structural diagram of an embodiment of a computer-readable storage medium according to the present application.
Detailed Description
The following describes in detail the embodiments of the present application with reference to the drawings attached hereto.
In the following description, for purposes of explanation and not limitation, specific details are set forth such as particular system structures, interfaces, techniques, etc. in order to provide a thorough understanding of the present application.
The term "and/or" herein is merely an associative relationship describing an associated object, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates a relationship in which the front and rear associated objects are an "or". Further, the term "plurality" herein means two or more than two. In addition, the term "at least one" herein means any combination of at least two of any one or more of a plurality, for example, including at least one of A, B, C, and may mean including any one or more elements selected from the group consisting of A, B and C.
Referring to fig. 1, fig. 1 is a schematic flow chart of a material management method according to a first embodiment of the present application. The method comprises the following steps:
step 11: and acquiring material distribution information of the target area and a monitoring image of the target area.
In some embodiments, the material distribution information may be determined in advance from the material zones. As shown in fig. 2, there are a material area a, a material area B, and a material area C. The material area A, the material area B and the material area C can be used for placing different kinds of materials and can also be used for placing the same kind of materials. Each material area can be according to actual demand, puts in corresponding quantity's material. For example, the material area A, the material area B and the material area C throw the same type of materials. However, the material usage amount corresponding to the material area A is larger than that corresponding to the material area B, and the material usage amount corresponding to the material area B is larger than that corresponding to the material area C. When the initial material is put in, corresponding amount of materials are put in different material areas according to the use amount of the materials.
In some embodiments, the target region is comprised of a plurality of sub-regions. For example, in the factory area, each building is a sub-area. Each target area corresponds to a monitoring image. Wherein, there is a material region in the monitoring image. Namely, the material area a, the material area B and the material area C shown in fig. 2 may be respectively monitored by using monitoring devices to acquire monitoring images, so as to obtain corresponding monitoring images.
In some embodiments, the material distribution information may be coordinate information of a material placement point. If so, counting the material placing points to further obtain a material distribution map of a target area, and marking the material feeding points on the material distribution map.
Step 12: and determining a target object in the monitoring image.
In some embodiments, the target object may be a material transport device, such as a forklift.
In some embodiments, the target object may be a human body.
The method for determining the target object in the monitored image may be to determine the target object in the monitored image by performing target identification on the monitored image.
In some embodiments, a monitoring image of a target area where the material area a exists is obtained, and the monitoring image is identified to determine a target object in the monitoring image, so as to obtain the monitoring image as described in fig. 3.
Step 13: and determining the material use condition of the target area according to the target object and the material distribution information.
In the monitoring image, if the target object exists, the target object has coordinate information. The target object and the material distribution information can be overlapped, and the overlapping condition is determined according to the coordinate information of the target object and the coordinate information of the material placement points in the material distribution information.
And if the coordinate information of the target object and the coordinate information of the material placing point meet the preset condition, determining that the target object and the material placing point are overlapped. Wherein the preset condition can be a preset distance between the target object and the material placing point. When the distance between the target object and the material placing point is smaller than the preset distance, the target object and the material placing point are determined to be overlapped.
In an application scenario, the overlapping situation may be determined in an image overlapping manner, which is described with reference to fig. 2, 3, and 4:
the process of fig. 3 is performed to determine the center point of the human body region detected in the monitored image, and the center point is used to replace the human body region. A monitoring image comprising a plurality of central points is obtained. This image is then superimposed with the material distribution map shown in figure 2 to obtain the image shown in figure 4.
In some embodiments, the overlap condition may represent the number of target objects within the material area. The material usage of the target area can be determined according to the number of the target objects.
In some embodiments, the area within 1 meter of the material placement point is defined as a material area, and the number of target objects in the material area can be determined.
For example, big data collection can be performed in advance, and the standard use amount of materials for each target object can be analyzed. When the number of the target objects is determined, the material use condition of the target area can be determined, the number of the residual materials can be determined according to the use condition, and material supplement reminding can be performed.
In an application scenario, the material in the target area is a printer and a corresponding amount of paper, and the material usage can be expressed as consumption of paper. First, when a sheet is thrown, the total number of sheets is determined. Then acquiring a monitoring image of the target area within preset time; determining a target human body in the monitoring image within preset time; and obtaining a human body distribution diagram in the monitoring image within the preset time. Superposing the human body distribution diagram and the material distribution diagram to determine the overlapping condition of the human body and the material area in the human body distribution diagram; and determining the material use condition of the target area according to the number of human bodies in the material area. If the standard number of sheets used per human body is 5, the number of sheets used is 500 when the number of human bodies in the material region is 100. Through the mode, the residual quantity of the paper can be estimated, and when the residual quantity of the paper is lower than the preset value, the paper is supplemented and reminded.
Therefore, the target object in the monitoring image is determined by utilizing the monitoring image, and then the material use condition of the target area is determined according to the target object and the material distribution information, so that the material use condition can be determined, the material is conveniently and reasonably managed, the management efficiency of the material is improved, the problem that the material is inconvenient to manage due to the fact that the material is dispersed in the material area can be solved, and the problem that the material cannot be found in time when the material is in shortage in the material area is solved.
Referring to fig. 5, fig. 5 is a schematic flow chart of a material management method according to a second embodiment of the present application. The method comprises the following steps:
step 51: and acquiring material distribution information of the target area and a monitoring image of the target area.
In some embodiments, there may be multiple zones of supplies in the target zone.
Step 52: and identifying the monitored image by using a target identification network, and determining a target object in the monitored image.
In some embodiments, the target recognition network may be constructed based on a convolutional neural network, a cyclic neural network, and a residual error network, and is trained by using the labeled monitoring image.
Step 53: and determining the track of the target object by using the monitoring image.
In some embodiments, a trajectory of a target object of a target area is determined using a plurality of consecutive monitored images. The target object in the target area is in a flowing state, such as entering the target area from the outside of the target area, further entering the material area, and then leaving the target area. Thus, there is a corresponding trajectory. For example, monitoring images within one hour before the current time are obtained, and the tracks of the target objects in the target area are determined by using the monitoring images to obtain a corresponding track map.
Step 54: and determining the material use condition of the target area according to the track and the material distribution information.
In some embodiments, each frame of monitoring image may be identified, and all target objects in the frame of monitoring image may be determined. Because each target object has corresponding characteristics, the corresponding target object in each frame of monitoring image can be associated according to the characteristics. So far, the coordinates of the target object on each frame of monitoring image are connected to form a track. And determining the overlapping condition of the target object and the material distribution information according to the track and the material distribution information.
It can be understood that each track point in the track has coordinate information, and the overlapping condition of the target object and the material distribution information can be determined by using the coordinate information and the material coordinate information in the material distribution information.
In other embodiments, each frame of monitoring image is identified, and all target objects in the frame of monitoring image are determined. And marking each target object according to the coordinates to obtain a track map. It is understood that, as each pair of one monitoring image is identified, the target object is further added to the track map, so as to form a track map based on the target object. And superposing the trajectory graph and the material distribution information to determine the superposition condition of the target object and the material area in the material distribution information.
Wherein, the track diagram can be displayed in the form of thermodynamic diagram. The thermodynamic diagram is an illustration of an area that is enthusiastic for visitors and the geographical area where the visitors are located in a particularly highlighted form. Thus, a trajectory thermodynamic diagram can be formed based on the movement trajectory of the target object. With the increase of target objects entering the material area in the material distribution information, a trajectory thermodynamic diagram based on the material area can be formed within a preset time. That is, the more target objects enter the material area, the more track points within the material area.
Therefore, utilize image recognition technology to carry out the target object discernment, and then determine each target object's orbit, can be convenient for discern the target object of thing material regional scope, and then determine the goods and materials in service behavior, and then be convenient for carry out reasonable management to goods and materials, promote the managerial efficiency of goods and materials.
In some embodiments, referring to fig. 6, step 54 may be the following flow:
step 541: and superposing the track and a distribution map corresponding to the material distribution information to obtain an superposed graph.
In some embodiments, when each track is obtained, the track and the distribution map corresponding to the material distribution information are superimposed until all the tracks and the corresponding distribution maps are superimposed to obtain a superimposed map.
In some embodiments, after the trajectory diagrams of all the trajectories are obtained, the trajectory diagrams and the corresponding distribution diagrams are overlapped to obtain an overlay diagram.
Step 542: and determining the overlapping condition of the target object and the material distribution information according to the overlay map.
Through the overlay, the number of target objects entering the material distribution area can be determined.
Step 543: and determining the material use condition of the target area according to the overlapping condition.
Step 543 has the same or similar technical solutions as any of the above embodiments, and is not described herein again.
Consequently, determine the overlapping condition of target object and goods and materials region in the surveillance image through utilizing the surveillance image to according to the mode of the goods and materials in overlapping condition determination target region's goods and materials in service behavior, can determine the goods and materials in service behavior, and then be convenient for carry out reasonable management to the goods and materials, promote the managerial efficiency of goods and materials, can solve because of the regional dispersion of goods and materials, the problem of the goods and materials management of being inconvenient for, and the problem that can't in time discover when solving the regional interior goods and materials shortage of goods and materials.
Referring to fig. 7, fig. 7 is a schematic flow chart of a material management method according to a third embodiment of the present application. The method comprises the following steps:
step 71: and acquiring material distribution information of the target area and a monitoring image of the target area.
Step 72: and identifying each frame of image in the monitored image by using a target identification network, and determining the human body in each frame of image.
For example, the biological feature is extracted by using human body recognition and face recognition technologies, and when the biological feature is extracted, the pixel point corresponding to the feature is determined to belong to the human body.
Step 73: and determining the track of the human body based on the human body in the continuous multi-frame images.
Corresponding human body regions exist in each frame of image, and the human body in the image flows along with time. Embodying the change of the human body area on each frame image. Therefore, the motion track of the human body can be determined according to the time continuity of the images.
Consequently, utilize image recognition technology to carry out human body identification to multiframe image, and then determine the flow orbit of each human body in the target area, can be convenient for discern the human body of thing material regional scope, and then determine the goods and materials in service behavior, and then be convenient for carry out rational management to the goods and materials, promote the managerial efficiency of goods and materials.
Step 74: and determining the overlapping condition of the target object and the material distribution information according to the track and the material distribution information.
In some embodiments, each frame of monitoring image may be identified, and all the target objects in the frame of monitoring image may be determined. Because each target object has corresponding characteristics, the corresponding target object in each frame of monitoring image can be associated according to the characteristics. So far, the coordinates of the target object on each frame of monitoring image are connected to form a track. And superposing the track and the material distribution information to determine the overlapping condition of the target object and the material area.
In other embodiments, each frame of monitoring image is identified, and all target objects in the frame of monitoring image are determined. And marking each target object according to the coordinates to obtain a track map. It is understood that as each pair of one monitoring image is identified, the target object is further added to the track map, thereby forming a track thermodynamic map based on the target object. And superposing the track thermodynamic diagram and the material distribution diagram to determine the overlapping condition of the target object and the material area.
Step 75: the formation time of each track in the overlapping case is determined.
In some embodiments, if the target human body stays in the material area when using materials, the time of staying in the material area can be determined by using each frame of monitoring image, and the forming time of each track can be further determined. For example, the time from entering the material area to leaving the material area is determined, and the time is determined as the forming time of each track in the overlapping condition.
When the material is used as a printer and paper, the longer the stay time is, the larger the number of used paper is.
In other embodiments, the supplies may also be bottled water, staplers, pens, notebooks, and the like.
Step 76: and determining the material use condition of the target area according to the forming time.
Through the formation time of confirming each orbit in the overlapping condition, confirm the goods and materials in service behavior in target area according to the formation time, can confirm the goods and materials in service behavior based on the corresponding relation between orbit formation time and the goods and materials, and then be convenient for carry out reasonable management to the goods and materials, promote the managerial efficiency of goods and materials.
In some embodiments, referring to fig. 8, step 76 may be the following flow:
step 761: and acquiring the use data of the material in unit time.
For example, big data collection can be performed in advance, and the use data of each material in unit time can be analyzed. The use data of the corresponding material in the unit time can be obtained according to the material type of the target area. For example, the types of materials include paper, bottled water, staplers, pens, and notebooks. The usage data of the paper in unit time is 5, the usage data of bottled water in unit time is 50 bottles, the usage data of the stapler in unit time is 3, the usage data of the pen in unit time is 5 and the usage data of the notebook in unit time is 5.
At this time, if the material type of the target area is bottled water, the usage data of the bottled water per unit time is 50 bottles.
Step 762: and determining the material use condition of the target area by using the forming time and the use data.
And determining the material use condition of the target area by multiplying the forming time by the use data.
Through the goods and materials in the formation time and the use data determination target area, the goods and materials use condition can be determined based on the corresponding relation between the formation time and the use data in unit time, so that the goods and materials are conveniently and reasonably managed, and the management efficiency of the goods and materials is improved.
In some embodiments, when the use condition of the material is determined, the remaining condition of the material in each material area can be displayed in an interface display mode, and when the remaining condition meets a preset condition, a material supplement suggestion is made.
In some embodiments, when the material supplement suggestion is made, the supplement suggestion can be made according to the current time. If the current time is at rest time, when the material is bottled water, based on the drinking water demand, the consumption of the bottled water material will be greatly increased, and then a large amount of supplementary material is recommended.
For another example, when the current time is about to be in the rest time, the material use condition is determined according to the technical scheme, and reasonable material supplement suggestions are made based on the material use condition. And if the residual material quantity is lower than the estimated consumption quantity in the rest time, performing material supplement suggestion.
Referring to fig. 9, fig. 9 is a schematic flow chart of a material management method according to a fourth embodiment of the present application. The method comprises the following steps:
step 91: and acquiring material distribution information of the target area and a monitoring image of the target area.
And step 92: and determining a target object in the monitoring image.
In some embodiments, the target object comprises a person object; the monitoring image can be identified by using a face identification network, and the face image in the monitoring image is determined.
In some embodiments, the target object comprises a person object; the monitoring image can be identified by utilizing a human face and human body identification network, and the human face image and the human body image in the monitoring image are determined.
Step 93: and determining a plurality of first position information of the target object in the monitored image.
In the monitoring process, a plurality of frames of monitoring images exist, so that the position information of the target object can be involved in each frame of monitoring image, and a plurality of first position information of the target object in the monitoring image is determined.
In some embodiments, when the target object is a face image, referring to fig. 10, step 93 may be the following process:
step 101: and clustering the face images in the multi-frame monitoring images to determine a plurality of face images of at least one person object.
In some embodiments, the monitoring image is identified by using a face recognition network, and a face image in the monitoring image is determined. Because the face images appearing in the monitored images can be of a plurality of personnel objects, the face images in the multi-frame monitored images need to be clustered so as to classify each face image into different personnel objects. That is, each person object corresponds to a plurality of face images.
Step 102: and determining a plurality of pieces of first position information of the at least one person object in the monitoring image according to a plurality of face images of the at least one person object.
In some embodiments, when the face image is determined, coordinate information of the face image may be determined, and the coordinate information may be used as first position information of the person object in the monitoring image. Therefore, the information of the plurality of first positions of the at least one person object in the monitoring image can be determined according to the plurality of face images.
Consequently, utilize image recognition technology to carry out face identification to multiframe image, and then confirm at least one personnel object at a plurality of first positional information of surveillance image, can make statistics of the personnel object in the surveillance image, be convenient for follow-up according to the quantity of personnel object determine the goods and materials in service behavior, be convenient for carry out reasonable management to goods and materials, promote the managerial efficiency of goods and materials.
In some embodiments, when the target objects are a human face image and a human body image, referring to fig. 11, step 93 may be the following process:
step 111: and respectively clustering the face images and the human body images in the multi-frame monitoring images to determine a plurality of face images of at least one person object and a plurality of human body images of at least one person object.
In some embodiments, the monitoring image is identified by using a human face and human body identification network, and a human face image and a human body image in the monitoring image are determined. Because the face images and the body images appearing in the monitored images can be of a plurality of person objects, the face images and the body images in the multi-frame monitored images need to be clustered so as to classify each face image and body image into different person objects. That is, each person object corresponds to a plurality of face images and a plurality of body images.
Step 112: and determining the incidence relation between the plurality of face images and the plurality of human body images.
Wherein the association can be based on the relative position of the face image and the body image.
For example, the face image and the body image are time-matched to determine the face image and the body image in the same image. And then carrying out correlation according to the relative positions of the face image and the human body image. For example, the face image and the body image located right below the face image are associated.
Step 113: and determining a plurality of first position information of the at least one person object in the monitoring image according to the plurality of face images of the at least one person object, the plurality of human body images of the at least one person object and the incidence relation between the plurality of face images and the plurality of human body images.
In some embodiments, after determining the association relationship between the plurality of face images and the plurality of body images, the coordinate information of the face image and the body image in each monitoring image may be determined, and the coordinate information may be used as the first position information of the person object in the monitoring image.
Therefore, utilize image recognition technology to carry out face identification and human body recognition to multiframe image, and then confirm a plurality of first position information of at least one personnel object at the surveillance image, can make statistics of the personnel object in the surveillance image, be convenient for follow-up according to the quantity of personnel object determine the goods and materials in service behavior, be convenient for carry out reasonable management to the goods and materials, promote the managerial efficiency of goods and materials, and further, utilize the fixed unchangeable characteristics of human body characteristic, such as clothing characteristic, can be with face image and human image correlation, can improve the accuracy of discernment personnel discernment and clustering.
Step 94: and determining the track of the target object according to the first position information of the target object in the monitoring image.
In some embodiments, the order of each first location information in the plurality of first location information may be determined according to the timestamp of the monitoring image, so as to determine the trajectory of the target object.
In some embodiments, referring to fig. 12, step 94 may be the following flow:
step 121: and determining a plurality of second position information of the target object in the target space according to the plurality of first position information of the target object in the monitoring image and the mapping relation between the predetermined position information of the monitoring image and the target space describing the material distribution information.
Since the first position information is image coordinates, it is necessary to convert the image coordinates into spatial coordinates. The conversion matrix of the position information of the monitoring image and the target space describing the material distribution information can be determined in advance.
The first position information is converted into a plurality of second position information of the target object in the target space by using the conversion matrix.
Step 122: and determining the track of the target object according to the second position information.
In some embodiments, the first location information is therefore time-stamped, and the converted second location information is also time-stamped, and the second location information may be ranked according to the time-stamps to determine the trajectory of the target object.
Therefore, the mapping relation is utilized to convert the first position information into the second position information, the track of the target object is determined according to the second position information, the use condition of the materials can be determined by utilizing the track, the materials are conveniently and reasonably managed, and the management efficiency of the materials is improved.
Step 95: and determining the material use condition of the target area according to the track and the material distribution information.
When the track of any person object is detected to be located in the range of any target material, the target material used by any person object is determined.
Furthermore, the material use condition of the target area can be determined according to the number of the personnel objects positioned in the range of any target material.
Consequently, utilize the orbit to determine the goods and materials in service behavior, be convenient for rationally manage the goods and materials, promote the managerial efficiency of goods and materials.
In some embodiments, the material use condition of the target material in a specified time period can be counted. Wherein, big data acquisition can be carried out in advance, and the use data of each material in unit time is analyzed. The use data of the corresponding material in the unit time can be obtained according to the material type of the target area. For example, the types of materials include paper, bottled water, staplers, pens, and notebooks. The usage data of the paper in unit time is 5, the usage data of bottled water in unit time is 50 bottles, the usage data of the stapler in unit time is 3, the usage data of the pen in unit time is 5 and the usage data of the notebook in unit time is 5.
At this time, if the material type of the target area is bottled water, the usage data of the bottled water per unit time is 50 bottles.
Therefore, the material use condition of the target material in a specified time period can be counted.
In the embodiment, a plurality of first position information of the target object in the monitored image is determined by utilizing an image recognition technology; according to the first position information of the target object in the monitoring image, the track of each target object is determined, the material use condition of the target area is determined according to the track and the material distribution information, the track of the target object can be determined according to the position information, the material use condition is determined according to the track and the material distribution information, the material is conveniently managed reasonably, and the material management efficiency is improved.
In an application scene, the use of materials by a user is explained as follows: specifically, referring to fig. 13, fig. 13 is a schematic flow chart of a material management method according to a fifth embodiment of the present application. The method comprises the following steps:
step 131: and acquiring a real-time monitoring image acquired from the monitoring equipment.
Step 132: and performing face analysis and human body analysis on the real-time monitoring image.
In some embodiments, a human face and body analysis algorithm may be used to perform human face analysis and body analysis on the real-time monitored image.
Step 133: and carrying out cluster analysis on the human face and the human body obtained by analysis to obtain corresponding crowd activity tracks, and synthesizing the crowd activity tracks into a track thermodynamic diagram by using a density function.
Wherein, the color in the track thermodynamic diagram is associated with the number of people, and the darker the color is, the more people in the area is represented.
In some embodiments, since the faces and the human bodies are analyzed at each time, many faces and human bodies exist in a time period. Therefore, it is necessary to cluster the faces and the human bodies using a clustering algorithm so that the faces and the human bodies belonging to the same human body are clustered as the same target object. Therefore, the number of people and the track of each human body can be counted, and the track of the activities of the people can be synthesized into a track thermodynamic diagram by using a density function.
Step 134: and superposing the track thermodynamic diagram and the material distribution diagram.
In some embodiments, the trajectory thermodynamic diagram fetches only data within 10 meters of the adjacent asset region of the asset map. And determining a crowd corresponding to the trajectory thermodynamic diagram within 1 meter near the material area, wherein the crowd can be considered to be using the materials in the material area.
Step 135: and listing the track thermodynamic diagram and the resources at the positions with higher coincidence degrees of the material areas, and calculating the corresponding relation between the time length of the crowd staying in various material areas and the material use by using a decision tree algorithm.
A decision tree algorithm is a method of approximating discrete function values. It is a typical classification method, which first processes the data, generates readable rules and decision trees using an inductive algorithm, and then analyzes the new data using decisions. In essence, a decision tree is a process of classifying data through a series of rules.
After the use condition of the materials is determined, the use condition of the materials is provided for resource management personnel, and the resource management personnel can improve the supply quantity and the supply frequency of the materials for the material areas so as to solve the problems of insufficient materials and supply of the materials.
Referring to fig. 14, fig. 14 is a schematic structural diagram of an embodiment of a material management device provided in the present application. The material management apparatus 140 includes: the obtaining module 141 is configured to obtain material distribution information of the target area and a monitoring image of the target area; a determining module 142, configured to determine a target object in the monitored image; and the processing module 143 is configured to determine the material usage of the target area according to the target object and the material distribution information.
Therefore, the target object in the monitoring image is determined by utilizing the monitoring image, and then the material use condition of the target area is determined according to the target object and the material distribution information, so that the material use condition can be determined, the material is conveniently and reasonably managed, and the management efficiency of the material is improved.
In some embodiments, the determining module 142 is further configured to identify the monitored image by using a target identification network, and determine a target object in the monitored image.
Therefore, utilize image recognition technology to carry out target object discernment, can be convenient for discern the target object of goods and materials regional within range, and then determine goods and materials in service behavior, and then be convenient for carry out reasonable management to goods and materials, promote the managerial efficiency of goods and materials.
In some embodiments, the processing module 143 is further configured to determine a plurality of first position information of the target object in the monitored image; determining the track of the target object according to a plurality of first position information of the target object in the monitored image; and determining the material use condition of the target area according to the track and the material distribution information.
Therefore, a plurality of first position information of the target object in the monitored image is determined by utilizing an image recognition technology; according to the target object at a plurality of first position information of monitoring image, and then determine each target object's orbit, according to orbit and material distribution information, confirm the goods and materials in target area behavior, can determine the orbit of target object according to position information, and then according to orbit and goods and materials distribution information, determine the goods and materials behavior, and then be convenient for carry out reasonable management to the goods and materials, promote the managerial efficiency of goods and materials.
In some embodiments, the target object comprises a person object; the determining module 142 is further configured to identify the monitored image by using a face recognition network, and determine a face image in the monitored image.
The processing module 143 is further configured to perform clustering on the face images in the multiple frame monitoring images, and determine multiple face images of at least one person object; and determining a plurality of pieces of first position information of the at least one person object in the monitoring image according to a plurality of face images of the at least one person object.
Therefore, utilize image recognition technology to carry out face identification to multiframe image, and then confirm at least one personnel object at a plurality of first positional information of surveillance image, can make statistics of the personnel object in the surveillance image, be convenient for follow-up quantity according to personnel object determines the goods and materials in service behavior, is convenient for carry out reasonable management to the goods and materials, promotes the managerial efficiency of goods and materials.
In some embodiments, the target object comprises a person object; the determining module 142 is further configured to identify the monitored image by using a human face and human body identification network, and determine a human face image and a human body image in the monitored image.
The processing module 143 is further configured to perform clustering processing on the face images and the human body images in the multiple frames of monitored images, respectively, to determine multiple face images of at least one person object and multiple human body images of at least one person object; determining the correlation relationship between a plurality of face images and a plurality of human body images; and determining a plurality of first position information of the at least one person object in the monitoring image according to the plurality of face images of the at least one person object, the plurality of body images of the at least one person object and the association relationship between the plurality of face images and the plurality of body images.
Therefore, utilize image recognition technology to carry out face identification and human body recognition to multiframe image, and then confirm a plurality of first positional information of at least one personnel object at the surveillance image, can make statistics of the personnel object in the surveillance image, be convenient for follow-up quantity according to personnel object determines the goods and materials in service behavior, be convenient for carry out reasonable management to the goods and materials, promote the managerial efficiency of goods and materials, and furthermore, utilize the fixed unchangeable characteristics of human body characteristic, can be associated face image and human image, can improve the accuracy of discernment personnel discernment and clustering.
In some embodiments, the processing module 143 is further configured to determine a plurality of second position information of the target object in the target space according to a plurality of first position information of the target object in the monitored image and a predetermined mapping relationship between the position information of the monitored image and the target space describing the material distribution information; and determining the track of the target object according to the second position information.
Therefore, the mapping relation is utilized to convert the first position information into the second position information, the track of the target object is determined according to the second position information, the use condition of the materials can be determined by utilizing the track, the materials are conveniently and reasonably managed, and the management efficiency of the materials is improved.
In some embodiments, the processing module 143 is further configured to determine that any person object uses the target material when the trajectory of any person object is detected to be within the range of any target material.
Therefore, the track is utilized to determine the use condition of the materials, the materials are conveniently and reasonably managed, and the management efficiency of the materials is improved.
In some embodiments, the processing module 143 is further configured to count the material usage of the target material in a specified time period.
Therefore, through the material service condition of the statistical target material in the appointed time period, the reasonable management of the material is facilitated, and the management efficiency of the material is improved.
Referring to fig. 15, fig. 15 is a schematic structural diagram of an embodiment of an electronic device provided in the present application. The electronic device 150 includes a processor 151 and a memory 152 coupled to the processor 151; the memory 152 stores a computer program, and the processor 151 is configured to execute the computer program to implement the steps of any one of the material management method embodiments.
In one particular implementation scenario, the electronic device 150 may include, but is not limited to: the devices such as smart phones, tablet computers, wearable devices, and individual soldier systems are not limited herein.
In particular, the processor 151 is configured to control itself and the memory 152 to implement the steps of any of the above-described embodiments of the image segmentation method. Processor 151 may also be referred to as a CPU (Central Processing Unit). Processor 151 may be an integrated circuit chip having signal processing capabilities. The Processor 151 may also be a general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. In addition, the processor 151 may be commonly implemented by integrated circuit chips.
According to the scheme, the overlapping condition of the target object and the material distribution information in the monitoring image is determined by utilizing the monitoring image, the material using condition of the target area is determined according to the overlapping condition, the material using condition can be determined, and further the material is conveniently and reasonably managed, and the material management efficiency is improved.
Referring to fig. 16, fig. 16 is a block diagram illustrating an embodiment of a computer readable storage medium according to the present application. The computer-readable storage medium 160 stores a computer program 161, and the computer program 161 is configured to implement the steps of any of the material management method embodiments described above when executed by the processor.
Above-mentioned scheme determines target object in the surveillance image through utilizing the surveillance image, and then according to target object and goods and materials distribution information, confirms the mode of the goods and materials in target area behavior, can determine the goods and materials behavior, and then is convenient for carry out rational management to the goods and materials, promotes the managerial efficiency of goods and materials.
In some embodiments, functions of or modules included in the apparatus provided in the embodiments of the present disclosure may be used to execute the method described in the above method embodiments, and specific implementation thereof may refer to the description of the above method embodiments, and for brevity, will not be described again here.
The foregoing description of the various embodiments is intended to highlight various differences between the embodiments, and the same or similar parts may be referred to each other, and for brevity, will not be described again herein.
In the embodiments provided in the present application, it should be understood that the disclosed method and apparatus may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of a module or a unit is merely one type of logical division, and other divisions may be realized in practice, for example, the unit or component may be combined or integrated with another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some interfaces, and may be in an electrical, mechanical or other form.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a separate product, may be stored in a computer readable storage medium. Based on the understanding, the technical solutions of the present application, which are essential or contributing to the prior art, or all or part of the technical solutions may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor (processor) to execute all or part of the steps of the methods according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, an optical disk, or other various media capable of storing program codes.
Claims (11)
1. A method of material management, the method comprising:
acquiring material distribution information of a target area and a monitoring image of the target area;
determining a target object in the monitoring image;
and determining the material use condition of the target area according to the target object and the material distribution information.
2. The method of claim 1, wherein the determining the target object in the monitored image comprises:
and identifying the monitoring image by using a target identification network, and determining the target object in the monitoring image.
3. The method of claim 1, wherein the determining the material usage of the target area according to the target object and the material distribution information comprises:
determining a plurality of first position information of the target object in the monitoring image;
determining the track of the target object according to a plurality of first position information of the target object in the monitoring image;
and determining the material use condition of the target area according to the track and the material distribution information.
4. The method of claim 3, wherein the target object comprises a person object;
determining a target object in the monitored image, comprising:
identifying the monitoring image by using a face identification network to determine a face image in the monitoring image;
determining a plurality of first position information of the target object in the monitoring image according to the target object in the monitoring image, including:
clustering the face images in the multi-frame monitoring images to determine a plurality of face images of at least one person object;
and determining a plurality of pieces of first position information of the at least one person object in the monitoring image according to a plurality of face images of the at least one person object.
5. The method of claim 3, wherein the target object comprises a person object;
determining a target object in the monitoring image, including:
identifying the monitoring image by using a human face and human body identification network, and determining a human face image and a human body image in the monitoring image;
determining a plurality of first position information of the target object in the monitoring image according to the target object in the monitoring image, including:
clustering the face images and the human body images in the multi-frame monitoring images respectively to determine a plurality of face images of at least one person object and a plurality of human body images of at least one person object;
determining the incidence relation between the human face images and the human body images;
and determining a plurality of pieces of first position information of the at least one person object in the monitoring image according to the plurality of face images of the at least one person object, the plurality of body images of the at least one person object and the association relationship between the plurality of face images and the plurality of body images.
6. The method of claim 3, wherein determining the trajectory of the target object according to a plurality of first position information of the target object in the monitored image comprises:
determining a plurality of second position information of the target object in the target space according to a plurality of first position information of the target object in the monitoring image and a mapping relation between the predetermined position information of the monitoring image and the target space describing the material distribution information;
and determining the track of the target object according to the second position information.
7. The method of claim 3, wherein determining material usage for the target zone based on the trajectory and the material distribution information comprises:
and when the track of any person object is detected to be located in the range of any target material, determining that the target material is used by the any person object.
8. The method of claim 7, wherein determining material usage for the target zone based on the trajectory and the material distribution information further comprises:
and counting the material use condition of the target material in a specified time period.
9. A material management device, characterized in that, the material management device includes:
the acquisition module is used for acquiring material distribution information of a target area and a monitoring image of the target area;
the determining module is used for determining a target object in the monitoring image;
and the processing module is used for determining the material use condition of the target area according to the target object and the material distribution information.
10. An electronic device comprising a processor and a memory coupled to the processor; the memory has stored therein a computer program for execution by the processor to implement the method of any one of claims 1-8.
11. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, implements the method according to any one of claims 1-8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210307861.9A CN114708631A (en) | 2022-03-25 | 2022-03-25 | Material management method and device, electronic equipment and computer readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210307861.9A CN114708631A (en) | 2022-03-25 | 2022-03-25 | Material management method and device, electronic equipment and computer readable storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114708631A true CN114708631A (en) | 2022-07-05 |
Family
ID=82171551
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210307861.9A Pending CN114708631A (en) | 2022-03-25 | 2022-03-25 | Material management method and device, electronic equipment and computer readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114708631A (en) |
-
2022
- 2022-03-25 CN CN202210307861.9A patent/CN114708631A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7136524B1 (en) | Robust perceptual color identification | |
US20190392244A1 (en) | Article management system, information processing apparatus, and control method and control program of information processing apparatus | |
Weidner | Contribution to the assessment of segmentation quality for remote sensing applications | |
CN109447169A (en) | The training method of image processing method and its model, device and electronic system | |
CN206193853U (en) | Article management system based on electronic label | |
CN110414313A (en) | Abnormal behaviour alarm method, device, server and storage medium | |
CN101848377B (en) | Device and method for intelligent linkage of multi-video recording device based on cloud computing and mass video searching | |
CN107992820A (en) | Counter automatic selling method based on binocular vision | |
CN102119343B (en) | Target detection device and target detection method | |
CN104809187A (en) | Indoor scene semantic annotation method based on RGB-D data | |
CN101896924A (en) | System and method for determining RFID tagged items encompassed in a given area | |
CN107330386A (en) | A kind of people flow rate statistical method and terminal device | |
US20070143079A1 (en) | Method and apparatus for extracting information from an array of hazardous material sensors | |
CN116403339B (en) | Printer intelligent management system and method based on RFID tag identification | |
CN102017606A (en) | Image processing device, camera, image processing method, and program | |
CN112070079B (en) | X-ray contraband package detection method and device based on feature map weighting | |
CN108009216A (en) | The processing method of destination object, device and system, storage medium, processor | |
CN109447103B (en) | Big data classification method, device and equipment based on hard clustering algorithm | |
CN105843848A (en) | Business monitoring data processing method, system, database system and electronic equipment | |
CN108596052A (en) | A kind of articles seeking method, system and terminal device | |
CN114387595A (en) | Automatic cargo identification method and device based on cargo splicing identification | |
CN114708631A (en) | Material management method and device, electronic equipment and computer readable storage medium | |
Zhou et al. | Variability in individual home-work activity patterns | |
CN115083004B (en) | Identity recognition method and device and computer readable storage medium | |
CN113879724A (en) | Garbage classification system based on crowdsourcing intelligence |
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 |