Teller behavior monitoring method, device, system and equipment and storage medium
Through the comparison of image detection algorithms and preset violation rules, the teller behavior is automatically judged, which solves the problem of low manual detection efficiency in the existing technology, and realizes efficient monitoring of violations and alarms.
Patent Information
- Application Number
- CN202410566465.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-09
- Publication Date
- 2024-11-12
AI Technical Summary
In the prior art, it is less efficient to detect whether the teller has violated the violation by manually watching the video surveillance large screen, resulting in less efficient detection of the violation.
By obtaining the video frames pointed to the counter by the monitoring lens, using an image detection algorithm to determine the categories of each object contained in the video frame, and comparing them with the preset violation rules to automatically determine whether the teller has violated the rules.
It realizes automatic monitoring of teller behavior, improves the efficiency of detecting violations, reduces the missed detection rate, and can detect and record teller violations in real time, reducing the missed report and inefficient efficiency of manual supervision.
Smart Images

Figure CN118942022A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of monitoring technology, and in particular to a method, device, system, equipment and storage medium for monitoring teller behavior. Background Art
[0002] In actual application environments, many scenarios require monitoring the behavior of tellers, for example, monitoring whether the behavior of tellers at bank counters violates regulations. In the prior art, whether the teller violates regulations is manually judged by watching the video monitoring screen, which results in low efficiency in detecting violations. Summary of the invention
[0003] The purpose of the embodiments of the present invention is to provide a method, device, system, equipment and storage medium for monitoring teller behavior, so as to automatically monitor teller behavior and improve the efficiency of detecting illegal behavior. The specific technical solution is as follows:
[0004] In a first aspect, a method for monitoring teller behavior is provided, comprising:
[0005] Acquire a video frame in which the surveillance camera points to a counter, where the teller is located;
[0006] Determining the category of each object contained in the video frame by an image detection algorithm;
[0007] Obtaining preset violation rules associated with the surveillance camera;
[0008] Determining whether the category of each object contained in the video frame complies with the preset violation rules;
[0009] If so, it is determined that the teller has violated the rules.
[0010] Optionally, after acquiring the video frame in which the surveillance camera points to the counter, the method further includes:
[0011] Determining the position information of each object contained in the video frame by an image detection algorithm;
[0012] Based on the position information of each object, determine the object to be detected that is located in the detection area among the objects;
[0013] The determining whether the category of each object contained in the video frame complies with the preset violation rule includes:
[0014] Determine whether the category of the object to be detected conforms to the preset violation rules.
[0015] Optionally, determining the objects to be detected located in the detection area among the objects based on the position information of the objects includes:
[0016] Acquiring the position information of the pre-marked detection area;
[0017] The position information of each object is compared with the position information of the detection area, and objects whose position information is within the range of the detection area represented by the position information of the detection area are determined as objects to be detected.
[0018] Optionally, the method also includes: after determining that the category of each object contained in the video frame meets the preset violation rule, obtaining the current time; calculating the difference between the current time and the violation start time, wherein the violation start time is recorded by a timer, and the timer corresponds to the preset violation rule associated with the surveillance camera; if the difference exceeds a preset duration, triggering an alarm.
[0019] Optionally, after determining whether the category of each object contained in the video frame complies with the preset violation rule, the method further includes:
[0020] The detection result of the video frame of the surveillance camera pointing to the counter is saved, and the detection result includes a result that complies with the preset violation rule and is obtained based on the video frame of the surveillance camera pointing to the counter.
[0021] Optionally, obtaining a video frame in which the surveillance camera points to the counter includes:
[0022] Get the video stream of the surveillance camera pointing to the counter;
[0023] A video frame is extracted from the video stream as a video frame in which the surveillance camera is directed to the counter.
[0024] Optionally, the preset violation rules include at least one of the following: the category of the object to be detected includes cash but does not include human body, the category of the object to be detected includes two open doors, and the category of the object to be detected includes a person.
[0025] In a second aspect, a device for monitoring teller behavior is provided, comprising:
[0026] A first acquisition module is used to acquire a video frame of a counter pointed by a surveillance camera, where the counter is where a teller is located;
[0027] A first determination module, configured to determine the category of each object contained in the video frame by using an image detection algorithm;
[0028] A second acquisition module, used to acquire a preset violation rule associated with the surveillance camera;
[0029] A first judgment module, used to judge whether the category of each object contained in the video frame conforms to the preset violation rule;
[0030] The second determination module is used to determine that the teller has violated the regulations if the conditions are met.
[0031] In a third aspect, a system for monitoring teller behavior is provided, comprising:
[0032] A processing device and at least one monitoring camera, each monitoring camera corresponding to at least one counter;
[0033] For each surveillance camera, the surveillance camera is used to collect a video frame of the counter pointed by the surveillance camera, where the counter is where the teller is located;
[0034] The processing device is used to obtain a video frame in which a surveillance camera points to a counter, and determine the category of each object contained in the video frame through an image detection algorithm; obtain a preset violation rule associated with the surveillance camera; determine whether the category of each object contained in the video frame complies with the preset violation rule; if so, determine that the teller has violated the rule.
[0035] In a fourth aspect, a processing device is provided, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;
[0036] Memory, used to store computer programs;
[0037] The processor is used to implement any method step described in the first aspect when executing the program stored in the memory.
[0038] In a fifth aspect, a computer-readable storage medium is provided, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, any method step described in the first aspect is implemented.
[0039] An embodiment of the present invention further provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute any of the above-mentioned methods for monitoring teller behavior.
[0040] Beneficial effects of the embodiments of the present invention:
[0041] In an embodiment of the present invention, an image detection algorithm is used to determine the categories of objects contained in a video frame in which a surveillance camera points to a counter, and whether the categories of objects contained in the video frame conform to preset violation rules. If the categories of objects contained in the video frame conform to the preset violation rules, it is determined that the teller has violated the rules. In this way, the teller's behavior can be automatically monitored, thereby improving the efficiency of detecting violations.
[0042] Of course, it is not necessary to achieve all of the advantages described above at the same time to implement any product or method of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other embodiments can also be obtained based on these drawings.
[0044] Figure 1 A flow chart of a method for monitoring teller behavior provided by an embodiment of the present invention;
[0045] Figure 2 A schematic diagram of the structure of a device for monitoring teller behavior provided by an embodiment of the present invention;
[0046] Figure 3 A schematic diagram of the structure of a system for monitoring teller behavior provided by an embodiment of the present invention;
[0047] Figure 4 A schematic diagram of the structure of a processing device provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0048] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field based on the present invention belong to the scope of protection of the present invention.
[0049] In order to realize automatic monitoring of teller behavior, for example, monitoring whether the teller's behavior at the bank counter violates the rules. In the embodiment of the present invention, preset violation rules associated with the monitoring camera can be set in advance, and corresponding monitoring cameras can be configured for each counter. In actual application, the monitoring camera is pointed at the counter where the teller is located, and the video frame of the counter where the teller is located is collected by the monitoring camera, and the video frame of the counter where the teller is located collected by the monitoring camera is analyzed by the processing device, for example, analyzing which objects are included in the video frame; then, the result of the video frame analysis is compared with the preset violation rules associated with the monitoring camera, so as to determine whether the teller has violated the rules, and trigger an alarm when it is determined that the teller has violated the rules.
[0050] The processing device may be a server, a terminal, etc., for example, a computer, a mobile phone, etc. The monitoring lens may also be understood as an image acquisition device, for example, a camera, a webcam, etc.
[0051] In one example, the counter in the embodiment of the present invention may be a bank counter, and the method for monitoring the behavior of a teller provided in the embodiment of the present invention may be understood as a method for monitoring the behavior of a financial teller in the financial field.
[0052] The following will first describe in detail the method for monitoring teller behavior provided by an embodiment of the present invention in conjunction with the accompanying drawings. The method for monitoring teller behavior provided by an embodiment of the present invention can be applied to the above-mentioned processing device.
[0053] Reference Figure 1 The method for monitoring teller behavior provided by the embodiment of the present invention may include:
[0054] S101, obtaining a video frame in which the surveillance camera points to a counter, where the teller is located;
[0055] S102, determining the category of each object contained in the video frame through an image detection algorithm;
[0056] S103, obtaining preset violation rules associated with the surveillance camera;
[0057] S104, determining whether the category of each object contained in the video frame complies with a preset violation rule;
[0058] S105, if it is in compliance, it is determined that the teller has violated the rules.
[0059] In the embodiment of the present invention, the categories of the objects contained in the video frame of the surveillance camera pointing to the counter are determined through an image detection algorithm, and it is judged whether the categories of the objects contained in the video frame meet the preset violation rules. If the categories of the objects contained in the video frame meet the preset violation rules, it is determined that the teller has violated the rules, so that the teller's behavior can be automatically monitored and the efficiency of detecting violations can be improved. In addition, the missed detection rate of missed violations can be reduced.
[0060] It can be understood that the embodiment of the present invention can automatically discover the teller's illegal behavior in real time, solving the problem of underreporting and low efficiency in manual supervision of illegal behavior.
[0061] In the embodiment of the present invention, a monitoring lens can be used to monitor multiple counters, and a monitoring lens can collect video frames of multiple counters. In this case, different counters can be represented by different frames in the lens picture. In an optional manner, a corresponding monitoring lens can also be set for each counter, and the monitoring lens points to the counter to collect video frames of the counter.
[0062] The preset violation rules associated with a surveillance camera can also be understood as the preset violation rules associated with the counter that the surveillance camera points to, or can also be understood as the preset violation rules corresponding to the camera position where the surveillance camera is located.
[0063] In S101, the surveillance camera collects video frames in which the surveillance camera points to the counter, and the processing device obtains the video frames in which the surveillance camera points to the counter from the surveillance camera.
[0064] In one possible implementation, the surveillance camera collects video frames of the counter pointed by the surveillance camera in real time, and sends each captured video frame to the processing device. Alternatively, the surveillance camera can send the captured video frames to the processing device at intervals of one frame or multiple frames according to the performance limit of the processing device.
[0065] In another possible implementation, the processing device obtains a video stream of the surveillance camera pointing to the counter; and extracts a video frame from the video stream as a video frame of the surveillance camera pointing to the counter. Specifically, the surveillance camera can periodically capture the video stream, for example, once every preset time period, wherein the preset time period can be determined based on experience or actual needs, for example, 10 seconds, 20 seconds, and so on. The surveillance camera captures the video stream, and sends the captured video stream to the processing device, and the processing device extracts a video frame from the video stream as the currently captured video frame of the surveillance camera pointing to the counter.
[0066] In S102, the object category is used to indicate the type of the object, for example, the video frame contains cash, a person, a door, etc. In one implementation, the object category may indicate not only the category of the object but also the state of the object, for example, an open door, a moving person, etc.
[0067] In S103, the associated violation rules are set for each surveillance camera in advance. Specifically, in the process of setting the violation rules, the processing device can provide an operation interface, and the management personnel can set the associated violation rules for each surveillance camera through the operation interface. The violation rules are the preset violation rules associated with the surveillance camera. The processing device can save the associated violation rules set by the management personnel for each surveillance camera, so that when analyzing the behavior of the teller with a surveillance camera pointing to the counter, the preset violation rules associated with the surveillance camera can be obtained.
[0068] Among them, one surveillance camera can be associated with one violation rule, or can also be associated with multiple violation rules.
[0069] In an embodiment of the present invention, a corresponding preset violation rule can be set for the surveillance camera according to the characteristics of the counter pointed at by the surveillance camera. For example, different counters handle different businesses, and different businesses require tellers to perform different operations. In this way, preset violation rules related to the business handled by the counter can be set for the surveillance camera according to the business handled by the counter. Among them, a surveillance camera pointing to a corresponding counter to collect video frames of the counter can be understood as a channel, and setting corresponding preset violation rules for different surveillance cameras can be understood as flexible setting of violation rules for channels.
[0070] For example, the preset violation rules include at least one of the following: the category of the object to be detected includes cash and does not include human body, the category of the object to be detected includes two open doors, and the category of the object to be detected includes a person.
[0071] In S104, the categories of the objects contained in the video frame of the surveillance camera pointing to the counter are compared with the preset violation rules. If the categories of the objects contained in the video frame meet the preset violation rules, S105 is executed; if the categories of the objects contained in the video frame do not meet the preset violation rules, it is determined that the teller of the counter pointed by the surveillance camera has not violated the rules. In an example, it can be determined whether the combination of the categories of the objects contained in the video frame meets the preset violation rules.
[0072] In one implementation, after S101, the embodiment of the present invention further includes: determining the location information of each object contained in the video frame by using an image detection algorithm. Alternatively, it can also be understood that in S102, the category of each object contained in the video frame and the location information of each object are determined by using an image detection algorithm.
[0073] Then, based on the position information of each object, determine the objects to be detected that are located in the detection area. In this way, S104 includes: judging whether the category of the object to be detected meets the preset violation rules, and S105 includes: if the category of the object to be detected meets the preset violation rules, it is determined that the teller has violated the rules.
[0074] It can also be understood that before comparing the detection results of the video frame with the preset violation rules associated with the surveillance camera, objects whose coordinates are outside the set detection frame are first filtered out, and the categories of the objects in the filtered video frame are compared with the configured preset violation rules.
[0075] Among them, based on the position information of each object, the objects to be detected located in the detection area among the objects are determined, including: obtaining the position information of the pre-marked detection area; comparing the position information of each object with the position information of the detection area, and determining the objects whose position information is within the range of the detection area represented by the position information of the detection area as the objects to be detected.
[0076] For example, in an embodiment of the present invention, for each monitoring lens, an image of the counter pointed by the monitoring lens can be collected in advance, and then the positions of the areas to be monitored and the areas to be excluded are marked with wireframes in the image. The positions are the positions of the areas to be monitored and the areas to be excluded in the lens, wherein the areas to be monitored are the above-mentioned detection areas.
[0077] In this way, irrelevant pictures in the video frame can be excluded, which not only makes the detection result more accurate, but also reduces the calculation amount of subsequent detection.
[0078] In one possible implementation, after determining whether the categories of objects contained in the video frame comply with preset violation rules, the detection results of the video frame in which the surveillance camera is pointing to the counter are saved, and the detection results include results that comply with preset violation rules based on the video frame in which the surveillance camera is pointing to the counter.
[0079] Specifically, when a detection result is obtained based on a video frame to determine whether the category of an object in the video frame meets the preset violation rule, the detection result is saved corresponding to the video frame. When saving the video frame and the detection result corresponding to the video frame, the timestamp of the video frame can be saved at the same time, such as the timestamp of collecting the video frame.
[0080] In an example, a label can be used to indicate whether the category of an object in a video frame meets the preset violation rules. For example, if the category of an object in a video frame meets the preset violation rules, the detection result of the video frame is set to correspond to the label 1, TRUE, etc.; if the category of an object in a video frame does not meet the preset violation rules, the detection result of the video frame is set to correspond to the label 0, FALSE.
[0081] In an optional embodiment, after determining that the categories of the objects contained in the video frame meet the preset violation rules, it further includes: triggering an alarm. It can also be understood that after determining that the category of the object to be detected meets the preset violation rules, it is determined that the teller has violated the rules and the alarm is triggered. The embodiment of the present invention does not limit the form of the alarm.
[0082] In an optional embodiment, when determining that a teller has violated the rules in the video frame based on a single video frame, it is not taken as the final result of whether the teller has violated the rules. Instead, the video frames in which the surveillance camera is pointing to the counter are continuously detected. When the teller has violated the rules for a preset period of time, it is finally determined that the teller has violated the rules and an alarm is triggered.
[0083] In an optional embodiment, after determining whether the category of each object contained in the video frame meets the preset violation rule, the current time is obtained, and the difference between the current time and the violation start time is calculated; if the difference exceeds the preset time, an alarm is triggered. The violation start time is recorded by a timer, and the timer corresponds to the preset violation rule associated with the surveillance camera.
[0084] The preset duration can be determined based on actual needs or experience, for example, 60 seconds, 5 seconds, 15 seconds, etc.
[0085] It can be understood that each preset violation rule configured for a surveillance camera corresponds to a timer. When the video frame captured by the surveillance camera is detected to meet the preset violation rule, the timer can be used to record the corresponding time. This time can be the time when the current video is detected to meet the preset violation rule, or it can also be understood as the time when the preset violation rule is triggered. Afterwards, in the next process of using the video frame captured by the surveillance camera to detect whether it meets the preset violation rule, if it is detected that it does not meet the preset violation rule again, the timer is deleted. If it is detected that it meets the preset violation rule again, the current time of triggering the preset violation rule is obtained, and the difference between the current time and the violation start time is calculated; if the difference exceeds the preset duration, an alarm is triggered, and the timer can be deleted; if the difference does not exceed the preset duration, wait for the next detection result. In this way, the violation contained in the lens can be continuously detected.
[0086] Among them, when the previous video frame is used to detect that the counter meets the preset violation rules, if the next detection result received does not meet the preset violation rules, the timer will be deleted. Only when the detection results of consecutive video frames all meet the preset violation rules will the timer be maintained. In addition, when the duration of meeting the preset violation rules is greater than the preset duration, an alarm can be triggered, and in this case, the timer can also be deleted. Therefore, the time recorded by the timer in the embodiment of the present invention that triggers the preset violation rules can be understood as the violation start time.
[0087] For example, when the detection result of the first frame of video captured by the surveillance camera is that the teller has violated the rules, a timer is created to record the time when the first frame of video is used to detect that the preset violation rule is met, or it can also be understood as the time when the preset violation rule is triggered;
[0088] Next, the second video frame captured by the surveillance camera is used for detection. If the detection result obtained by the second video frame captured by the surveillance camera shows that the teller has not violated the rules, that is, the preset violation rules have not been triggered, the aforementioned counter is deleted; and if the detection result obtained by the second video frame captured by the surveillance camera also shows that the teller has violated the rules, the difference between the current time and the time recorded by the aforementioned timer can be determined. If the difference exceeds the preset duration, an alarm is triggered, and the aforementioned timer can be deleted; and if the difference does not exceed the preset duration, wait for the next detection result. By analogy, in the process of subsequent video frame detection using the surveillance camera, the aforementioned rules can be used to detect the teller's violations and determine whether to trigger an alarm.
[0089] Each video frame based on the surveillance camera pointing to the counter is detected to obtain a detection result of whether the category of the object in the video frame meets the preset violation rules, and the detection result is saved in correspondence with the video frame. In one implementable method, after obtaining the corresponding detection result based on a video frame, the detection result and the video frame can be saved in the memory in correspondence. It can be understood that these data are saved for a period of time, for example, 5 minutes, 10 minutes. If these detection results do not involve triggering an alarm after a period of time, these data can be deleted from the memory to save storage resources; and if the alarm information of the channel is received, the video recording and results of the alarm start time and alarm end time are recorded for subsequent review. Among them, the alarm information received from the channel can be understood as using the surveillance camera to collect the video frame of the corresponding counter and using the video frame to detect violations and trigger an alarm.
[0090] In this way, after acquiring the current video frame and obtaining the detection result corresponding to the current video frame based on the current video frame analysis, it is further determined whether the violation continues for a preset time period to determine whether to trigger an alarm.
[0091] In the embodiment of the present invention, the preset violation rules include the above Figure 1 In the embodiment, the violation rule also includes a preset duration of the violation rule. For example, the preset violation rule includes at least one of the following: the category of the object to be detected includes cash and does not include human body and lasts for 60 seconds, the category of the object to be detected includes two open doors and lasts for more than 5 seconds, and the category of the object to be detected includes a person and lasts for more than 15 seconds.
[0092] As described above, in the embodiment of the present invention, after determining that the category of the object to be detected meets the preset violation rules, it is determined that the teller has violated the rules and an alarm is triggered.
[0093] In this case, the preset violation rules can also be understood as alarm rules.
[0094] Simply put, in the embodiment of the present invention, the surveillance camera is pointed at the counter where the teller is located, and the processing device analyzes which objects are contained in each frame of the image (i.e., the video frame) received, and determines whether the detected object triggers an alarm by comparing it with the alarm rules pre-set for the camera position. For example, the alarm rules associated with the current surveillance camera are obtained, objects whose coordinates are outside the set detection frame are filtered out, and the categories of objects in the filtered video frame are compared with the configured alarm rules. If the detected object combination meets the alarm rules, an alarm is issued, otherwise no alarm is triggered.
[0095] For example, cash is detected in a video stream, but no human body is detected, and the camera is configured with a cash left behind alarm. In this case, the preset violation rule is: cash is detected in the picture and no human body is detected for 60 seconds. When the detection result obtained based on the video frame pointed at the counter by the surveillance camera meets the preset violation rule, an alarm is generated;
[0096] Two door-opening objects are detected in one video stream, and the camera is configured with linked door double opening. In this case, the preset violation rule is: if two doors are detected to be opened simultaneously in the image and the duration is greater than 5 seconds, an alarm is generated when the detection result obtained based on the video frame pointed at the counter by the surveillance camera meets the preset violation rule;
[0097] Only one person is detected in one video stream, and the camera is configured for a single person to enter the cash loading room. In this case, the preset violation rule is: only one person is detected in the picture and the duration is greater than 15 seconds. When the detection result obtained based on the video frame pointed at the counter by the surveillance camera meets the preset violation rule, an alarm is generated.
[0098] In one possible implementation, after determining that the teller has violated the rules, a violation video including a current video frame and at least one historical video frame may be saved, and a violation record may be generated.
[0099] In this case, the above-mentioned processing device can also be understood as a storage device.
[0100] In this way, it is easy to record the teller's illegal behavior, and the teller's behavior can be regulated in real time or based on the alarm record to avoid the risk of illegal behavior being exploited.
[0101] In an optional embodiment, the counter in the embodiment of the present invention is a bank counter, and the method for monitoring the behavior of a teller provided in the embodiment of the present invention can be understood as a method for monitoring the behavior of a financial teller in the financial field.
[0102] When the method for monitoring teller behavior provided by the embodiment of the present invention is applied to the financial field, the teller's violations can be discovered and recorded in real time, and alarms can be pushed and statistics on violations can be collected in real time. The teller's violations can also be effectively supervised and regulated, thereby reducing the risk of financial institutions being infringed.
[0103] The embodiment of the present invention also provides a device for monitoring teller behavior, such as Figure 2 As shown, this may include:
[0104] The first acquisition module 201 is used to acquire a video frame of a counter pointed by a surveillance camera, where the counter is where the teller is located;
[0105] A first determination module 202, configured to determine the category of each object contained in the video frame by using an image detection algorithm;
[0106] A second acquisition module 203 is used to acquire preset violation rules associated with the surveillance camera;
[0107] The first judgment module 204 is used to judge whether the category of each object contained in the video frame meets the preset violation rules;
[0108] The second determination module 205 is used to determine that the teller has violated the rules if the conditions are met.
[0109] Optionally, the device further comprises:
[0110] The third determination module is used to determine the position information of each object contained in the video frame through an image detection algorithm after acquiring the video frame in which the surveillance camera points to the counter; based on the position information of each object, determine the object to be detected located in the detection area among the objects;
[0111] The first judgment module 204 is specifically used to judge whether the category of the object to be detected conforms to the preset violation rules.
[0112] Optionally, the third determination module is specifically used to obtain the position information of a pre-marked detection area; compare the position information of each object with the position information of the detection area, and determine the object whose position information is within the range of the detection area represented by the position information of the detection area as the object to be detected.
[0113] Optionally, the device further comprises:
[0114] The alarm module is used to obtain the current time after determining that the categories of each object contained in the video frame meet the preset violation rules; calculate the difference between the current time and the violation start time, wherein the violation start time is recorded by a timer, and the timer corresponds to the preset violation rules associated with the monitoring camera; if the difference exceeds the preset time, an alarm is triggered.
[0115] Optionally, the device further comprises:
[0116] The second saving module is used to save the detection results of the video frame in which the surveillance camera is pointing to the counter after determining whether the categories of each object contained in the video frame conform to the preset violation rules. The detection results include the results that conform to the preset violation rules obtained based on the video frame in which the surveillance camera is pointing to the counter.
[0117] Optionally, the first acquisition module 201 is specifically configured to acquire a video stream in which the surveillance camera is pointing to the counter; and extract a video frame from the video stream as a video frame in which the surveillance camera is pointing to the counter.
[0118] Optionally, the preset violation rules include at least one of the following: the category of the object to be detected includes cash but does not include human body, the category of the object to be detected includes two open doors, and the category of the object to be detected includes a person.
[0119] The embodiment of the present invention also provides a system for monitoring teller behavior, such as Figure 3 As shown, this may include:
[0120] A processing device 301 and at least one monitoring camera 302, each monitoring camera 302 corresponds to at least one counter;
[0121] For each surveillance camera 302, the surveillance camera 302 is used to collect a video frame of the counter pointed at by the surveillance camera 302, where the counter is where the teller is located;
[0122] The processing device 301 is used to obtain the video frame of the monitoring camera 302 pointing to the counter, and determine the category of each object contained in the video frame through an image detection algorithm; obtain the preset violation rules associated with the monitoring camera 302; determine whether the category of each object contained in the video frame meets the preset violation rules; if so, determine that the teller has violated the rules.
[0123] The specific execution steps of the processing device 301 and the monitoring camera 302 in the system for monitoring teller behavior provided by the embodiment of the present invention have been described in detail in the embodiment of the method for monitoring teller behavior, and will not be repeated here.
[0124] The embodiment of the present invention also provides a processing device, such as Figure 4 As shown, it includes a processor 401, a communication interface 402, a memory 403 and a communication bus 404, wherein the processor 401, the communication interface 402, and the memory 403 communicate with each other through the communication bus 404;
[0125] Memory 403, used for storing computer programs;
[0126] The processor 401 is used to implement the steps of the above-mentioned method for monitoring teller behavior when executing the program stored in the memory 403.
[0127] The communication bus mentioned in the above processing device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.
[0128] The communication interface is used for communication between the above processing device and other devices.
[0129] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.
[0130] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
[0131] In another embodiment of the present invention, a computer-readable storage medium is provided, in which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned methods for monitoring teller behavior are implemented.
[0132] In another embodiment of the present invention, a computer program product including instructions is provided, which, when executed on a computer, enables the computer to execute any of the methods for monitoring teller behavior in the above embodiments.
[0133] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk Solid State Disk (SSD)), etc.
[0134] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.
[0135] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, system, processing device, computer-readable storage medium embodiment and computer program product, since they are basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.
[0136] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.
Claims
1. A method for monitoring teller behavior, characterized in that: include: Acquire a video frame in which the surveillance camera points to a counter, where the teller is located; Determining the category of each object contained in the video frame by an image detection algorithm; Obtaining preset violation rules associated with the surveillance camera; Determining whether the category of each object contained in the video frame complies with the preset violation rules; If so, it is determined that the teller has violated the rules.
2. The method according to claim 1, characterized in that After acquiring the video frame in which the surveillance camera points to the counter, the method further includes: Determining the position information of each object contained in the video frame by an image detection algorithm; Based on the position information of each object, determine the object to be detected that is located in the detection area among the objects; The determining whether the category of each object contained in the video frame complies with the preset violation rule includes: Determine whether the category of the object to be detected conforms to the preset violation rules.
3. The method according to claim 2, characterized in that The step of determining the object to be detected located in the detection area among the objects based on the position information of the objects includes: Acquiring the position information of the pre-marked detection area; The position information of each object is compared with the position information of the detection area, and objects whose position information is within the range of the detection area represented by the position information of the detection area are determined as objects to be detected.
4. The method according to claim 1, characterized in that: The method further comprises: After determining that the category of each object contained in the video frame meets the preset violation rule, obtaining the current time; Calculating a difference between a current time and a violation start time, wherein the violation start time is recorded by a timer corresponding to a preset violation rule associated with the surveillance camera; If the difference exceeds a preset time, an alarm is triggered.
5. The method according to claim 1, characterized in that After determining whether the category of each object contained in the video frame conforms to the preset violation rule, the method further includes: The detection result of the video frame of the surveillance camera pointing to the counter is saved, and the detection result includes a result that complies with the preset violation rule and is obtained based on the video frame of the surveillance camera pointing to the counter.
6. The method according to any one of claims 1 to 5, characterized in that: The step of obtaining a video frame in which the surveillance camera points to the counter includes: Get the video stream of the surveillance camera pointing to the counter; A video frame is extracted from the video stream as a video frame in which the surveillance camera is directed to the counter.
7. The method according to any one of claims 1 to 5, characterized in that: The preset violation rules include at least one of the following: the category of the object to be detected includes cash but does not include human body, the category of the object to be detected includes two open doors, and the category of the object to be detected includes a person.
8. A device for monitoring teller behavior, characterized in that: include: A first acquisition module is used to acquire a video frame of a counter pointed by a surveillance camera, where the counter is where a teller is located; A first determination module, configured to determine the category of each object contained in the video frame by using an image detection algorithm; A second acquisition module, used to acquire a preset violation rule associated with the surveillance camera; A first judgment module, used to judge whether the category of each object contained in the video frame conforms to the preset violation rule; The second determination module is used to determine that the teller has violated the regulations if the conditions are met.
9. A system for monitoring teller behavior, characterized in that: include: A processing device and at least one monitoring camera, each monitoring camera corresponding to at least one counter; For each surveillance camera, the surveillance camera is used to collect a video frame of the counter pointed by the surveillance camera, where the counter is where the teller is located; The processing device is used to obtain a video frame in which the surveillance camera is pointing to the counter, and determine the category of each object contained in the video frame through an image detection algorithm; Obtaining the preset violation rules associated with the surveillance camera; determining whether the categories of the objects contained in the video frame conform to the preset violation rules; and if so, determining that the teller has violated the rules.
10. A processing device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, for implementing the method steps described in any one of claims 1 to 7 when executing a program stored in a memory.
11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method steps described in any one of claims 1 to 7 are implemented.
Citation Information
Patent Citations
Personnel behavior compliance detection method and device and electronic device
CN112668398A
Monitoring method and system for violation operation of super counter
CN113850187A
Abnormal behavior detection method and device for bank outlets
CN115019250A
Personnel violation behavior identification method and device, equipment and storage medium
CN116071784A
Illegal behavior analysis method and device, electronic equipment and computer storage medium
CN116912773A
