CN114529971A - Article pickup management method, article pickup management device, and computer storage medium - Google Patents

Abstract

The application discloses an article pickup management method, an article pickup management system and a computer storage medium. The article pickup management method comprises the following steps: acquiring a video stream in a storage room, and identifying characteristic information of a target object in the storage room from the video stream, wherein the characteristic information at least comprises face information of the target object; and determining that the current article pickup behavior is not compliant based on the characteristic information, and generating alarm information. By the mode, the compliance of the article taking of the storage room can be automatically identified, and the automatic alarm of the non-compliant article taking behavior can be realized.

Description

Article pickup management method, article pickup management device, and computer storage medium

Technical Field

The present application relates to the field of video analysis technologies, and in particular, to an article pickup management method, an article pickup management apparatus, and a computer storage medium.

Background

In order to ensure effective management of articles, strict management of article pickup is required. However, many storage rooms now adopt a manual recording mode to record the articles received; the manual recording mode cannot identify the compliance of the article receiving link, and the automatic alarm cannot be realized for the non-compliant article receiving behavior.

Disclosure of Invention

The technical problem that this application mainly solved is how to automatic identification storeroom article get the compliance, and realizes the automatic alarm to the article of non-compliance and get the action.

In order to solve the technical problem, the application adopts a technical scheme that: an article pickup management method is provided. The article pickup management method comprises the following steps: acquiring video stream in a storage room, and identifying characteristic information of a target object in the storage room from the video stream, wherein the characteristic information at least comprises face information of the target object; and determining that the current article picking behavior is not compliant based on the characteristic information, and generating alarm information.

By the method, the face information and the like of the target object in the storage room are acquired based on the video stream analysis in the storage room, and whether the current article getting behavior in the storage room is in compliance is determined based on the face information and the like, so that the compliance of article getting in the storage room can be automatically identified; and an alarm is generated when the current item pickup behavior is not compliant. Therefore, the method and the device can also realize automatic alarm of non-compliant article pickup behaviors.

Wherein, the target object includes article management object and article supervision object, and the above-mentioned behavior of receiving the current article is determined to be not in compliance based on the characteristic information includes: matching the face information with first preset face information to obtain a matching result; and determining that the current article picking behavior is not in compliance if the article management object or the article surveillance object does not exist in the storage room based on the matching result.

By the method, the compliance of whether the article management object and the article supervision object are in the field or not can be automatically identified.

Wherein the characteristic information further includes a number of target objects, and the determining that the current item pickup behavior is not compliant based on the characteristic information further includes: determining that an article management object and an article surveillance object exist in the storage room based on the face information, and comparing the quantity with a quantity threshold value; if the quantity is smaller than the quantity threshold value, determining that the current article picking behavior is not in compliance; the article pickup management method further includes: and if the quantity is greater than or equal to the quantity threshold value, determining that the current article picking behavior is in compliance.

By the method, the compliance of the number of the existing target objects in the article pickup process can be automatically identified.

Wherein, the determining that the current item pickup behavior is not compliant based on the characteristic information further comprises: determining that an article management object and an article surveillance object exist in a storage chamber based on the face information, and acquiring a first time node for recognizing the face information for the first time, a second time node for recognizing the face information of the article management object for the first time and a third time node for recognizing the face information of the article management object for the first time; and if the time length between the second time node and the first time node is longer than a second preset time length, or the time length between the third time node and the first time node is longer than the second preset time length, determining that the current article getting behavior is not in compliance.

By the mode, the compliance of whether the article management object and the article monitoring object appear at the specified time in the article receiving process can be automatically identified.

Wherein the characteristic information further includes: identifying a time node of the face information, wherein the determining of the non-compliance of the current article pickup behavior based on the feature information further comprises: determining that an article management object and an article surveillance object exist in the storage room based on the face information, and respectively acquiring a time node corresponding to the article management object and a time node corresponding to the article surveillance object; respectively calculating a first time length between two adjacent time nodes of the article management object and a second time length between two adjacent time nodes of the article supervision object; and if the first duration or the second duration is longer than a first preset duration, determining that the current article picking behavior is not in compliance.

By the method, the compliance of whether the article management object and the article monitoring object are absent for a long time in the article picking process can be automatically identified.

Wherein the determining that the current item pickup behavior is not compliant based on the characteristic information further comprises: if the number is larger than or equal to the number threshold, matching the face information except the face information of the article management object and the face information of the article surveillance object with second preset face information; if the matching is successful, acquiring preset article information corresponding to the face information successfully matched with the second preset face information; comparing the article information corresponding to the current article pickup behavior with preset article information; and if the article information corresponding to the current article pickup behavior is inconsistent with the preset article information, determining that the current article pickup behavior is not in compliance.

By the mode, whether the article picking object has the article picking authority or not and whether the picked article accords with the identity of the article picking object or not can be determined, and the safety can be improved.

Wherein, the article picking management method further comprises: and when no target object in the storage room within a third preset time is monitored, determining that the current article getting behavior is finished.

In this way, the current item pickup behavior can be automatically identified and ended.

Wherein, the article picking method further comprises: acquiring the pickup time and the first article information of the article, and the return time and the second article information of the article from the video stream; if the time length between the getting time and the returning time is longer than a fourth preset time length, generating alarm information; and if the error between the first article information and the second article information is larger than the error threshold value, generating alarm information.

By the method, whether the picked up article meets the related requirements or not can be determined through the information during article picking and the information during returning, and an alarm is given when the picked up article does not meet the related requirements.

In order to solve the technical problem, the application adopts a technical scheme that: an article pickup management system is provided. The article pickup management system includes: the video acquisition device is used for acquiring video streams in the storage room; the electronic equipment is communicated with the video acquisition device and used for acquiring the video stream from the video acquisition device and identifying the characteristic information of the target object in the storage room from the video stream, wherein the characteristic information at least comprises face information; the electronic equipment is used for determining that the current article picking behavior is not compliant based on the characteristic information and generating alarm information.

The method and the device for acquiring the object information of the storage room are based on video stream analysis in the storage room, face information and the like of the target object in the storage room are acquired, and whether the current object getting behavior in the storage room is in compliance or not is determined based on the face information and the like, so that the method and the device for acquiring the object information of the storage room can automatically identify the compliance of the object getting in the storage room; and an alarm is generated when the current item pickup behavior is not compliant. Therefore, the method and the device can also realize automatic alarm of non-compliant article pickup behaviors.

In order to solve the technical problem, the application adopts a technical scheme that: a computer storage medium is provided. The computer storage medium has stored thereon program instructions that, when executed, implement the article pickup management method described above.

The method and the device for acquiring the object information of the storage room are based on video stream analysis in the storage room, face information and the like of the target object in the storage room are acquired, and whether the current object getting behavior in the storage room is in compliance or not is determined based on the face information and the like, so that the method and the device for acquiring the object information of the storage room can automatically identify the compliance of the object getting in the storage room; and an alarm is generated when the current item pickup behavior is not compliant. Therefore, the method and the device can also realize automatic alarm of non-compliant article pickup behaviors.

The beneficial effect of this application is: different from the prior art, the article picking management method comprises the following steps: acquiring video stream in a storage room, and identifying characteristic information of a target object in the storage room from the video stream, wherein the characteristic information at least comprises face information; and determining that the current article picking behavior is not compliant based on the characteristic information, and generating alarm information. The method and the device for acquiring the object information of the storage room are based on video stream analysis in the storage room, face information and the like of the target object in the storage room are acquired, and whether the current object getting behavior in the storage room is in compliance or not is determined based on the face information and the like, so that the method and the device for acquiring the object information of the storage room can automatically identify the compliance of the object getting in the storage room; and an alarm is generated when the current item pickup behavior is not compliant. Therefore, the method and the device can also realize automatic alarm of non-compliant article pickup behaviors.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts. Wherein:

FIG. 1 is a schematic flow chart diagram illustrating an embodiment of an article pickup management method according to the present application;

FIG. 2 is a flowchart illustrating a specific step S12 in the embodiment of FIG. 1;

FIG. 3 is a flowchart illustrating a specific step S12 in the embodiment of FIG. 1;

FIG. 4 is a flowchart illustrating a specific step S12 in the embodiment of FIG. 1;

FIG. 5 is a schematic flow chart diagram illustrating an embodiment of an article pickup management method according to the present application;

FIG. 6 is a schematic diagram of an embodiment of an article pickup management system according to the present application;

FIG. 7 is a flowchart of the operation of the article pickup management system of the embodiment of FIG. 6;

FIG. 8 is a schematic structural diagram of an embodiment of an electronic device of the present application;

FIG. 9 is a schematic structural diagram of an embodiment of a computer storage medium according to the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

The terms "first" and "second" in this application are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. In the description of the present application, "plurality" means at least two, e.g., two, three, etc., unless explicitly specifically limited otherwise. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.

The present application first proposes an article pickup management method, as shown in fig. 1, fig. 1 is a schematic flow chart of an embodiment of the article pickup management method of the present application. The article pickup management method of the embodiment specifically comprises the following steps:

step S11: and acquiring a video stream in the storage room, and identifying the characteristic information of the target object in the storage room from the video stream, wherein the characteristic information comprises face information.

The storage compartment for storing articles is generally a closed space, and only one door is provided to allow entry and exit. Can install video acquisition device in the apotheca, gather the information in the apotheca like the camera to the realization is to the control of apotheca, and can automatic identification get into the target object of apotheca, for example personnel etc.. To improve safety, the video capture device should cover the entire storage compartment, i.e., the visible range of the video capture device covers the entire interior area of the storage compartment. The video acquisition device and the article picking management system are in wired or wireless communication.

The embodiment can acquire the video stream in the storage chamber through the video acquisition device such as a camera installed in the storage chamber; the video acquisition device uploads the acquired video stream to the article picking management system, and the article picking management system identifies the face information of the target object in the storage room from the video stream by using a video analysis technology.

In an application scene, when a target object appears in the storage room, the video stream in the storage room can be acquired, and the monitoring method can be realized through infrared or door opening instructions and the like.

In another application scenario, a time node of a first occurrence of a target object in a storage room can be identified through a video analysis method, and the time node is taken as a starting time point of a current article pickup behavior, so that characteristic information of a video stream after the time node is identified.

And if the video stream monitors that no target object exists in the storage chamber within the third preset time, determining that the current article getting behavior is finished, and recording an end time node. For example, when no face information exists in a certain frame of image, the timer starts to time, the face information appears in the following image frame, the time counting is finished, and if the time counted by the timer is longer than a third preset time length, it is determined that no target object exists in the storage room within the third preset time length. And identifying characteristic information of the video stream between the starting time node and the ending time node.

Step S12: and determining that the current article picking behavior is not compliant based on the characteristic information, and generating alarm information.

The object picking management system determines whether the current object picking behavior is in compliance or not based on the face information of the target object in the storage room, and generates alarm information if the current object picking behavior is not in compliance.

In the embodiment, based on video stream analysis in the storage room, face information and the like of a target object in the storage room are obtained, and whether the current article pickup behavior in the storage room is in compliance is determined based on the face information and the like, so that the embodiment can automatically identify the compliance of article pickup in the storage room; and an alarm is generated when the current item pickup behavior is not compliant. Therefore, the embodiment can also realize automatic alarm of non-compliant article picking-up behavior.

In an application scenario, the rules for picking up the articles in the storage room are as follows: 1) the article management object and the article surveillance object are required to be simultaneously present when entering the storage room; 2) the number of target objects present reaches 3. The article can be picked up only if the rules 1) and 2) are satisfied, and the importance of the rule 1) is greater than that of the rule 2) for the improvement of the security.

Specifically, the present embodiment may implement step S12 by the method as shown in fig. 2. The method of the present embodiment includes steps S21 to S24.

Step S21: and matching the face information with the first preset face information to obtain a matching result.

The face information of the article management object and the face information of the article surveillance object can be input into the article picking management system in advance to serve as first preset face information; the number of article management objects and the number of article supervision objects are not limited; the face information of the object with the article picking authority can be pre-input into the article picking management system to serve as second preset face information; the object management object, the object supervision and the object with the object receiving authority are respectively stored in different face information bases, so that the processing speed of subsequent face information matching is improved.

The article picking management system matches the face information acquired from the video stream with first preset face information in an article management object face information base, if matching is successful, it is determined that an article management object exists in the storage room, other unmatched face information acquired from the video stream is continuously matched with the first preset face information in an article surveillance object face information base, and if matching is successful, it is determined that an article surveillance object exists in the storage room; if the matching with the first preset face information in the article management object face information base fails, other unsuccessfully matched face information acquired from the video stream does not need to be continuously matched with the first preset face information in the article surveillance object face information base.

Of course, in order to refine the log of records of non-compliance of the article pickup behavior (specific information of alarms introduced later), after the matching with the first preset face information in the article management object face information base fails, other face information which is not successfully matched and is obtained from the video stream may be continuously matched with the first preset face information in the article surveillance object face information base, so as to further determine whether an article surveillance object exists in the storage room.

In other embodiments, the determination of the object for article surveillance may be performed first, and then the determination of the object for article management may be performed, or both (where computational overhead allows, matching efficiency may be improved).

Step S22: and if the article management object or the article surveillance object does not exist in the storage room based on the matching result, determining that the current article picking behavior is not compliant, and generating alarm information.

If no article management object or article supervision exclusive share exists in the storage room, the rule 1) is not met, so that the current article picking-up behavior is determined to be not in compliance.

The article pickup behavior that does not comply with the above rule 1) can be automatically recognized by the steps S21 and S22.

The characteristic information further comprises the number of target objects in the storage room, and the article picking management system can obtain the number of the target objects by counting the number of the face information recognized from the video stream.

Step S23: and determining that the article management object and the article surveillance object exist in the storage chamber based on the face information, and comparing the quantity with a quantity threshold value.

If an article management object and an article surveillance object exist in the storage room, determining that the current article picking behavior meets the rule 1); after the current item pickup behavior meets the rule 1), continuously determining whether the current item pickup behavior meets the rule 2), and comparing the number of the target objects with a number threshold (known from the above analysis, the number threshold is 3) by the item pickup management system.

Step S24: and if the quantity is smaller than the quantity threshold value, determining that the current article picking behavior is not compliant, and generating alarm information.

If the number of the target objects is less than 3, determining that the current article pickup behavior does not conform to the rule 2), and therefore determining that the current article pickup behavior does not conform. This case belongs to a scene where there is no article pickup object.

The article pickup behavior not complying with the above rule 2) can be automatically recognized in steps S23 and S24.

Further, if the number is greater than or equal to the number threshold, determining that the current item pickup behavior is compliant.

If the number is greater than or equal to 3, determining that the current item pickup behavior meets the rule 2), and therefore determining that the current item pickup behavior is compliant. The article pickup behavior according to the above rule 2) can be automatically recognized.

In the embodiment, whether the article management object and the article surveillance object exist in the storage room is determined firstly, so that the safety of the articles is ensured in the whole article picking process.

In another application scenario, to improve the security of the article pickup behavior, the rule of article pickup in the storage room may be set as: 1) an article management object and an article surveillance object need to be present at the same time when entering the storage room; 2) the article management object and the article surveillance object are present within a second preset time before the article picking process; 3) the number of target objects present reaches 3; the article can be picked up only if the rules 1 to 3) are satisfied, and the security is improved, the importance of the rule 1) is greater than that of the rule 2).

Alternatively, the present embodiment may implement step S12 by the method shown in fig. 3. The method of the present embodiment includes steps S31 to S33.

Step S31: and matching the face information with first preset face information to determine whether an article management object and an article supervision object exist in the storage room.

Step S31 is similar to step S21 described above and is not described here.

The feature information further includes a time node at which the face information is recognized, that is, a time node at which the target object is in the storage room.

Step S32: and determining that an article management object and an article surveillance object exist in the storage chamber based on the face information, and then acquiring a first time node for recognizing the face information for the first time, a second time node for recognizing the face information of the article management object for the first time and a third time node for recognizing the face information of the article management object for the first time.

If the article management object and the article surveillance object exist in the storage room, the article pickup management system respectively acquires a first time node for firstly recognizing the face information, a second time node for firstly recognizing the face information of the article management object and a third time node for firstly recognizing the face information of the article management object so as to determine the presence condition of the article management object and the article surveillance object when the current article pickup action starts.

Step S33: and if the time length between the second time node and the first time node is greater than a second preset time length, or the time length between the third time node and the first time node is greater than the second preset time length, determining that the current article pickup behavior is not compliant, and generating alarm information.

If the time length between the second time node and the first time node is longer than a second preset time length, the article management object is not present in the second preset time length before the current article pickup action is started; and if the time length between the third time node and the first time node is longer than a second preset time length, the object supervision object is considered to be absent in the second preset time length before the current object picking behavior starts, and the object supervision object does not accord with the rule 2), and the current object picking behavior is determined to be not in compliance.

Optionally, the present embodiment further includes step S34 and step S35.

Step S34: and if the duration between the second time node and the first time node is less than or equal to a second preset duration, and the duration between the third time node and the first time node is less than or equal to the second preset duration, comparing the quantity with a quantity threshold value.

If the time length between the second time node and the first time node is less than or equal to a second preset time length, and the time length between the third time node and the first time node is less than or equal to the second preset time length, the article management object and the article supervision object are present within the second preset time length before the current article pickup action is started, and the article management object and the article supervision object conform to 1) and the rule 2), and whether the current article pickup action conforms to the rule 3) is continuously determined.

Step S35: and if the quantity is smaller than the quantity threshold value, determining that the current article picking behavior is not qualified, and generating alarm information.

Steps S34 and S35 are similar to steps S23 and S24, and are not repeated here.

In the embodiment, after determining whether the article management object and the article surveillance object exist in the receiving storage room, it is determined whether the article management object and the article surveillance object are present within a second preset time period before the current article receiving behavior starts, so that the safety of the whole article receiving process is improved.

Further, if the number of the target objects is larger than or equal to the number threshold, the current item picking behavior compliance is determined.

In another application scenario, to improve the normative of the article pickup behavior, the rule of article pickup in the storage room may be set as: 1) the article management object and the article surveillance object are required to be simultaneously present when entering the storage room; 2) the number of target objects present reaches 3; 3) the object to be picked up is consistent with the picked up object information; the article can be picked up only if the rules 1 to 3) are satisfied, and the security is improved, the importance of the rule 1) is greater than that of the rule 2).

Alternatively, the present embodiment may implement step S12 by the method shown in fig. 4. The method of the present embodiment includes steps S41 to S48.

Step S41: and matching the face information with the first preset face information to obtain a matching result.

Step S41 is similar to step S21 described above and is not repeated here.

Step S42: and if the article management object or the article surveillance object does not exist in the storage room based on the matching result, determining that the current article picking behavior is not compliant, and generating alarm information.

Step S42 is similar to step S22 described above and is not repeated here.

Step S43: and determining that the article management object and the article surveillance object exist in the storage chamber based on the matching result, and comparing the quantity with a quantity threshold value.

Step S43 is similar to step S23 described above and is not repeated here.

Step S44: and if the quantity is smaller than the quantity threshold value, determining that the current article picking behavior is not compliant, and generating alarm information.

Step S44 is similar to step S24 described above and is not repeated here.

Step S45: and if the number is larger than or equal to the number threshold value, determining that the face information except the face information of the object to be managed and the face information of the object to be supervised are matched with the second preset face information.

If the number is greater than or equal to 3, determining that the current item pickup behavior meets the rule 2), and further determining whether the current item pickup behavior meets the rule 3).

The article pickup management system matches the other face information unsuccessfully matched in step S41 with the second preset face information in the article pickup object face information base.

Step S46: and if the matching is successful, acquiring preset article information corresponding to the face information successfully matched with the second preset face information.

And if the second preset face information is matched with the second preset face information in the face information base of the object picking object, the object picking object in the storage room is considered to have the object picking permission, and the preset object information corresponding to the object picking object is further obtained.

And if the second preset face information is not matched with the second preset face information in the face information base of the object picking object, the object picking object in the storage room is considered to have no object picking authority, and alarm information is generated.

Step S47: and comparing the article information corresponding to the current article pickup behavior with preset article information.

The article pick-up management system further identifies the picked-up article information from the video stream; and the article pickup management system picks up the article information corresponding to the current article pickup action. Such as the type and quantity of the article, and the like, are compared with the preset article information to determine whether the article pickup object picks up the article.

Step S48: and if the article information corresponding to the current article picking behavior is inconsistent with the preset article information, determining that the current article picking behavior is not compliant, and generating alarm information.

Further, if the article information corresponding to the current article pickup behavior is inconsistent with the preset article information, determining that the current article pickup behavior is not compliant, and generating alarm information that the article pickup is not matched.

The embodiment further determines whether the object to be picked up has the object picking authority or not and whether the picked object conforms to the identity of the object to be picked up, so that the safety can be improved.

The article pickup object management system may perform the method of the above embodiment in real time during the current article pickup object process, or may perform the method of the above embodiment after the current article pickup object process is ended.

Specifically, if the behavior of the current article pickup object is not compliant due to the fact that no article management object or article surveillance object exists in the storage room, alarm information that the article management object or the article surveillance object is not present is generated; if the behavior of the current object picking object is not in compliance due to the fact that the number of the target objects is less than 3, alarm information that the number of the target objects in the field is insufficient is generated; if the current behavior of the object for article pickup is not compliant due to the fact that the object for article management and the object for article surveillance are present in the second preset time before the process for article pickup, alarm information is generated that the object for article management or the object for article surveillance does not appear in the set time; if the behavior of the current object to be picked up is not compliant due to the fact that the object to be picked up is not matched, alarm information that the object to be picked up has no object picking authority is generated; and if the current article picking behavior is not in accordance due to the fact that the article information is not matched, the article is not matched with the alarm information.

In another embodiment, in order to improve the security of the article pickup behavior, the article pickup management system may further obtain, in real time, the face information identifying the article management object and the time node identifying the face information identifying the article surveillance object in the current article pickup process; and then respectively calculating a first time length between two adjacent time nodes of the article management object and a second time length between two adjacent time nodes of the article pickup supervision object.

The article pickup management system calculates a first time length between two adjacent time nodes of the article management object so as to obtain the time length when the article pickup management object is absent; the article picking management system calculates a first time length between two adjacent time nodes of the article surveillance object to acquire the time length when the article surveillance object is not present.

If the first duration or the second duration is longer than the first preset duration, the article surveillance object or the article management object is determined not to be present for a long time, and alarm information is generated to inform the article surveillance object or the article management object of the presence, so that the safety can be improved.

In other embodiments, the article pickup rule may be adjusted according to the application scenario, and the method similar to the above embodiments may be adopted to implement automatic identification and alarm of compliance of article pickup behavior.

In another embodiment, as shown in fig. 5, the method for managing article pickup in this embodiment specifically includes the following steps:

step S51: and acquiring a video stream in the storage room, and identifying the characteristic information of the target object in the storage room from the video stream, wherein the characteristic information comprises face information.

Step S52: and determining that the current article picking behavior is not compliant based on the characteristic information, and generating alarm information.

Steps S51 and S52 are similar to steps S11 and S12, and are not repeated here.

Step S53: and acquiring the pickup time and the first article information of the article, and the return time and the second article information of the article from the video stream.

The first item information may be first picture information of a picked-up item acquired from the video stream at the time of pickup, and the second pickup information may be second picture information of a returned item acquired from the video stream at the time of return.

Step S54: and if the time length between the picking time and the returning time is greater than the fourth preset time length, generating alarm information.

And if the time length between the getting time and the returning time of the article is greater than the specified first preset time length, the article is not returned on time, and alarm information is generated.

Step S55: and if the error between the first article information and the second article information is larger than the error threshold value, generating alarm information.

If a large deviation exists between the first picture information when the article is picked up and the second picture information when the article is returned, such as the quantity reduction or the article abrasion, alarm information is generated.

The embodiment can determine whether the picked up article meets the relevant requirements or not through the information in the article picking-up process and the information in the article returning process, and alarm when the picked-up article does not meet the relevant requirements.

The present application further provides an article pickup management system, as shown in fig. 6, the article pickup management system of this embodiment includes: a video acquisition device 61 and an electronic device 62; the video acquisition device 61 is used for acquiring video streams in the storage room; the electronic equipment 62 is in communication with the video acquisition device 61 and is used for acquiring a video stream from the video acquisition device 61 and identifying characteristic information of a target object in the storage room from the video stream, wherein the characteristic information at least comprises face information; the electronic device 62 is configured to determine that the current item pickup behavior is non-compliant based on the characteristic information and generate an alert message.

In an application scenario, as shown in fig. 7, the electronic device 62 determines that the video capture device 61 detects a target object, and records a start time; the electronic device 62 then obtains all the face information present; if the target object does not appear within X minutes, the electronic device 62 determines that the article pickup process is finished, and records the end time; the electronic device 62 analyzes the video stream and determines whether there are object management objects and object surveillance objects in all face information; if yes, the electronic device 62 further determines whether the article management object and the article surveillance object appear within three minutes after the start time, and if not, the electronic device 62 generates alarm information that the article management object or the article surveillance object does not appear; if the alarm information does not appear within three minutes after the starting time, the electronic device 62 generates alarm information that the article management object and/or the article surveillance object do not appear within the specified time; if the item management object and the item surveillance object appear within three minutes after the start time, the electronic device 62 further determines whether the number of target objects present is greater than or equal to 3; if the number of the target objects in the scene is greater than or equal to 3, the electronic equipment 62 judges that the article is successfully picked up, and displays the snapshot pictures according to the face classification; if the number of target objects present is less than 3, the electronic device 62 generates alert information that the number of target objects present is insufficient.

The electronic device 62 is also used for implementing the above-mentioned article picking management method, which is not described herein.

The electronic device 62 is further provided with a UI interface, and the face information of the article management object and the face information of the article surveillance object may be entered into the article pickup management system in advance through the UI interface to be used as first preset face information; the face information of the object to be picked up with the object picking authority can be pre-input into the object picking management system to serve as second preset face information; the face information of the article management object, the article supervision object and the article pickup object with the article pickup authority are respectively stored in different face information bases, so that the processing speed of subsequent face information matching is improved.

When the current item pickup behavior is compliant, the electronic device 62 generates an item pickup record and displays the item pickup record through the UI interface; when the current item pickup behavior is not compliant, the electronic device 62 generates alarm information and displays the alarm information through the UI interface, where the alarm information includes: snapshot when giving an alarm, trigger the reason of the alarm (without accompanying object of article management, without accompanying object of article supervision, less than 3 present).

The object of the item pickup can be automatically recorded, the item pickup record is generated according to the item pickup batch, and the item pickup record is a product in the aspect of the first-payment item pickup compliance.

As shown in fig. 8, the electronic device 62 of the present embodiment includes a processor 101, a memory 102 coupled to the processor 101, an input/output device 103, and a bus 104.

The processor 101, the memory 102, and the input/output device 103 are respectively connected to the bus 104, the memory 102 stores program instructions, and the processor 101 is configured to execute the program instructions to implement the article pickup management method.

In the present embodiment, the processor 101 may also be referred to as a CPU (Central Processing Unit). The processor 101 may be an integrated circuit chip having signal processing capabilities. The processor 101 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 101 may be any conventional processor or the like.

The present application further provides a computer storage medium, as shown in fig. 9, fig. 9 is a schematic structural diagram of an embodiment of the computer storage medium of the present application. The computer storage medium 110 has stored thereon program instructions 111, which program instructions 111, when executed by a processor (not shown), implement an article pickup management method.

The computer storage medium 110 of the embodiment may be, but is not limited to, a usb disk, an SD card, a PD optical drive, a removable hard disk, a high-capacity floppy drive, a flash memory, a multimedia memory card, a server, etc.

Different from the prior art, the article picking management method comprises the following steps: acquiring video stream in a storage room, and identifying characteristic information of a target object in the storage room from the video stream, wherein the characteristic information at least comprises face information; and determining that the current article picking behavior is not compliant based on the characteristic information, and generating alarm information. The method and the device for acquiring the object information of the storage room are based on video stream analysis in the storage room, face information and the like of the target object in the storage room are acquired, and whether the current object getting behavior in the storage room is in compliance or not is determined based on the face information and the like, so that the method and the device for acquiring the object information of the storage room can automatically identify the compliance of the object getting in the storage room; and an alarm is generated when the current item pickup behavior is not compliant. Therefore, the method and the device can also realize automatic alarm of non-compliant article pickup behaviors.

In addition, if the above functions are implemented in the form of software functions and sold or used as a standalone product, the functions may be stored in a storage medium readable by a mobile terminal, that is, the present application also provides a storage device storing program data, which can be executed to implement the method of the above embodiments, the storage device may be, for example, a usb disk, an optical disk, a server, etc. That is, the present application may be embodied as a software product, which includes several instructions for causing an intelligent terminal to perform all or part of the steps of the methods described in the embodiments.

In the description of the present application, reference to the description of the terms "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.

Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "plurality" means at least two, e.g., two, three, etc., unless explicitly specified otherwise.

Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and the scope of the preferred embodiments of the present application includes other implementations in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.

The logic and/or steps represented in the flowcharts or otherwise described herein, such as an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device (such as a personal computer, server, network device, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions). For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.

The above description is only for the purpose of illustrating embodiments of the present application and is not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application or are directly or indirectly applied to other related technical fields, are also included in the scope of the present application.

Claims (10)

1. An article pickup management method, comprising:

acquiring a video stream in a storage room, and identifying characteristic information of a target object in the storage room from the video stream, wherein the characteristic information at least comprises face information of the target object;

and determining that the current article picking-up behavior is not compliant based on the characteristic information, and generating alarm information.

2. The method according to claim 1, wherein the target objects include an item management object and an item surveillance object, and the determining that the current item pickup behavior is not compliant based on the characteristic information includes:

matching the face information with first preset face information to obtain a matching result;

and determining that the current article picking behavior is not in compliance if the article management object or the article surveillance object does not exist in the storage chamber based on the matching result.

3. The item pickup management method according to claim 2, wherein the characteristic information further includes a number of the target objects, and the determining that the current item pickup behavior is not compliant based on the characteristic information further comprises:

determining that the article management object and the article surveillance object exist in the storage chamber based on the face information, and comparing the number with a number threshold;

if the quantity is smaller than the quantity threshold value, determining that the current article picking behavior is not in compliance;

further comprising:

and if the number is greater than or equal to the number threshold, determining that the current article pickup behavior is compliant.

4. The item pickup management method according to claim 2, wherein the determining that the current item pickup behavior is not compliant based on the characteristic information further comprises:

determining that the article management object and the article surveillance object exist in the storage chamber based on the face information, and acquiring a first time node at which the face information is recognized for the first time, a second time node at which the face information of the article management object is recognized for the first time, and a third time node at which the face information of the article management object is recognized for the first time;

and if the time length between the second time node and the first time node is greater than a second preset time length, or the time length between the third time node and the first time node is greater than the second preset time length, determining that the current article pickup behavior is not in compliance.

5. The item pickup management method according to claim 2, wherein the characteristic information further includes: identifying a time node of the face information, the determining that the current item pickup behavior is not compliant based on the feature information, further comprising:

determining that the article management object and the article surveillance object exist in the storage chamber based on the face information, and respectively acquiring the time node corresponding to the article management object and the time node corresponding to the article surveillance object;

respectively calculating a first time length between two adjacent time nodes of the article management object and a second time length between two adjacent time nodes of the article supervision object;

and if the first duration or the second duration is longer than a first preset duration, determining that the current article picking behavior is not in compliance.

6. The item pickup management method according to claim 3, wherein the determining that the current item pickup behavior is not compliant based on the characteristic information further comprises:

if the number is greater than or equal to the number threshold, matching the face information except the face information of the article management object and the face information of the article surveillance object with second preset face information;

if the matching is successful, acquiring preset article information corresponding to the face information successfully matched with the second preset face information;

comparing the article information corresponding to the current article pickup behavior with the preset article information;

and if the article information corresponding to the current article pickup behavior is inconsistent with the preset article information, determining that the current article pickup behavior is not in compliance.

7. The item pickup management method according to claim 1, further comprising:

and when no target object in the storage room within a third preset time length is monitored, determining that the current article getting behavior is finished.

8. The item pickup management method according to claim 1, further comprising:

acquiring the pickup time and first article information of an article, and the return time and second article information of the article from the video stream;

if the time length between the picking time and the returning time is longer than a fourth preset time length, generating alarm information;

and if the error between the first article information and the second article information is larger than an error threshold value, generating alarm information.

9. An article pickup management system, comprising:

the video acquisition device is used for acquiring video streams in the storage room;

the electronic equipment is communicated with the video acquisition device and is used for acquiring the video stream from the video acquisition device and identifying the characteristic information of the target object in the storage room from the video stream, wherein the characteristic information at least comprises face information; the electronic equipment is used for determining that the current article picking behavior is not compliant based on the characteristic information and generating alarm information.

10. A computer storage medium having stored thereon program instructions which, when executed, implement the item pickup management method of any one of claims 1 to 8.

Images