A method and system for monitoring a compact shelf, a terminal device and a storage medium

Abstract

The application relates to the warehouse technology field, in particular to a compact shelf monitoring method and system, terminal equipment and a storage medium. The method comprises the following steps: acquiring a taking and placing behavior picture corresponding to a target person; analyzing the taking and placing behavior picture, judging whether the article category corresponding to the taking and placing articles of the target person is consistent with the taking and placing permission of the target person; if not, associating the identity information of the target person with the taking and placing articles, and generating corresponding taking and placing permission abnormal warning information; if the face features corresponding to the face image do not meet the preset face feature standard, controlling the monitoring equipment to track and acquire a behavior action picture of the corresponding abnormal target person; associating the face image and the behavior action picture of the abnormal target person, and generating corresponding abnormal personnel intrusion warning information. The compact shelf monitoring method and system, terminal equipment and storage medium provided by the application can improve the safety of the taking and placing of the articles related to the compact shelf.

Description

Technical Field

[0001] This application relates to the field of warehousing technology, and in particular to a method, system, terminal equipment and storage medium for monitoring mobile shelving. Background Technology

[0002] Mobile shelving is a system used for storing and managing items or documents. It typically uses movable shelves to maximize storage space. Its design can be adjusted according to the user's needs to accommodate different items or documents of varying sizes and quantities. Mobile shelving is commonly found in offices, libraries, hospitals, museums, and commercial warehouses.

[0003] In practical applications, the items stored in mobile shelving units are usually very valuable. Without proper security measures, unauthorized personnel may maliciously access or steal sensitive items such as confidential documents. If such a situation occurs, the existing fixed monitoring equipment will have difficulty effectively recording and reporting the abnormal behavior, thereby reducing the security of retrieving items from the mobile shelving units. Summary of the Invention

[0004] To improve the security of retrieving and placing items in mobile shelving units, this application provides a mobile shelving monitoring method, system, terminal device, and storage medium.

[0005] Firstly, this application provides a method for monitoring mobile shelving units, comprising the following steps:

[0006] Acquire and identify item retrieval and placement instructions, and control the monitoring equipment to move to the corresponding mobile shelving coordinates;

[0007] Obtain the mobile shelving unit identifier within the target monitoring area corresponding to the coordinates of the mobile shelving unit;

[0008] If the mobile shelving identifier matches the mobile shelving coordinates, the corresponding target mobile shelving is opened according to the item retrieval and placement instruction, and a face image of the person within the target monitoring area is obtained;

[0009] If the facial features corresponding to the facial image meet the preset facial feature standards, then the item retrieval and placement permissions for the corresponding target person are generated based on the facial features.

[0010] Obtain the image of the picking and placing actions corresponding to the target personnel;

[0011] Analyze the image of the picking and placing behavior to determine whether the item category of the target person picking and placing the item matches the item picking and placing permissions of the target person.

[0012] If the target person does not correspond to the article category of the article taking and placing, and does not correspond to the article taking and placing permission of the target person, the identity information of the target person and the article taking and placing are associated, and corresponding taking and placing permission abnormal warning information is generated;

[0013] If the face feature corresponding to the face image does not meet the preset face feature standard, the monitoring device is controlled to track and acquire the behavior action picture of the corresponding abnormal target person;

[0014] The face image corresponding to the abnormal target person and the behavior action picture are associated, and corresponding abnormal personnel intrusion warning information is generated.

[0015] By using the above technical scheme, the monitoring device is moved to the corresponding dense shelf coordinate according to the user article taking and placing instruction before the target dense shelf is opened, which can improve the monitoring completeness of the dense shelf usage, and then the dense shelf identifier is matched and analyzed with the dense shelf coordinate after the monitoring device is in place, which can reduce the occurrence of the situation that the monitoring device does not move to the specified monitoring position due to system positioning indication error, further identify and analyze the face feature of the face image in the target monitoring area, which can reduce the possibility of unauthorized personnel taking and placing articles, improve the taking and placing safety of the dense shelf, and at the same time, through face recognition and article category confirmation of the valid authorized personnel, the operation efficiency and accuracy can be improved, and in addition, if an abnormal personnel intrusion is found, warning information is immediately generated, and the monitoring device is controlled to track and acquire the behavior action picture of the abnormal target person, so as to further confirm and control the risk. Since the monitoring device can accurately move to the monitoring area corresponding to the target dense shelf according to the specific article taking and placing instruction in advance, and track and monitor the analysis according to the target personnel identity and specific behavior action, the safety of the dense shelf related article taking and placing is improved.

[0016] Optionally, after the dense shelf identifier in the target monitoring area corresponding to the dense shelf coordinate is acquired, the following steps are further included:

[0017] If the dense shelf identifier matches the dense shelf coordinate, it is determined whether the dense shelf monitoring picture corresponding to the dense shelf identifier in the target monitoring area meets the preset monitoring standard;

[0018] If the dense shelf monitoring picture corresponding to the dense shelf identifier in the target monitoring area does not meet the preset monitoring standard, the monitoring adjustment control parameter corresponding to the dense shelf monitoring picture is generated according to the preset monitoring standard;

[0019] The monitoring device is controlled to adjust according to the monitoring adjustment control parameter.

[0020] By adopting the technical scheme, the monitoring equipment that does not meet the monitoring standard is controlled and adjusted according to the monitoring adjustment control parameter, so that abnormal problems existing in the monitoring process of the dense shelf can be found and corrected in time, and the accuracy of obtaining the dense shelf monitoring picture is improved.

[0021] Optionally, after judging whether the article category of the target personnel corresponding to the taking and placing article meets the article taking and placing permission corresponding to the target personnel, the method further comprises the following steps:

[0022] If the article category of the target personnel corresponding to the taking and placing article meets the article taking and placing permission corresponding to the target personnel, it is judged whether the article category of the taking and placing article meets the target article category corresponding to the article taking and placing instruction.

[0023] If the article category of the taking and placing article does not meet the target article category corresponding to the article taking and placing instruction, corresponding taking and placing classification prompt information is generated according to the target article category.

[0024] By adopting the technical scheme, the abnormal taking and placing behavior of the target personnel is prompted according to the taking and placing classification prompt information, so that the standardization of the target personnel taking and placing related articles is strengthened.

[0025] Optionally, after if the article category of the taking and placing article does not meet the target article category corresponding to the article taking and placing instruction, corresponding taking and placing classification prompt information is generated according to the target article category, the method further comprises the following steps:

[0026] If the taking and placing classification prompt information is not confirmed, the target taking and placing article corresponding to the target personnel and the dense shelf number corresponding to the target taking and placing article are obtained through the taking and placing behavior picture.

[0027] According to the target taking and placing article and the dense shelf number, an abnormal taking and placing trace record is generated.

[0028] By adopting the technical scheme, according to the abnormal taking and placing trace record, the abnormal taking and placing behavior of the target personnel can be effectively traced and the related articles can be timely classified and restored, so that the processing efficiency of the abnormal taking and placing problem in the use process of the dense shelf is improved.

[0029] Optionally, after if the face feature corresponding to the face image does not meet the preset face feature standard, the behavior action picture of the corresponding abnormal target personnel is controlled to be obtained by the monitoring equipment, the method further comprises the following steps:

[0030] The behavior action picture is analyzed to generate corresponding abnormal behavior action features.

[0031] If the abnormal behavior action features are multiple, each of the abnormal behavior action features is classified according to a preset abnormal behavior action standard to form a corresponding abnormal behavior action identification group.

[0032] By using the above technical solution, according to the abnormal behavior action identification group, the behavior action of the abnormal target person can be more intuitively analyzed, thereby improving the safety of the related article taking and placing of the compact shelf.

[0033] Optionally, if the abnormal behavior action features are multiple, the behavior action features are classified according to a preset abnormal behavior action standard to form a corresponding abnormal behavior action identification group, including the following steps:

[0034] If the abnormal behavior action features are multiple, each of the abnormal behavior action features is classified according to a preset abnormal behavior action standard, and a feature information acquisition instruction corresponding to each of the abnormal behavior action features is generated;

[0035] According to the feature information acquisition instruction, the abnormal article taking and placing and the abnormal compact shelf number corresponding to the abnormal behavior action features are acquired;

[0036] The abnormal behavior action features, the abnormal article taking and placing, and the abnormal compact shelf number are combined to form the corresponding abnormal behavior action identification group.

[0037] By using the above technical solution, according to the abnormal behavior action identification group, the abnormal situation caused by each specific abnormal behavior action feature can be accurately traced and confirmed, thereby improving the safety of the related article taking and placing of the compact shelf.

[0038] Optionally, after the abnormal article taking and placing and the abnormal compact shelf number corresponding to the abnormal behavior action features are acquired according to the feature information acquisition instruction, the following steps are further included:

[0039] It is judged whether there is an original taking and placing relationship between the abnormal article taking and placing and the abnormal compact shelf number;

[0040] If the original taking and placing relationship exists between the abnormal article taking and placing and the abnormal compact shelf number, a corresponding recovery indication mark is generated according to the abnormal article taking and placing and the abnormal compact shelf number;

[0041] If the original taking and placing relationship does not exist between the abnormal article taking and placing and the abnormal compact shelf number, a heterogeneous addition mark corresponding to the abnormal compact shelf number is generated according to the abnormal article taking and placing.

[0042] By adopting the technical scheme, whether there is an original taking and placing relationship between the current abnormal taking and placing of the article and the abnormal dense shelf number is judged, and then adaptive analysis and marking processing is made according to the specific relationship, thereby improving the safety processing efficiency of the dense shelf abnormal taking and placing problem.

[0043] In a second aspect, the application provides a dense shelf monitoring system, comprising:

[0044] A taking and placing instruction acquisition module is configured to acquire and identify an article taking and placing instruction, and control a monitoring device to move to a corresponding dense shelf coordinate;

[0045] A dense shelf identifier acquisition module is configured to acquire a dense shelf identifier in a target monitoring area corresponding to the dense shelf coordinate;

[0046] An instruction execution module is configured to open a target dense shelf corresponding to the article taking and placing instruction and acquire a face image in the target monitoring area if the dense shelf identifier matches the dense shelf coordinate;

[0047] A permission analysis module is configured to generate an article taking and placing permission of a target person according to a face feature corresponding to the face image if the face feature meets a preset face feature standard;

[0048] A behavior picture acquisition module is configured to acquire a taking and placing behavior picture corresponding to the target person;

[0049] A picture analysis module is configured to analyze the taking and placing behavior picture, and judge whether an article category of the article taken and placed by the target person meets the article taking and placing permission of the target person;

[0050] A first association module is configured to associate identity information of the target person and the article, and generate corresponding taking and placing permission abnormal warning information if the article category of the article taken and placed by the target person does not meet the article taking and placing permission of the target person;

[0051] A tracking and monitoring module is configured to control the monitoring device to track and acquire a behavior action picture of a corresponding abnormal target person if the face feature corresponding to the face image does not meet the preset face feature standard;

[0052] A second association module is configured to associate the face image and the behavior action picture of the abnormal target person, and generate corresponding abnormal person intrusion warning information.

[0053] By adopting the technical scheme, the monitoring device is controlled to move to the corresponding dense shelf coordinate according to the user's item taking and placing instruction through the taking and placing instruction acquisition module before the target dense shelf is opened, which can improve the monitoring completeness of the dense shelf usage, and then the dense shelf identifier is matched and analyzed with the dense shelf coordinate through the instruction execution module after the monitoring device is in place, which can reduce the occurrence of the situation that the monitoring device does not move to the specified monitoring position due to system positioning indication errors, and further, the face features of the face image in the target monitoring area are recognized and analyzed through the permission analysis module, which can reduce the possibility of unauthorized personnel taking and placing items, improve the taking and placing safety of the dense shelf, and at the same time, the face recognition and item category confirmation of the valid authorized personnel can reduce misoperation and misjudgment, improve operation efficiency and accuracy, and in addition, if an abnormal personnel intrusion is found, warning information is immediately generated, and the behavior action picture of the abnormal target personnel is tracked and acquired through the tracking and monitoring module to control the monitoring device, so as to further confirm and control the risk. Since the monitoring device can accurately move to the monitoring area corresponding to the target dense shelf according to the specific item taking and placing instruction in advance, and tracking and monitoring analysis is performed according to the target personnel identity and specific behavior action, the safety of the dense shelf related item taking and placing is improved.

[0054] In a third aspect, the present application provides a terminal device, which adopts the following technical scheme:

[0055] A terminal device includes a memory and a processor, the memory stores computer instructions capable of running on the processor, and when the processor loads and executes the computer instructions, the above-mentioned dense shelf monitoring method is adopted.

[0056] By adopting the above technical scheme, the above-mentioned dense shelf monitoring method generates computer instructions, which are stored in the memory to be loaded and executed by the processor, so that the terminal device is made of the memory and the processor, which is convenient to use.

[0057] In a fourth aspect, the present application provides a computer readable storage medium, which adopts the following technical scheme:

[0058] A computer readable storage medium stores computer instructions, and when the computer instructions are loaded and executed by a processor, the above-mentioned dense shelf monitoring method is adopted.

[0059] By adopting the above technical scheme, the above-mentioned dense shelf monitoring method generates computer instructions, which are stored in the computer readable storage medium to be loaded and executed by the processor, and the computer readable storage medium facilitates the readability and storage of the computer instructions.

[0060] In summary, the present application includes at least one of the following beneficial technical effects: before opening the target dense shelf, the monitoring device is first moved to the corresponding dense shelf coordinate according to the user's item taking and placing instructions, which can improve the monitoring completeness of the dense shelf usage, then after the monitoring device is in place, the dense shelf identification and dense shelf coordinate are matched and analyzed, which can reduce the occurrence of the monitoring device not moving to the specified monitoring position due to system positioning indication errors, further identifying and analyzing the face features of the face image in the target monitoring area can reduce the possibility of unauthorized personnel taking and placing items, improve the safety of taking and placing dense shelves, at the same time, through face recognition and item category confirmation of authorized personnel, can reduce misoperation and misjudgment, improve operation efficiency and accuracy, in addition, if an abnormal person intrudes, an alarm information is generated immediately, and the monitoring device is controlled to track and obtain the behavior action picture of the abnormal target person, in order to further confirm and control the risk, since the monitoring device can be accurately moved to the monitoring area corresponding to the target dense shelf according to the specific item taking and placing instructions, and the target personnel identity and specific behavior action are tracked and analyzed according to the situation, the safety of taking and placing dense shelves is improved. BRIEF DESCRIPTION OF DRAWINGS

[0061] Figure 1 is a flowchart of steps S101 to S109 in a dense shelf monitoring method provided by the present application;

[0062] Figure 2 is a flowchart of steps S201 to S203 in a dense shelf monitoring method provided by the present application;

[0063] Figure 3 is a flowchart of steps S301 to S302 in a dense shelf monitoring method provided by the present application;

[0064] Figure 4 is a flowchart of steps S401 to S402 in a dense shelf monitoring method provided by the present application;

[0065] Figure 5 is a flowchart of steps S501 to S502 in a dense shelf monitoring method provided by the present application;

[0066] Figure 6 is a flowchart of steps S601 to S603 in a dense shelf monitoring method provided by the present application;

[0067] Figure 7 is a flowchart of steps S701 to S703 in a dense shelf monitoring method provided by the present application;

[0068] Figure 8 is a module diagram of a dense shelf monitoring system provided by the present application;

[0069] BRIEF DESCRIPTION OF DRAWINGS

[0070] 1, take and put instruction acquisition module; 2, dense shelf identification acquisition module; 3, instruction execution module; 4, permission analysis module; 5, behavior picture acquisition module; 6, picture analysis module; 7, first correlation module; 8, tracking monitoring module; 9, second correlation module. DETAILED DESCRIPTION

[0071] The following will be described in detail in combination with the accompanying drawings Figures 1-8 The application is further described in detail.

[0072] The embodiment of the application discloses a dense shelf monitoring method, as shown in the figure, comprising the following steps: Figure 1

[0073] S101. Acquire and identify the item taking and placing instruction, and control the monitoring device to move to the corresponding dense shelf coordinate;

[0074] S102. Acquire the dense shelf identification in the target monitoring area corresponding to the dense shelf coordinate;

[0075] S103. If the dense shelf identification matches the dense shelf coordinate, open the corresponding target dense shelf according to the item taking and placing instruction, and acquire the face image in the target monitoring area;

[0076] S104. If the face feature corresponding to the face image meets the preset face feature standard, generate the item taking and placing permission of the corresponding target personnel according to the face feature;

[0077] S105. Acquire the taking and placing behavior picture of the target personnel;

[0078] S106. Analyze the taking and placing behavior picture, and judge whether the item category of the target personnel corresponding to the taking and placing item meets the item taking and placing permission of the target personnel;

[0079] S107. If the item category of the target personnel corresponding to the taking and placing item does not meet the item taking and placing permission of the target personnel, associate the identity information of the target personnel and the taking and placing item, and generate the corresponding taking and placing permission abnormal warning information;

[0080] S108. If the face feature corresponding to the face image does not meet the preset face feature standard, control the monitoring device to track and acquire the behavior action picture of the corresponding abnormal target personnel;

[0081] S109. Associate the face image and the behavior action picture of the abnormal target personnel, and generate the corresponding abnormal personnel intrusion warning information.

[0082] ​In step S101, the article taking and placing instruction is an opening instruction sent to the compact shelf according to the actual article taking and placing demand of the user and through the control terminal.

[0083] In actual application, the article storage position can be transmitted to the database of the remote control terminal through wireless scanner scanning during article shelving. The database can define the exclusive keyword of the shelved article according to the attribute of the article, and then form different category numbers according to the exclusive keyword, and then associate with the specific storage module number of the compact shelf, to generate the taking and placing instruction of each article and its storage compact shelf. The user can select and input the corresponding article taking and placing instruction on the remote control terminal interface according to the self taking and placing demand.

[0084] Secondly, in order to better monitor and shoot the compact shelf to be opened, the system controls the monitoring device to move to the corresponding monitoring and shooting position of the compact shelf, i.e. the compact shelf coordinate, before the compact shelf receives the article taking and placing instruction and identifies the article taking and placing instruction.

[0085] Specifically, a moving mechanism is arranged above the compact shelf, including a moving track, a boom, a mounting frame, a motor, a synchronous wheel, a driven wheel and a synchronous belt. The track is hoisted above the compact shelf by the boom, the synchronous wheel and the driven wheel are arranged in the grooves on both sides of the moving track, the synchronous belt connects the synchronous wheel and the driven wheel, the synchronous wheel is driven by the motor, the motor on both sides of the track is fixedly connected by the mounting frame, the rotating shaft of the driven wheel is fixed on the mounting frame, and the monitoring device is fixed on the mounting frame.

[0086] Among them, after the system identifies the article taking and placing instruction, it will analyze the article taking and placing instruction to generate a control signal for controlling the movement of the motor. The control signal can control the motor to drive the monitoring device to move to the specific position of the article storage compact shelf, i.e. the compact shelf coordinate. Among them, the system stores the plane coordinate, i.e. the compact shelf coordinate, formed according to the specific storage position of each type of article in the compact shelf. By identifying the article taking and placing instruction, the compact shelf coordinate corresponding to the specific article taking and placing can be obtained.

[0087] For example, the article taking and placing instruction is a taking instruction of document A, wherein the document A is stored in row 1, column 1 of the compact shelf, and the corresponding coordinate of the compact shelf is (1, 1). After the system identifies the taking instruction of document A, it sends a control signal to the motor to move to the compact shelf coordinate (1, 1). The motor drives the monitoring device to move to the position of row 1, column 1 of the compact shelf according to the control signal.

[0088] Specifically, the compact shelf can also be controlled by a computer or other automatic equipment, which can automatically monitor the capacity, position and operation of the shelf, and mark or record the operation. The operator can obtain the required article or file by operating the equipment or other manual method.

[0089] In steps S102 to S103, the shelf identifier refers to the identification information provided on the shelf, and the shelf identifier has a one-to-one correspondence with the shelf coordinates. The purpose is to verify the positioning of the target monitoring area after the monitoring device is in place.

[0090] The shelf identifier can be set as a positioning identification code. After the monitoring device reaches the specified position, it begins to take pictures. If the monitoring device corresponding to the monitoring area, i.e., the target monitoring area, appears a shelf identifier corresponding to the shelf coordinates corresponding to it, it can be determined that the current shelf identifier matches the shelf coordinates. Then the system opens the corresponding target shelf according to the above item taking and placing instructions, and acquires the face image of the person to be present in the target monitoring area.

[0091] Furthermore, if the shelf identifier does not match the shelf coordinates, it means that the monitoring device control signal sent by the system is incorrect or the corresponding movement mechanism control of the monitoring device is abnormal, resulting in the monitoring device being brought to other shelf coordinate positions. The system then re-sends the control signal corresponding to the item taking and placing instructions to the movement mechanism, i.e., the motor, of the monitoring device to control the movement of the monitoring device again.

[0092] In step S104, in order to further improve the safety of the shelf taking and placing, the system internally stores the face feature information of authorized personnel, i.e., the preset face feature standard. If the face feature corresponding to the face image in the target monitoring area meets the preset face feature standard, it means that the target personnel is authorized personnel. The judgment of whether the face feature corresponding to the face image in the target monitoring area meets the preset face feature standard can be realized through face recognition technology.

[0093] Further, in order to further limit the taking and placing authority of authorized personnel and improve the safety of the shelf use, the taking and placing authority of the target personnel is further acquired and identified on the basis that the current target personnel meets the authorization. The item taking and placing authority refers to the relevant authority of the corresponding personnel for taking and placing according to the different attributes of the items.

[0094] For example, in a hospital application scenario, the files stored in the shelf are divided into clinical files and non-clinical files. Clinical staff have the taking and placing authority of clinical files, and non-clinical staff have the taking and placing authority of non-clinical files.

[0095] In steps S105 to S106, in order to further monitor the behavior of the target personnel, the taking and placing behavior of the target personnel is acquired and analyzed to generate the behavior characteristics of the target personnel, which include the taking and placing behavior of the target personnel in the shelf area. Then, through the above taking and placing behavior, it is determined whether the item category of the target personnel taking and placing the items meets the corresponding item taking and placing authority.

[0096] Wherein, the determination of whether the target personnel corresponds to the taking and placing of the article category of the article is consistent with the article taking and placing authority corresponding to the target personnel can be realized by identifying whether the article category of the article taken and placed by the target personnel or the specific location of the dense shelf corresponding to the taking and placing behavior is corresponding to the article taking and placing authority of the target personnel. The article category of the article taken and placed by the target personnel can be confirmed by identifying the text features displayed on the taking and placing article in the monitoring picture, or by identifying the number of the specific dense shelf corresponding to the taking and placing behavior of the target personnel.

[0097] In step S107, if the target personnel corresponds to the taking and placing of the article category of the article is not consistent with the article taking and placing authority corresponding to the target personnel, it means that the current target personnel has implemented a behavior different from the article taking and placing authority. In order to regulate and backup the behavior of the target personnel, the identity information of the target personnel and the article taken and placed by the target personnel are associated to generate corresponding taking and placing authority abnormal warning information. Through the taking and placing authority abnormal warning information, the current target personnel can be reminded to pay attention, and the abnormal article taking and placing problem can be effectively traced back.

[0098] Furthermore, if the target personnel corresponds to the taking and placing of the article category of the article is consistent with the article taking and placing authority corresponding to the target personnel, it means that the current target personnel correctly exercises the corresponding article taking and placing authority. In order to improve the safety of the dense shelf related stored article taking and placing, the behavior picture of the target personnel in the target monitoring area is monitored and photographed in real time.

[0099] In steps S108 to S109, if the face feature corresponding to the face image of the current target personnel does not meet the preset face feature standard, it means that the target personnel is not authorized. In order to effectively monitor and record the abnormal intrusion situation, the monitoring device is controlled to track and obtain the behavior action picture of the abnormal target personnel. The behavior action picture includes all behavior actions of the abnormal target personnel in the dense shelf monitoring area. The face image and behavior action picture corresponding to the abnormal target personnel are associated to generate corresponding abnormal personnel intrusion warning information. Through the abnormal personnel intrusion warning information, the abnormal target personnel can be warned, and it is also helpful for the relevant management personnel to effectively trace back the specific personnel information and intrusion behavior in the abnormal intrusion situation.

[0100] Wherein, the control of the monitoring device to track and obtain the behavior action picture of the abnormal target personnel can be realized by an automatic tracking monitoring system and an AI intelligent algorithm. After the monitoring device determines that the current target personnel is an abnormal target personnel without authorization, the abnormal target personnel is immediately marked as a tracking monitoring target. The action image of the target personnel is zoomed in and enlarged for tracking, and the action, position and related action of the target personnel are recorded in real time.

[0101] The dense shelf monitoring method provided in the embodiment can improve the monitoring completeness of the use of the dense shelf, and can reduce the occurrence of the situation that the monitoring device does not move to the specified monitoring position due to the positioning indication error of the system. Further, the face features of the face image in the target monitoring area are identified and analyzed, which can reduce the possibility of unauthorized personnel taking and placing articles, and improve the safety of taking and placing articles in the dense shelf. Meanwhile, the face recognition and article category confirmation of the valid authorized personnel can reduce the misoperation and misjudgment, and improve the operation efficiency and accuracy. In addition, if an abnormal personnel intrudes, an alarm information is immediately generated, and the monitoring device is controlled to track and acquire the behavior action picture of the abnormal target personnel, so as to further confirm and control the risk. Since the monitoring device can accurately move to the monitoring area corresponding to the target dense shelf according to the specific article taking and placing instruction in advance, and the target personnel identity and specific behavior action are tracked and analyzed according to the situation, the safety of taking and placing articles in the dense shelf is improved.

[0102] In one of the implementation manners of the embodiment, as shown in Figure 2 the step S102 of acquiring the dense shelf identification corresponding to the target monitoring area of the dense shelf coordinate further includes the following steps:

[0103] S201. If the dense shelf identification matches the dense shelf coordinate, it is judged whether the dense shelf monitoring picture corresponding to the dense shelf identification in the target monitoring area meets the preset monitoring standard.

[0104] S202. If the dense shelf monitoring picture corresponding to the dense shelf identification in the target monitoring area does not meet the preset monitoring standard, the monitoring adjustment control parameter corresponding to the dense shelf monitoring picture is generated according to the preset monitoring standard.

[0105] S201. The monitoring device is controlled to be adjusted according to the monitoring adjustment control parameter.

[0106] In the step S201, in order to reduce the occurrence of the situation that the monitoring picture is blocked or the monitoring picture is not clear due to some obstacles after the monitoring device is in place, and the target dense shelf cannot be monitored, on the basis that the dense shelf identification matches the dense shelf coordinate, it is further judged whether the dense shelf monitoring picture corresponding to the dense shelf identification in the target monitoring area corresponding to the current monitoring device meets the preset monitoring standard. The preset monitoring standard refers to the relevant standard specified in advance for the monitoring picture of the monitoring device. The dense shelf monitoring picture corresponding to the dense shelf identification refers to the target dense shelf area that needs to be monitored corresponding to the article taking and placing instruction.

[0107] In steps S202 to S203, if the shelf monitoring picture corresponding to the shelf mark in the target monitoring area does not meet the preset monitoring standard, the corresponding monitoring adjustment control parameter is generated according to the actual situation of the current shelf monitoring picture and the preset monitoring standard corresponding thereto, and then the monitoring device is adaptively adjusted according to the monitoring adjustment control parameter.

[0108] For example, after the monitoring device is positioned, it is determined that the exposure value corresponding to the target monitoring area does not meet the preset monitoring standard due to indoor light, that is, the brightness of the shelf monitoring picture is not enough, and then the system adaptively adjusts the exposure value of the monitoring device according to the actual environmental brightness and light and the preset monitoring standard, so as to control the brightness of the monitoring picture of the monitoring device to be in a moderate range.

[0109] For another example, after the monitoring device is positioned, it is determined that there is an occlusion in the shelf monitoring picture, and then the system generates a shooting angle adjustment control parameter of the monitoring device according to the angle of the current monitoring area and the special requirements of the preset monitoring standard, and the monitoring device is adaptively adjusted according to the shooting angle adjustment control parameter.

[0110] Further, if the shelf monitoring picture corresponding to the shelf mark in the target monitoring area meets the preset monitoring standard, the system continues to obtain and analyze the monitoring shooting parameters of the monitoring device in real time according to the preset monitoring standard.

[0111] The shelf monitoring method provided in the embodiment can timely find and correct abnormal problems existing in the process of monitoring the shelf, and improve the accuracy of obtaining the shelf monitoring picture.

[0112] In one of the embodiments of the present embodiment, as shown in Figure 3 After step S106, that is, analyzing the taking and placing behavior picture, it is further determined whether the target personnel corresponds to the taking and placing permission of the target personnel according to the taking and placing behavior picture.

[0113] S301. If the target personnel corresponds to the taking and placing permission of the target personnel, it is determined whether the taking and placing permission of the target personnel corresponds to the target personnel according to the taking and placing behavior picture.

[0114] S302. If the taking and placing permission of the target personnel does not correspond to the target personnel, corresponding taking and placing classification prompt information is generated according to the target personnel.

[0115] In steps S301-S302, if the target personnel corresponds to the article category of the article to be taken or placed in accordance with the article taking or placing authority of the target personnel, in order to improve the safety and standardization of the article taking or placing of the compact shelf, it is determined whether the article category of the article to be taken or placed by the target personnel corresponds to the target article category corresponding to the article taking or placing instruction, which refers to the instruction of the specific article to be taken or placed by the target personnel before the article taking or placing.

[0116] Further, if the article category of the article to be taken or placed by the target personnel does not correspond to the target article category corresponding to the article taking or placing instruction, it indicates that the current article taking or placing by the target personnel may not correspond due to negligence, and then corresponding taking or placing classification prompt information is generated according to the target article category, and the target personnel can check the article to be taken or placed through the taking or placing classification prompt information.

[0117] Furthermore, if the article category of the article to be taken or placed corresponds to the target article category corresponding to the article taking or placing instruction, in order to standardize the article taking or placing process, the taking or placing behavior picture of the target personnel is continuously acquired and analyzed in real time.

[0118] The compact shelf monitoring method provided by the embodiment can prompt the abnormal taking or placing behavior of the target personnel according to the taking or placing classification prompt information, thereby strengthening the standardization of the target personnel in taking or placing related articles.

[0119] In one embodiment of the present embodiment, as shown in Figure 4 the article taking or placing instruction, the following steps are further included after the corresponding taking or placing classification prompt information is generated according to the target article category:

[0120] S401. If the taking or placing classification prompt information is not confirmed, the target article to be taken or placed by the target personnel and the compact shelf number corresponding to the target article to be taken or placed are acquired through the taking or placing behavior picture;

[0121] S402. According to the target article to be taken or placed and the compact shelf number, an abnormal taking or placing trace record is generated.

[0122] In steps S401-S402, if the taking or placing classification prompt information generated by the system is not confirmed, it indicates that the current target personnel does not receive the taking or placing classification prompt information due to some special reasons, and in order to record the abnormal behavior of the target personnel, the target article to be taken or placed by the target personnel and the compact shelf number corresponding to the target article to be taken or placed are acquired through the taking or placing behavior picture corresponding to the current target personnel, and according to the target article to be taken or placed and the compact shelf number, an abnormal taking or placing trace record is generated. The relevant management personnel can trace the target personnel according to the above abnormal taking or placing trace record, and effectively and reasonably position the related article to be taken or placed.

[0123] Further, if the current taking and placing classification prompt information has been confirmed, it indicates that the current target person has noticed the prompt information. In order to strengthen the monitoring of the overall taking and placing behavior of the target person, the system will continue to acquire and analyze the taking and placing behavior picture of the target person in real time.

[0124] The dense shelf monitoring method provided by the embodiment can effectively trace the abnormal taking and placing behavior of the target person and timely classify and restore the related articles according to the abnormal taking and placing trace record, thereby improving the processing efficiency of the abnormal taking and placing problem in the use process of the dense shelf.

[0125] In one of the embodiments of the present embodiment, as shown in Figure 5 If the face feature corresponding to the face image does not meet the preset face feature standard, the control monitoring device further includes the following steps after tracking and acquiring the behavior action picture of the corresponding abnormal target person in step S108.

[0126] S501. Analyzing the behavior action picture to generate corresponding abnormal behavior action features;

[0127] S502. If the abnormal behavior action features are multiple, classifying each abnormal behavior action feature according to the preset abnormal behavior action standard to form a corresponding abnormal behavior action identification group.

[0128] In step S501, in order to track and monitor the behavior of the abnormal intruder, i.e. the abnormal target person, the behavior action picture of the abnormal target person is analyzed to generate corresponding abnormal behavior action features. The abnormal behavior action features include the movement track of the abnormal target person in the dense shelf area and the specific action performed on the dense shelf.

[0129] In step S502, if the abnormal behavior action features are multiple, it indicates that multiple specific behavior actions are performed. For example, the abnormal target person steals the articles stored in different dense shelf numbers, or exchanges the articles stored in different dense shelf numbers.

[0130] Further, in order to effectively record and feedback the above abnormal behavior action features, each abnormal behavior action feature is classified according to the preset abnormal behavior action standard to form a corresponding abnormal behavior action identification group.

[0131] The preset abnormal behavior action standard refers to an abnormal behavior judgment standard preset by the monitoring and identification system. For example, an abnormal target person changes the positions of articles stored in different dense shelves, which is an abnormal change of positions of different types of articles stored in positions classified according to the preset abnormal behavior action standard. The abnormal behavior action identification group refers to a record set formed according to the same abnormal behavior action feature, and the purpose is to more effectively identify and analyze the abnormal behavior action features of the abnormal target person.

[0132] The dense shelf monitoring method provided by the embodiment can more intuitively analyze the behavior actions of the abnormal target person according to the abnormal behavior action identification group, thereby improving the safety of taking and placing articles related to the dense shelf.

[0133] In one of the embodiments of the present embodiment, as shown in Figure 6 If the abnormal behavior action feature is multiple, the preset abnormal behavior action standard is used to classify each abnormal behavior action feature, and corresponding feature information acquisition instructions of each abnormal behavior action feature are generated.

[0134] S601. If the abnormal behavior action feature is multiple, the preset abnormal behavior action standard is used to classify each abnormal behavior action feature, and corresponding feature information acquisition instructions of each abnormal behavior action feature are generated.

[0135] S602. According to the feature information acquisition instruction, the abnormal behavior action feature corresponding abnormal taking and placing articles and abnormal dense shelf number are obtained.

[0136] S603. The corresponding abnormal behavior action identification group is formed by combining the abnormal behavior action feature, the abnormal taking and placing articles and the abnormal dense shelf number.

[0137] In steps S601 to S602, in order to effectively record and trace the taking and placing article information caused by multiple abnormal behavior action features, the preset abnormal behavior action standard is used to classify each abnormal behavior action feature, and corresponding feature information acquisition instructions of each abnormal behavior action feature are generated. Then, according to the feature information acquisition instruction, the abnormal behavior action feature corresponding abnormal taking and placing articles and abnormal dense shelf number are obtained.

[0138] For example, the abnormal behavior action feature is abnormal change of positions of different types of articles stored in positions and storage article repacking. Then, the system classifies the above abnormal behavior action features according to the preset abnormal behavior action standard, generates feature information acquisition instructions of abnormal change of positions of different types of articles stored in positions and storage article repacking, and obtains taking and placing article information, i.e., abnormal taking and placing articles, and dense shelf numbers corresponding to the taking and placing articles before and after the change of positions of the taking and placing articles, through the feature information acquisition instruction of abnormal change of positions of different types of articles stored in positions.

[0139] In step S603, the abnormal behavior action features, the abnormal taken and placed articles, and the abnormal rack numbers are combined to form an abnormal behavior action identification group, so that the relevant management personnel can more intuitively and effectively trace the behavior performed by the abnormal target personnel and the article information involved in the behavior.

[0140] The rack monitoring method provided in the embodiment can accurately trace and confirm the abnormal situation caused by each specific abnormal behavior action feature, thereby improving the safety of taking and placing articles related to the rack.

[0141] In one of the embodiments of the present embodiment, as shown in Figure 7 After step S602, i.e., obtaining the abnormal taken and placed articles and the abnormal rack numbers corresponding to the abnormal behavior action features according to the feature information acquisition instruction, the following steps are further included:

[0142] S701. Determine whether there is an original taking and placing relationship between the abnormal taken and placed articles and the abnormal rack numbers;

[0143] S702. If there is an original taking and placing relationship between the abnormal taken and placed articles and the abnormal rack numbers, generate a corresponding recovery indication mark according to the abnormal taken and placed articles and the abnormal rack numbers;

[0144] S703. If there is no original taking and placing relationship between the abnormal taken and placed articles and the abnormal rack numbers, generate an abnormal type addition mark corresponding to the abnormal rack number according to the abnormal taken and placed articles.

[0145] In step S701, in order to effectively and accurately recover the abnormal taken and placed articles, it is determined whether there is an original taking and placing relationship between the abnormal taken and placed articles and the abnormal rack numbers. The original taking and placing relationship refers to that the taking and placing of the abnormal taken and placed articles are directed to a specific abnormal rack number.

[0146] For example, the abnormal target personnel exchanges the part A article in the rack numbered 1 with the part B article in the rack numbered 2, and implements a package exchange between the C article carried by the abnormal target personnel and the D article in the rack numbered 3. At this time, the abnormal taken and placed articles are the A article, the B article, the C article, and the D article. The A article and the B article have an original taking and placing relationship with the rack numbered 1 and the rack numbered 2, and the C article does not have an original taking and placing relationship with the rack numbered 3.

[0147] In step S702, if there is an original taking and placing relationship between the abnormal taking and placing article and the abnormal dense shelf number, in order to facilitate the tracing of the original storage location of the abnormal taking and placing article, a corresponding recovery indication mark is generated according to the abnormal taking and placing article and the abnormal dense shelf number. For example, a corresponding exchange recovery indication mark is generated according to the number 1 dense shelf and the A article, and according to the exchange recovery indication mark, the original storage location of the A article on the dense shelf can be clearly known.

[0148] In step S703, if there is no original taking and placing relationship between the abnormal taking and placing article and the abnormal dense shelf number, in order to facilitate the differentiation from the abnormal taking and placing article and the abnormal dense shelf number with the original taking and placing relationship, an alien addition mark corresponding to the abnormal dense shelf number is generated according to the abnormal taking and placing article. For example, a drop-off alien addition mark corresponding to the number 3 dense shelf is generated according to the C article, and according to the alien addition mark, it can be known that the number 3 dense shelf has a switching situation, wherein the C article is an alien addition, and the D article is an original storage.

[0149] The dense shelf monitoring method provided by the embodiment judges whether there is an original taking and placing relationship between the current abnormal taking and placing article and the abnormal dense shelf number, and then makes adaptive analysis and marking processing according to the specific relationship, thereby improving the safety processing efficiency of the dense shelf abnormal taking and placing problem.

[0150] The embodiment of the application discloses a dense shelf monitoring system, as shown in the figure, comprising: Figure 8 As shown in the figure, comprising:

[0151] The taking and placing instruction acquisition module 1 is used for acquiring and identifying the article taking and placing instruction, and controlling the monitoring device to move to the corresponding dense shelf coordinate;

[0152] The dense shelf identification acquisition module 2 is used for acquiring the dense shelf identification in the target monitoring area corresponding to the dense shelf coordinate;

[0153] The instruction execution module 3 is used for opening the corresponding target dense shelf according to the article taking and placing instruction, and acquiring the face image in the target monitoring area, if the dense shelf identification matches the dense shelf coordinate;

[0154] The permission analysis module 4 is used for generating the article taking and placing permission of the corresponding target personnel according to the face feature, if the face feature corresponding to the face image meets the preset face feature standard;

[0155] The behavior picture acquisition module 5 is used for acquiring the taking and placing behavior picture corresponding to the target personnel;

[0156] The picture analysis module 6 is used for analyzing the taking and placing behavior picture, and judging whether the article category of the taking and placing article corresponding to the target personnel meets the article taking and placing permission of the target personnel;

[0157] The first association module 7 is configured to associate the identity information of the target person with the taking and placing of the article, and generate taking and placing permission abnormality warning information, if the article category corresponding to the taking and placing of the article by the target person does not conform to the taking and placing permission corresponding to the target person.

[0158] The tracking and monitoring module 8 is configured to control the monitoring device to track and acquire the behavior action picture of the abnormal target person, if the face feature corresponding to the face image does not conform to the preset face feature standard.

[0159] The second association module 9 is configured to associate the face image and the behavior action picture of the abnormal target person, and generate abnormal person intrusion warning information.

[0160] The dense shelf monitoring system provided in the embodiment can improve the monitoring completeness of the use of the dense shelf, and can reduce the occurrence of the situation that the monitoring device does not move to the specified monitoring position due to the positioning indication error of the system. Further, the face feature of the face image in the target monitoring area can be identified and analyzed by the permission analysis module 4, which can reduce the possibility of taking and placing articles by unauthorized personnel, and improve the taking and placing safety of the dense shelf. Meanwhile, the face recognition and article category confirmation of the valid authorized personnel can reduce the misoperation and misjudgment, and improve the operation efficiency and accuracy. In addition, if an abnormal person intrusion is found, warning information is immediately generated, and the tracking and monitoring module 8 controls the monitoring device to track and acquire the behavior action picture of the abnormal target person, so as to further confirm and control the risk. Since the monitoring device can accurately move to the monitoring area corresponding to the target dense shelf according to the specific article taking and placing instruction in advance, and can track and monitor according to the identity of the target person and the specific behavior action, the safety of the taking and placing of the articles related to the dense shelf is improved.

[0161] It should be noted that the dense shelf monitoring system provided in the embodiment also includes various modules and / or corresponding sub-modules corresponding to the logical functions or logical steps of any one of the above dense shelf monitoring methods, which achieve the same effect as the various logical functions or logical steps, and will not be repeated here.

[0162] The embodiment of the application also discloses a terminal device, which comprises a memory, a processor, and computer instructions stored in the memory and capable of running on the processor. When the processor executes the computer instructions, any one of the dense shelf monitoring methods in the above embodiments is adopted.

[0163] The terminal device can be a computer device such as a desktop computer, a notebook computer or a cloud server, and the terminal device includes but is not limited to a processor and a memory. For example, the terminal device can also include an input / output device, a network access device and a bus.

[0164] The processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), programmable logic devices (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, and the present application is not limited thereto.

[0165] The memory can be an internal storage unit of the terminal device, such as a hard disk or a memory of the terminal device, or an external storage device of the terminal device, such as a plug-in hard disk, a smart memory card (SMC), a secure digital card (SD) or a flash memory card (FC) provided on the terminal device. The memory can also be a combination of the internal storage unit and the external storage device of the terminal device. The memory is used to store computer instructions and other instructions and data required by the terminal device. The memory can also be used to temporarily store data that has been output or will be output, and the present application is not limited thereto.

[0166] The terminal device stores any one of the shelf monitoring methods in the above embodiments in the memory of the terminal device, and loads and executes the method on the processor of the terminal device, which is convenient to use.

[0167] The computer readable storage medium stores computer instructions, and when the computer instructions are executed by the processor, any one of the shelf monitoring methods in the above embodiments is used.

[0168] The computer instructions can be stored in the computer readable medium, and the computer instructions include computer instruction codes in the form of source code, object code, executable files or some middleware, etc. The computer readable medium includes any entity or device, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc. that can carry computer instruction codes. It should be noted that the computer readable medium includes but is not limited to the above components.

[0169] The rack monitoring method in any of the above embodiments is stored in the computer readable storage medium by the computer readable storage medium, and is loaded and executed on the processor to facilitate storage and application of the method.

[0170] The above are preferred embodiments of the application, and do not limit the protection scope of the application, so: any equivalent changes made according to the structure, shape, principle of the application should be covered within the protection scope of the application.

Claims

1. A method for monitoring mobile shelving units, characterized in that, The method comprises the following steps: acquiring and identifying an article taking and placing instruction, and controlling a monitoring device to move to a corresponding compact shelf coordinate; acquiring a compact shelf identifier in a target monitoring area corresponding to the compact shelf coordinate; if the compact shelf identifier matches the compact shelf coordinate, opening a target compact shelf corresponding to the article taking and placing instruction, and acquiring a face image in the target monitoring area; if a face feature corresponding to the face image meets a preset face feature standard, indicating that a current target person meets an authorization basis, and acquiring and identifying an article taking and placing authority of the target person, wherein the article taking and placing authority refers to relevant authorities of corresponding persons for taking and placing according to different article category attributes; acquiring a taking and placing behavior picture of the target person; analyzing the taking and placing behavior picture to determine whether an article category of the article taken and placed by the target person meets the article taking and placing authority of the target person; if the article category of the article taken and placed by the target person does not meet the article taking and placing authority of the target person, associating identity information of the target person with the article taken and placed to generate corresponding article taking and placing authority abnormality warning information; if the face feature corresponding to the face image does not meet the preset face feature standard, controlling the monitoring device to track and acquire a behavior action picture of a corresponding abnormal target person; associating the face image and the behavior action picture of the abnormal target person to generate corresponding abnormal person intrusion warning information.

2. The method of claim 1, wherein, After the step of acquiring the compact shelf identifier in the target monitoring area corresponding to the compact shelf coordinate, the following step is further included: if the compact shelf identifier matches the compact shelf coordinate, determining whether a compact shelf monitoring picture corresponding to the compact shelf identifier in the target monitoring area meets a preset monitoring standard; if the compact shelf monitoring picture corresponding to the compact shelf identifier in the target monitoring area does not meet the preset monitoring standard, generating a monitoring adjustment control parameter corresponding to the compact shelf monitoring picture according to the preset monitoring standard; controlling the monitoring device to adjust according to the monitoring adjustment control parameter.

3. The method of claim 1, wherein the step of detecting the presence of the product comprises the step of: After the step of analyzing the taking and placing behavior picture to determine whether the article category of the article taken and placed by the target person meets the article taking and placing authority of the target person, the following step is further included: ​ if the article category of the article taken and placed by the target person meets the article taking and placing authority of the target person, determining whether the article category of the article taken and placed meets a target article category corresponding to the article taking and placing instruction; if the article category of the article taken and placed does not meet the target article category corresponding to the article taking and placing instruction, generating corresponding taking and placing classification prompt information according to the target article category.

4. The method of claim 3, wherein the step of detecting the presence of the product comprises the step of: After the step of generating the taking and placing classification prompt information according to the target article category if the article category of the article taken and placed does not meet the target article category corresponding to the article taking and placing instruction, the following step is further included: ​ If the taking and placing classification prompt information is not confirmed, the target taking and placing object corresponding to the target personnel and the dense shelf number corresponding to the target taking and placing object are acquired through the taking and placing behavior picture; According to the target taking and placing object and the dense shelf number, an abnormal taking and placing trace record is generated.

5. The method of claim 1, wherein, If the face feature corresponding to the face image does not conform to the preset face feature standard, the monitoring device is further controlled to track and acquire a behavior action picture of a corresponding abnormal target personnel, and the behavior action picture is analyzed to generate a corresponding abnormal behavior action feature. If the abnormal behavior action feature is multiple, the abnormal behavior action features are classified according to a preset abnormal behavior action standard to form a corresponding abnormal behavior action identification group. If the abnormal behavior action feature is multiple, the abnormal behavior action features are classified according to a preset abnormal behavior action standard to form a corresponding abnormal behavior action identification group.

6. The method of claim 5, wherein the step of detecting the presence of the product comprises the step of: If the abnormal behavior action feature is multiple, the abnormal behavior action features are classified according to a preset abnormal behavior action standard to form a corresponding abnormal behavior action identification group. ​ According to the feature information acquisition instruction, an abnormal taking and placing object and an abnormal dense shelf number corresponding to the abnormal behavior action feature are acquired. The abnormal behavior action feature, the abnormal taking and placing object, and the abnormal dense shelf number are combined to form the corresponding abnormal behavior action identification group. After the feature information acquisition instruction is acquired, the abnormal behavior action feature, the abnormal taking and placing object, and the abnormal dense shelf number are further acquired.

7. The method of claim 6, wherein the step of detecting the presence of the product comprises the step of: It is judged whether there is an original taking and placing relationship between the abnormal taking and placing object and the abnormal dense shelf number. ​ If the abnormal taking and placing object and the abnormal dense shelf number have the original taking and placing relationship, a corresponding restoration indication mark is generated according to the abnormal taking and placing object and the abnormal dense shelf number. If the abnormal taking and placing object and the abnormal dense shelf number do not have the original taking and placing relationship, a heterogeneous addition identification corresponding to the abnormal dense shelf number is generated according to the abnormal taking and placing object. It includes:

8. A shelving monitoring system, characterized by A taking and placing instruction acquisition module (1) is used to acquire and identify an object taking and placing instruction, and control a monitoring device to move to a corresponding dense shelf coordinate; A dense shelf identification acquisition module (2) is used to acquire a dense shelf identification in a target monitoring area corresponding to the dense shelf coordinate; An instruction execution module (3) is used to open a corresponding target dense shelf according to the object taking and placing instruction if the dense shelf identification matches the dense shelf coordinate, and acquire a face image in the target monitoring area; An authority analysis module (4) is used to determine that a current target personnel conforms to an authorized basis if a face feature corresponding to the face image conforms to a preset face feature standard, and to acquire and identify an object taking and placing authority of the target personnel, wherein the object taking and placing authority refers to relevant authorities of corresponding personnel for taking and placing according to different object category attributes. ​ The behavior picture acquisition module (5) is configured to acquire a taking and placing behavior picture corresponding to the target person; The picture analysis module (6) is configured to analyze the taking and placing behavior picture, and determine whether the article category corresponding to the taking and placing article of the target person conforms to the article taking and placing permission corresponding to the target person; The first association module (7) is configured to associate the identity information of the target person and the taking and placing article, and generate corresponding taking and placing permission abnormality warning information, if the article category corresponding to the taking and placing article of the target person does not conform to the article taking and placing permission corresponding to the target person; The tracking and monitoring module (8) is configured to control the monitoring device to track and acquire a behavior action picture of the corresponding abnormal target person, if the face feature corresponding to the face image does not conform to the preset face feature standard; The second association module (9) is configured to associate the face image and the behavior action picture corresponding to the abnormal target person, and generate corresponding abnormal person intrusion warning information. 9.A terminal device, comprising a memory and a processor, characterized in that, The memory stores computer instructions capable of running on the processor, and the processor loads and executes the computer instructions.

10. A computer readable storage medium having stored therein computer instructions, wherein, The computer instructions are loaded and executed by the processor, and a shelf monitoring method according to any one of claims 1 to 7 is adopted.

Images