Banknote adding process detection method and device, computer device and readable storage medium

Abstract

The application relates to a banknote adding process detection method and device, computer equipment and a computer readable storage medium. The opening and closing states of banknote box doors in a banknote adding room and the number of people in the banknote adding room are obtained based on monitoring data collected by a camera arranged in the banknote adding room. Whether the banknote adding process of the banknote adding room is compliant is judged according to the opening and closing states of the banknote box doors and the number of people in the banknote adding room. The application only obtains the opening and closing states of the banknote box doors and the number of people in the banknote adding room based on the monitoring data collected by the camera arranged in the banknote adding room, greatly simplifies installation and deployment requirements, and effectively reduces the installation and deployment cost of the banknote adding process detection.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent monitoring, in particular to a banknote adding process detection method and device, computer equipment and a computer readable storage medium. BACKGROUND

[0002] In the financial industry, the security of the ATM banknote adding room is particularly important. For the banknote adding process, the bank has relevant rules that require the number of people in the banknote adding process to meet the set requirements and require the banknote case door to be in the fully open state throughout the banknote adding process to ensure that the banknote adding process is fully transparent and that the banknote adding staff play a mutual supervision role.

[0003] In the prior art, a pressure sensor is arranged on the banknote case door to obtain the opening and closing state of the banknote case door. The arrangement of the pressure sensor will additionally increase the detection installation and deployment cost and the workload of the bank system joint debugging, resulting in the problem of high banknote adding process detection installation and deployment cost in the prior art. SUMMARY

[0004] Therefore, it is necessary to provide a banknote adding process detection method, device, computer equipment and computer readable storage medium to solve the problem of high banknote adding process detection installation and deployment cost in the related art.

[0005] In a first aspect, the embodiments of the present application implement a banknote adding process detection method for detecting whether the banknote adding process in the banknote adding room is compliant. The method comprises the following steps:

[0006] Based on the monitoring data collected by the camera arranged inside the banknote adding room, the opening and closing state of the banknote case door in the banknote adding room and the number of people in the banknote adding room are obtained.

[0007] According to the opening and closing state of the banknote case door and the number of people in the banknote adding room, it is judged whether the banknote adding process in the banknote adding room is compliant.

[0008] In some embodiments, the opening and closing state of the banknote case door includes a fully open state, a half open state and a closed state.

[0009] In some embodiments, the opening and closing state of the banknote case door in the banknote adding room is obtained based on the monitoring data collected by the camera arranged inside the banknote adding room, comprising the following steps:

[0010] The feature extraction is performed on the area where the banknote case door is located in the real-time video frame captured by the camera, and the extracted features are compared with the picture features of the preset banknote case door pictures in different opening and closing states.

[0011] According to the comparison result, the opening and closing state of the banknote case door is determined.

[0012] In some embodiments, the extracted features are compared with preset features of the picture of the cash box door in different switch states, and the switch state of the cash box door is determined according to the comparison result, including the following steps:

[0013] The extracted features are compared with the features of the picture of the cash box door in the closed state and the half-open state.

[0014] If the similarity of the extracted features and the features of the picture of the cash box door in the closed state exceeds a set threshold, it is determined that the cash box door is in the closed state.

[0015] If the similarity of the extracted features and the features of the picture of the cash box door in the half-open state exceeds the set threshold, it is determined that the cash box door is in the half-open state.

[0016] If the similarity of the extracted features and the features of the picture of the cash box door in the closed state does not exceed the set threshold, and the similarity of the extracted features and the features of the picture of the cash box door in the half-open state does not exceed the set threshold, it is determined that the cash box door is in the fully open state.

[0017] In some embodiments, the number of people in the cash loading room is obtained based on monitoring data collected by a camera arranged inside the cash loading room, including the following steps:

[0018] The number of people in the cash loading room is obtained by detecting and tracking the human body target based on the monitoring data collected by the camera arranged inside the cash loading room.

[0019] In some embodiments, whether the cash loading process of the cash loading room is compliant is determined according to the switch state of the cash box door and the number of people in the cash loading room, including the following steps:

[0020] If the number of people in the cash loading room does not meet the set requirement when the cash box door is in the fully open state, it is determined that the cash loading process of the cash loading room is not compliant.

[0021] If the duration of the cash box door being in the half-open state exceeds a preset time range, it is determined that the cash loading process of the cash loading room is not compliant.

[0022] In some embodiments, before the feature extraction of the area where the cash box door is located in the real-time video frame captured by the camera, the method further includes:

[0023] The endpoint coordinate information of the area where the cash box door is located is obtained.

[0024] In a second aspect, an embodiment of the present application provides a banknote adding process detection device for detecting whether a banknote adding process in a banknote adding room is compliant, the device comprising: an acquisition module and a judgment module;

[0025] The acquisition module is configured to acquire an opening and closing state of a banknote case door in the banknote adding room and a number of people in the banknote adding room based on monitoring data collected by a camera arranged inside the banknote adding room.

[0026] The judgment module is configured to judge whether the banknote adding process in the banknote adding room is compliant according to the opening and closing state of the banknote case door and the number of people in the banknote adding room.

[0027] In a third aspect, a computer device is provided in the embodiment, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the method of the first aspect when executing the computer program.

[0028] In a fourth aspect, a computer readable storage medium is provided in the embodiment, which stores a computer program, and the computer program is executable on a processor to implement the steps of the method of the first aspect.

[0029] The banknote adding process detection method, device, computer device, and computer readable storage medium described above acquire the opening and closing state of the banknote case door in the banknote adding room and the number of people in the banknote adding room based on monitoring data collected by a camera arranged inside the banknote adding room, and judge whether the banknote adding process in the banknote adding room is compliant according to the opening and closing state of the banknote case door and the number of people in the banknote adding room. The present application only acquires the opening and closing state of the banknote case door and the number of people in the banknote adding room based on monitoring data collected by a camera arranged inside the banknote adding room, which greatly simplifies installation and deployment requirements and effectively reduces installation and deployment costs of the banknote adding process detection. BRIEF DESCRIPTION OF DRAWINGS

[0030] The accompanying drawings, which are included to provide a further understanding of the present application and constitute a part of this application, illustrate certain illustrative embodiments of the present application and together with the description serve to explain the present application. In the drawings:

[0031] Figure 1 is an application scenario diagram of a vehicle passing guidance method according to an embodiment of the present application;

[0032] Figure 2 is a flowchart of a vehicle passing guidance method according to an embodiment of the present application;

[0033] Figure 3 is a structural schematic diagram of a vehicle passing guidance device according to an embodiment of the present application;

[0034] Figure 4According to the structural schematic diagram of the computer device provided by the embodiment of the present application. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical solutions and advantages of the present application more clear, the present application is described and explained below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application. Based on the embodiments provided by the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of the present application.

[0036] Obviously, the drawings in the following description are only some examples or embodiments of the present application, and for those of ordinary skill in the art, the present application can be applied to other similar scenarios without creative labor on the basis of these drawings. In addition, it can be understood that although the efforts made in this development process can be complex and lengthy, for those of ordinary skill in the art related to the content disclosed in the present application, some design, manufacture or production changes on the basis of the technical content disclosed in the present application are only routine technical means and should not be understood as insufficient disclosure of the present application.

[0037] In the present application, the phrase "embodiment" means that the specific features, structures or characteristics described in combination with the embodiment can be included in at least one embodiment of the present application. The appearance of this phrase at various places in the specification does not necessarily mean the same embodiment, nor is it an independent or alternative embodiment that is not mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in the present application can be combined with other embodiments without conflict.

[0038] Unless otherwise defined, the technical or scientific terms used in this application shall have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms “a,” “an,” “an,” “the,” and similar words used in this application do not indicate quantity limitation and may indicate singular or plural. The terms “comprising,” “including,” “having,” and any variations thereof used in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units not listed, or may include other steps or units inherent to these processes, methods, products, or devices. The terms “connected,” “linked,” “coupled,” and similar words used in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. “Multiple” used in this application refers to two or more. “And / or” describes the relationship between related objects, indicating that three relationships may exist; for example, “A and / or B” can represent: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following objects are in an "or" relationship. The terms "first," "second," and "third" used in this application are merely to distinguish similar objects and do not represent a specific ordering of the objects.

[0039] Figure 1 This diagram illustrates an application scenario of a banknote-adding process detection method provided in one embodiment of this application. Figure 1 As shown, server 101 and monitoring terminal 102 can transmit data via a network. Monitoring terminal 102 collects monitoring data from inside the cash replenishment room and transmits the collected data to server 101. Server 101, based on the monitoring data collected by monitoring terminal 102, obtains the opening and closing status of the cash box door and the number of people inside the cash replenishment room; based on the opening and closing status of the cash box door and the number of people inside the cash replenishment room, it determines whether the cash replenishment process in the cash replenishment room is compliant. Server 101 can be implemented by a standalone server or a server cluster composed of multiple servers. Server 101 can be a component of monitoring terminal 102, and monitoring terminal 102 can be implemented by any camera.

[0040] This embodiment provides a method for detecting the cash replenishment process, used to detect whether the cash replenishment process in a cash replenishment room is compliant, such as... Figure 2 As shown, the method includes the following steps:

[0041] Step S210: Based on the monitoring data collected by the camera installed inside the cash replenishment room, obtain the opening and closing status of the cash box door inside the cash replenishment room and the number of people inside the cash replenishment room.

[0042] Specifically, the camera arranged inside the cash adding room can be one, but in order to obtain more comprehensive data in the cash adding room, a plurality of cameras can also be arranged in different corners of the cash adding room. Since the monitoring data captured by the camera can show the real-time dynamics in the cash adding room, the opening and closing state of the cash box door and the number of people in the cash adding room can be detected according to the monitoring data collected by the camera, so as to obtain the opening and closing state of the cash box door in the cash adding room and the number of people in the cash adding room.

[0043] In step S220, whether the cash adding process of the cash adding room is compliant is judged according to the opening and closing state of the cash box door and the number of people in the cash adding room.

[0044] Specifically, in the financial industry, the ATM cash adding room is a sensitive place, and security is particularly important. For the cash adding process, the bank has relevant rules, which require that the number of people during the cash adding process must meet the set requirements and that the cash box door must be in the fully open state during the entire cash adding process, so as to ensure that the cash adding process is fully transparent and that the cash adding staff can supervise each other. After obtaining the opening and closing state of the cash box door and the number of people in the cash adding room in the above step S210, whether the opening and closing state of the cash box door and the number of people in the cash adding room meet the set requirements can be judged according to the opening and closing state of the cash box door and the number of people in the cash adding room, so as to judge whether the cash adding process of the cash adding room is compliant.

[0045] In the prior art, a pressure sensor is arranged on the cash box door to obtain the opening and closing state of the cash box door. The arrangement of the pressure sensor will additionally increase the detection installation and deployment cost and the workload of bank system joint debugging, resulting in the problem of high cash adding process detection installation and deployment cost in the prior art.

[0046] In order to solve the above problems, the present application provides a cash adding process detection method, which obtains the opening and closing state of the cash box door in the cash adding room and the number of people in the cash adding room by collecting monitoring data based on the camera arranged inside the cash adding room. According to the opening and closing state of the cash box door and the number of people in the cash adding room, whether the cash adding process of the cash adding room is compliant is judged. The present application only obtains the opening and closing state of the cash box door and the number of people in the cash adding room based on the monitoring data collected by the camera arranged inside the cash adding room, greatly simplifying the installation and deployment requirements and effectively reducing the cash adding process detection installation and deployment cost.

[0047] As one of the embodiments, the opening and closing state of the cash box door includes a fully open state, a half open state and a closed state.

[0048] Specifically, for the banknote adding process, the bank has relevant rules that require the banknote adding process to have the banknote case door in a fully open state, and does not allow the banknote case door to be half open during the operation process. In the prior art, only the opening and closing states of the banknote case door are detected, and the half open state of the banknote case door is not considered, which still does not meet the relevant regulations of the bank. Therefore, in the present embodiment, the opening, closing and half open states of the banknote case door are obtained, so as to further accurately determine whether the banknote adding process in the banknote adding room is in compliance.

[0049] In one of the embodiments, the step S210 obtains the opening and closing states of the banknote case door in the banknote adding room based on the monitoring data collected by the camera arranged inside the banknote adding room, including the following steps:

[0050] In step S211, the features of the area where the banknote case door is located in the real-time video frame captured by the camera are extracted, and the extracted features are compared with the picture features of the preset banknote case door pictures in different opening and closing states.

[0051] Specifically, the preset banknote case door pictures in different opening and closing states can include banknote case door pictures in a fully open state, banknote case door pictures in a half open state, and banknote case door pictures in a closed state. In addition, in order to improve the accuracy of the opening and closing state recognition of the banknote case door, the preset banknote case door pictures in different opening and closing states can cover banknote case door pictures in different angles, different illuminations and different forms. Moreover, the preset banknote case door pictures can be updated in real time. In addition, based on the existing twin network feature extraction model, such as Siamese Network (twin neural network), Tripletnetwork (triplet network) and the like, the features of the area where the banknote case door is located in the real-time video frame captured by the camera can be extracted, and the picture features of the preset banknote case door pictures in different opening and closing states can be extracted, and then the extracted features are compared with the picture features of the preset banknote case door pictures in different opening and closing states. As one of the implementation manners, the existing cosine similarity calculation can be used to compare the similarity between the extracted features and the picture features of the preset banknote case door pictures in different opening and closing states.

[0052] In step S212, the opening and closing states of the banknote case door are determined according to the comparison result.

[0053] Specifically, the similarity comparison result can clearly indicate the similarity between the extracted features and the picture features of the preset banknote case door pictures in different opening and closing states, and according to the similarity of the comparison, the opening and closing states of the banknote case door can be determined.

[0054] Through the above steps S211 and S212, the opening and closing states of the banknote case door can be effectively determined according to the monitoring data collected by the camera.

[0055] Further, in one embodiment, the extracted feature is compared with the preset feature of the picture of the cash box door in different switch states, and the switch state of the cash box door is determined according to the comparison result, including the following steps:

[0056] In step S310, the extracted feature is compared with the preset feature of the picture of the cash box door in the closed state and the half-open state.

[0057] In step S320, if the similarity of the extracted feature and the feature of the picture of the cash box door in the closed state exceeds the set threshold, it is determined that the cash box door is in the closed state.

[0058] In step S330, if the similarity of the extracted feature and the feature of the picture of the cash box door in the half-open state exceeds the set threshold, it is determined that the cash box door is in the half-open state.

[0059] In step S340, if the similarity of the extracted feature and the feature of the picture of the cash box door in the closed state does not exceed the set threshold, and the similarity of the extracted feature and the feature of the picture of the cash box door in the half-open state does not exceed the set threshold, it is determined that the cash box door is in the fully open state.

[0060] Specifically, in order to reduce the workload of feature comparison, in the embodiment, the extracted feature is only compared with the preset feature of the picture of the cash box door in the closed state and the half-open state. Since the cash box door has three states, the fully open state, the half-open state and the closed state, by comparing the extracted feature with the preset feature of the picture of the cash box door in the closed state and the half-open state, if the extracted feature is successfully compared with the preset feature of the picture of the cash box door in which state, the state of the cash box door can be determined. If the comparison result of the extracted feature and the preset feature of the picture of the cash box door in the closed state and the half-open state is unsuccessful, it can be determined that the cash box door is in the fully open state. In addition, the extracted feature can be compared with the preset feature of the picture of the cash box door in any two of the fully open state, the half-open state and the closed state, and the state of the cash box door can be obtained according to the comparison result.

[0061] Through the above steps S310 to S340, the workload of feature comparison can be effectively reduced while ensuring effective identification of the switch state of the cash box door.

[0062] In one embodiment, the number of people in the cash loading room is obtained based on the monitoring data collected by the camera arranged inside the cash loading room in step S210, including the following steps:

[0063] Step S213, based on the monitoring data collected by the camera arranged inside the cash adding room, the human body target is detected and tracked, and the number of people in the cash adding room is obtained in real time.

[0064] Specifically, the human body target detection can be based on existing deep learning target detection algorithms, such as public algorithms such as SSD and YOLO. In the case of detecting a human body target, the existing target tracking algorithm is used, such as the nearest distance association combined with kalman filter prediction, to realize human body target tracking, obtain the number of human body target IDs in real time, and further obtain the number of people in the cash adding room. Since some potted plants, columnar objects or portraits in the wall in the cash adding room may be mistaken for human body targets, resulting in false detection of human body targets, as one of the embodiments, the duration of each human body target and the motion trajectory distance can be calculated in real time, and then it is determined whether the human body target is a real human body target (or living body target), so as to improve the accuracy of the obtained number of people in the cash adding room. Among them, the duration of the human body target = (the frame sequence number of the current human body target - the frame sequence number of the first human body target) / frame rate, and the motion trajectory distance of the human body target = the cumulative distance of the pixel movement between all video frames where the human body target appears. In the case where the duration of the human body target is greater than the set time, only when the motion trajectory distance is greater than the set distance, the human body target is considered as an effective human body target.

[0065] As one of the embodiments, the above step S220 determines whether the cash adding process of the cash adding room is compliant according to the opening and closing state of the cash box door and the number of people in the cash adding room, including the following steps:

[0066] Step S221, in the case where the cash box door is in the fully open state, if the number of people in the cash adding room does not meet the set requirement, it is determined that the cash adding process of the cash adding room is not compliant.

[0067] Step S222, in the case where the cash box door is in the half-open state, it is detected whether the duration of the cash box door in the half-open state exceeds the preset time range, and if the duration of the cash box door in the half-open state exceeds the preset time range, it is determined that the cash adding process of the cash adding room is not compliant.

[0068] In one embodiment, before the above step S211 extracts the features of the area where the cash box door is located in the real-time video frame captured by the camera, the cash adding process detection method provided by the embodiment further includes the following steps:

[0069] Obtain the endpoint coordinate information of the area where the cash box door is located.

[0070] Specifically, since the camera arranged inside the banknote adding room is configured to capture the whole picture of the banknote adding room, not only the banknote box door, the area where the banknote box door is located needs to be calibrated by the user in advance, and the area where the banknote box door is located is generally a polygon. After the user calibrates the area where the banknote box door is located, the end point coordinate information of the area where the banknote box door is located is obtained to determine the area where the banknote box door is located, so that the feature extraction of the area where the banknote box door is located is realized.

[0071] Figure 3 is a schematic diagram of a banknote adding process detection device according to an embodiment of the present application, as Figure 3 It is shown that a banknote adding process detection device 40 is provided for detecting whether the banknote adding process of a banknote adding room is compliant, and the device comprises an acquisition module 41 and a judgment module 42.

[0072] The acquisition module 41 is configured to acquire the opening and closing state of the banknote box door in the banknote adding room and the number of people in the banknote adding room based on the monitoring data collected by the camera arranged inside the banknote adding room.

[0073] The judgment module 42 is configured to judge whether the banknote adding process of the banknote adding room is compliant according to the opening and closing state of the banknote box door and the number of people in the banknote adding room.

[0074] In one of the embodiments, the opening and closing state of the banknote box door comprises a fully open state, a half open state and a closed state.

[0075] In one of the embodiments, the acquisition module 41 is further configured to perform feature extraction on the area where the banknote box door is located in the real-time video frame captured by the camera, compare the extracted features with the picture features of the preset banknote box door pictures in different opening and closing states, and determine the opening and closing state of the banknote box door according to the comparison result.

[0076] In one of the embodiments, the acquisition module 41 is further configured to compare the extracted features with the picture features of the preset banknote box door pictures in the closed state and the half open state, determine that the banknote box door is in the closed state if the similarity between the extracted features and the picture features of the banknote box door picture in the closed state exceeds a set threshold, determine that the banknote box door is in the half open state if the similarity between the extracted features and the picture features of the banknote box door picture in the half open state exceeds the set threshold, and determine that the banknote box door is in the fully open state if the similarity between the extracted features and the picture features of the banknote box door picture in the closed state does not exceed the set threshold and the similarity between the extracted features and the picture features of the banknote box door picture in the half open state does not exceed the set threshold.

[0077] In one of the embodiments, the acquisition module 41 is further configured to detect and track the human body target based on the monitoring data collected by the camera arranged inside the banknote adding room, and acquire the number of people in the banknote adding room in real time.

[0078] In one embodiment, the judgment module 42 is further configured to determine that the cash replenishment process in the cash replenishment room is non-compliant if the number of people in the cash replenishment room does not meet the set requirements when the cash box door is fully open.

[0079] When the cash box door is half-open, check whether the duration of the half-open state exceeds a preset time range. If the duration of the half-open state exceeds the preset time range, it is determined that the cash replenishment process in the cash replenishment room is non-compliant.

[0080] In one embodiment, the acquisition module 41 is also used to acquire the endpoint coordinate information of the area where the cash box door is located.

[0081] It should be noted that the above modules can be functional modules or program modules, and can be implemented in software or hardware. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or they can be stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0082] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 4 The computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores a set of preset configuration information. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements the aforementioned banknote-adding process detection method.

[0083] In one embodiment, a computer device is provided, which can be a terminal. The computer device comprises a processor, a memory, a network interface, a display screen and an input device connected through a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The network interface of the computer device is configured to communicate with external terminals through a network connection. The computer program is executed by the processor to implement a banknote adding process detection method. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0084] Those skilled in the art can understand that, Figure 4 The structure shown is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0085] In one embodiment, a computer readable storage medium is provided, which stores a computer program. The computer program is executed by a processor to implement the following steps:

[0086] Based on the monitoring data collected by the camera arranged inside the banknote adding room, the opening and closing state of the banknote case door and the number of people in the banknote adding room are obtained;

[0087] According to the opening and closing state of the banknote case door and the number of people in the banknote adding room, it is determined whether the banknote adding process of the banknote adding room is compliant.

[0088] In one embodiment, the opening and closing state of the banknote case door includes a fully open state, a half open state and a closed state.

[0089] In one embodiment, the processor further implements the following steps when executing the computer program:

[0090] Features of the area where the banknote case door is located in the real-time video frame captured by the camera are extracted, and the extracted features are compared with the picture features of the preset banknote case door pictures in different opening and closing states;

[0091] According to the comparison result, the opening and closing state of the banknote case door is determined.

[0092] In one embodiment, the processor further implements the following steps when executing the computer program:

[0093] The extracted feature is compared with the picture feature of the preset picture of the banknote case door in the closed state and the half-open state in terms of similarity;

[0094] If the similarity of the extracted feature and the picture feature of the banknote case door picture in the closed state exceeds the set threshold, it is determined that the banknote case door is in the closed state;

[0095] If the similarity of the extracted feature and the picture feature of the banknote case door picture in the half-open state exceeds the set threshold, it is determined that the banknote case door is in the half-open state;

[0096] If the similarity of the extracted feature and the picture feature of the banknote case door picture in the closed state does not exceed the set threshold, and the similarity of the extracted feature and the picture feature of the banknote case door picture in the half-open state does not exceed the set threshold, it is determined that the banknote case door is in the fully open state.

[0097] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0098] Based on the monitoring data collected by the camera arranged inside the banknote adding room, the human body target is detected and tracked, and the number of people in the banknote adding room is obtained in real time.

[0099] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0100] In the case where the banknote case door is in the fully open state, if the number of people in the banknote adding room does not meet the set requirement, it is determined that the banknote adding process of the banknote adding room is not in compliance.

[0101] In the case where the banknote case door is in the half-open state, it is detected whether the duration of the banknote case door being in the half-open state exceeds the preset time range, and if the duration of the banknote case door being in the half-open state exceeds the preset time range, it is determined that the banknote adding process of the banknote adding room is not in compliance.

[0102] In one embodiment, before the feature extraction on the area where the banknote case door is located in the real-time video frame captured by the camera, the processor, when executing the computer program, also implements the following steps:

[0103] The endpoint coordinate information of the area where the banknote case door is located is obtained.

[0104] The above storage medium obtains the opening and closing state of the banknote case door and the number of people in the banknote adding room based on the monitoring data collected by the camera arranged inside the banknote adding room, and judges whether the banknote adding process of the banknote adding room is in compliance according to the opening and closing state of the banknote case door and the number of people in the banknote adding room. The present application only obtains the opening and closing state of the banknote case door and the number of people in the banknote adding room based on the monitoring data collected by the camera arranged inside the banknote adding room, which greatly simplifies the installation and deployment requirements and effectively reduces the installation and deployment cost of the banknote adding process detection.

[0105] It should be understood that the detailed description and specific examples described herein are intended for purposes of illustration only and are not intended to limit the scope of the present application. Consequently, all other embodiments that would be apparent to one of ordinary skill in the art from the preceding description and drawings are intended to be within the scope and spirit of the present application.

[0106] Obviously, the drawings described herein are only a few examples of implementation or embodiment of the present application, and for those of ordinary skill in the art, the present application can also be applied to other similar situations without creative labor. In addition, it can be understood that although the work done in the development process may be complex and long, certain design, manufacture or production changes made by those of ordinary skill in the art based on the technical content disclosed in the present application are only routine technical means and should not be regarded as insufficient disclosure of the present application.

[0107] The word "embodiment" in the present application refers to the specific features, structures or characteristics described in conjunction with the embodiment can be included in at least one embodiment of the present application. The phrase appears in various places in the specification does not necessarily mean the same embodiment, nor does it mean independence or alternatives to other embodiments. It can be clearly or implicitly understood by those of ordinary skill in the art that the embodiments described in the present application can be combined with other embodiments without conflict.

[0108] The above embodiments only express several implementation manners of the present application, which are described in detail and specifically, but should not be understood as a limitation on the scope of patent protection. It should be pointed out that for those of ordinary skill in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of protection of the present application. Therefore, the scope of protection of the present application should be subject to the appended claims.

Claims

1. A method for detecting whether a banknote adding process in a banknote adding room is compliant, the method comprising: detecting a banknote adding process in a banknote adding room; and determining whether the banknote adding process is compliant based on a result of the detecting. The method comprises the following steps: The method comprises the following steps: The method further comprises the following steps before the feature extraction on the area where the banknote case door is located in the real-time video frame captured by the camera: Obtain the endpoint coordinate information of the area where the banknote case door is located.

2. The method of claim 1, wherein the step of detecting the cash insertion process is characterized by, The feature extraction on the area where the banknote case door is located in the real-time video frame captured by the camera comprises: The feature extraction on the area where the banknote case door is located in the real-time video frame captured by the camera is based on a twin network feature extraction model.

3. The method of claim 1, wherein the step of detecting the cash insertion process is characterized by, The similarity comparison of the extracted feature and the picture feature of the preset banknote case door picture in different switch states comprises: The similarity comparison of the extracted feature and the picture feature of the preset banknote case door picture in different switch states is performed by using a cosine similarity algorithm.

4. The method of claim 1, wherein the step of detecting the cash insertion process is characterized by, Based on the monitoring data captured by the camera, the continuous existence time and the motion trajectory distance of an individual target are determined, and in the case that the continuous existence time is greater than a set time and the motion trajectory distance is greater than a set distance, the individual target is determined to be a real human target, and the real human target is detected and tracked to obtain the number of people in the banknote adding room in real time; the continuous existence time is determined according to the frame sequence number at which the individual target appears, the frame sequence number at which the individual target first appears, and the frame rate; the motion trajectory distance is determined according to the pixel movement distance between all video frames in which the individual target appears. In the case that the banknote case door is in the fully open state, if the number of people in the banknote adding room does not meet the set requirement, it is determined that the banknote adding process of the banknote adding room is not in compliance; in the case that the banknote case door is in the half-open state, it is detected whether the duration of the banknote case door being in the half-open state exceeds a preset time range, and if the duration of the banknote case door being in the half-open state exceeds the preset time range, it is determined that the banknote adding process of the banknote adding room is not in compliance. In the case that the banknote case door is in the fully open state, if the number of people in the banknote adding room does not meet the set requirement, it is determined that the banknote adding process of the banknote adding room is not in compliance; in the case that the banknote case door is in the half-open state, it is detected whether the duration of the banknote case door being in the half-open state exceeds a preset time range, and if the duration of the banknote case door being in the half-open state exceeds the preset time range, it is determined that the banknote adding process of the banknote adding room is not in compliance. In the case that the banknote case door is in the fully open state, if the number of people in the banknote adding room does not meet the set requirement, it is determined that the banknote adding process of the banknote adding room is not in compliance; in the case that the banknote case door is in the half-open state, it is detected whether the duration of the banknote case door being in the half-open state exceeds a preset time range, and if the duration of the banknote case door being in the half-open state exceeds the preset time range, it is determined that the banknote adding process of the banknote adding room is not in compliance. In the case that the banknote case door is in the fully open state, if the number of people in the banknote adding room does not meet the set requirement, it is determined that the banknote adding process of the banknote adding room is not in compliance; in the case that the banknote case door is in the half-open state, it is detected whether the duration of the banknote case door being in the half-open state exceeds a preset time range, and if the duration of the banknote case door being in the half-open state exceeds the preset time range, it is determined that the banknote adding process of the banknote adding room is not in compliance.

5. The method of claim 1, wherein, The method comprises the following steps: The feature extraction of the area where the banknote case door is located in the real-time video frame captured by the camera arranged inside the banknote adding room comprises: The feature extraction of the area where the banknote case door is located in the real-time video frame captured by the camera arranged inside the banknote adding room comprises:

6. The method of claim 1, wherein, The feature extraction of the area where the banknote case door is located in the real-time video frame captured by the camera arranged inside the banknote adding room comprises: The feature extraction of the area where the banknote case door is located in the real-time video frame captured by the camera arranged inside the banknote adding room comprises:

7. A banknote replenishment process detection device, used to detect whether the banknote replenishment process in a banknote replenishment room is compliant, characterized in that, The feature extraction of the area where the banknote case door is located in the real-time video frame captured by the camera arranged inside the banknote adding room comprises: The device comprises an acquisition module and a judgment module. The acquisition module is configured to extract features of the area where the banknote case door is located in the real-time video frame captured by the camera arranged inside the banknote adding room, and compare the extracted features with picture features of preset banknote case door pictures in closed and half-open states; if the similarity between the extracted features and the picture features of the banknote case door picture in the closed state exceeds a set threshold, it is determined that the banknote case door is in the closed state; if the similarity between the extracted features and the picture features of the banknote case door picture in the half-open state exceeds the set threshold, it is determined that the banknote case door is in the half-open state; if the similarity between the extracted features and the picture features of the banknote case door picture in the closed state does not exceed the set threshold, and the similarity between the extracted features and the picture features of the banknote case door picture in the half-open state does not exceed the set threshold, it is determined that the banknote case door is in the fully open state; the preset banknote case door pictures in different opening and closing states are banknote case door pictures covering different angles, different illuminations and different forms, and the comparison result is used to indicate the similarity between the extracted features and the picture features of the preset banknote case door pictures in different opening and closing states; based on the monitoring data captured by the camera, the continuous existence time and the motion trajectory distance of an individual target are determined, and in the case that the continuous existence time is greater than a set time and the motion trajectory distance is greater than a set distance, the individual target is determined to be a real human target, and the real human target is detected and tracked to obtain the number of people in the banknote adding room in real time; the continuous existence time is determined according to the frame sequence number at which the individual target currently appears, the frame sequence number at which the individual target first appears and the frame rate; the motion trajectory distance is determined according to the pixel movement distance between all video frames in which the individual target appears; 8. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The judgment module is configured to, in the case that the banknote case door is in the fully open state, determine that the banknote adding process of the banknote adding room is not in compliance if the number of people in the banknote adding room does not meet a set requirement; and in the case that the banknote case door is in the half-open state, detect whether the duration that the banknote case door is in the half-open state exceeds a preset time range, and determine that the banknote adding process of the banknote adding room is not in compliance if the duration that the banknote case door is in the half-open state exceeds the preset time range. The processor executes the computer program to implement the steps of the method in any one of claims 1 to 6. The processor executes the computer program to implement the steps of the method in any one of claims 1 to 6.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program, which is executed by a processor, implements the steps of the method according to any one of claims 1 to 6.

Images