CN111814669A - Method and device for identifying abnormal behaviors of bank outlets - Google Patents
Method and device for identifying abnormal behaviors of bank outlets Download PDFInfo
- Publication number
- CN111814669A CN111814669A CN202010650509.6A CN202010650509A CN111814669A CN 111814669 A CN111814669 A CN 111814669A CN 202010650509 A CN202010650509 A CN 202010650509A CN 111814669 A CN111814669 A CN 111814669A
- Authority
- CN
- China
- Prior art keywords
- abnormal behavior
- behavior
- abnormal
- training
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
Abstract
The invention provides a method and a device for identifying abnormal behaviors of bank outlets, wherein the method comprises the following steps: acquiring video data of a designated video monitoring device; decoding the video data and extracting multi-frame pictures; obtaining an identification result of each frame of picture according to each frame of picture and the abnormal behavior identification model; and the abnormal behavior recognition model is obtained by training according to the abnormal behavior training data and the corresponding behavior labels. The device is used for executing the method. The method and the device for identifying the abnormal behaviors of the bank outlets, provided by the embodiment of the invention, improve the efficiency of identifying the abnormal behaviors.
Description
Technical Field
The invention relates to the technical field of image recognition, in particular to a method and a device for recognizing abnormal behaviors of bank outlets.
Background
At present, a video monitoring device is arranged at a bank outlet to monitor the conditions in the outlet.
In the prior art, a video monitoring device arranged in a bank outlet can send video data in a monitoring area to a background for storage, and a manager of the outlet confirms whether an abnormality exists in the monitoring area by checking the video data. By manually viewing video data, it takes a lot of time, is inefficient, and is difficult to monitor in real time. In addition, because the video is checked manually, the condition that the standard is not uniform or the information is omitted is difficult to avoid.
Disclosure of Invention
Aiming at the problems in the prior art, the embodiments of the present invention provide a method and an apparatus for identifying an abnormal behavior of a bank outlet, which can at least partially solve the problems in the prior art.
On one hand, the invention provides a method for identifying abnormal behaviors of bank outlets, which comprises the following steps:
acquiring video data of a designated video monitoring device;
decoding the video data and extracting multi-frame pictures;
obtaining an identification result of each frame of picture according to each frame of picture and the abnormal behavior identification model; and the abnormal behavior recognition model is obtained by training according to the abnormal behavior training data and the corresponding behavior labels.
In another aspect, the present invention provides an apparatus for identifying abnormal behavior of a bank outlet, including:
an acquisition unit configured to acquire video data of a specified video monitoring apparatus;
an extraction unit, configured to decode the video data and extract a plurality of frames of pictures;
the identification unit is used for acquiring an identification result of each frame of picture according to each frame of picture and the abnormal behavior identification model; and the abnormal behavior recognition model is obtained by training according to the abnormal behavior training data and the corresponding behavior labels.
In another aspect, the present invention provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the method for identifying abnormal behavior of a bank outlet according to any one of the above embodiments when executing the computer program.
In still another aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the method for identifying abnormal behavior of a banking outlet according to any one of the above embodiments.
The method and the device for identifying the abnormal behaviors of the bank outlets, provided by the embodiment of the invention, have the advantages that the video data of the preset video monitoring device is obtained, the video data is decoded, the multiple frames of pictures are extracted, the identification result of each frame of picture is obtained according to each frame of picture and the abnormal behavior identification model, the identification result of each frame of picture is rapidly obtained through the abnormal behavior identification model, and the identification efficiency of the abnormal behaviors is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts. In the drawings:
fig. 1 is a schematic flow chart of a method for identifying an abnormal behavior of a banking outlet according to an embodiment of the present invention.
Fig. 2 is a schematic flow chart of a method for identifying abnormal behavior of a banking outlet according to another embodiment of the present invention.
Fig. 3 is a schematic structural diagram of an apparatus for identifying an abnormal behavior at a banking outlet according to an embodiment of the present invention.
Fig. 4 is a schematic structural diagram of an apparatus for identifying an abnormal behavior at a banking outlet according to another embodiment of the present invention.
Fig. 5 is a schematic structural diagram of an apparatus for identifying an abnormal behavior at a banking outlet according to another embodiment of the present invention.
Fig. 6 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention. It should be noted that the embodiments and features of the embodiments in the present application may be arbitrarily combined with each other without conflict.
Fig. 1 is a schematic flow chart of a method for identifying an abnormal behavior of a bank branch according to an embodiment of the present invention, and as shown in fig. 1, the method for identifying an abnormal behavior of a bank branch according to an embodiment of the present invention includes:
s101, acquiring video data of a designated video monitoring device;
specifically, the video monitoring device sends the collected video data to an identification device (hereinafter referred to as an identification device) of abnormal behavior of a bank outlet, and the identification device receives the video data so as to acquire the video data. A plurality of video monitoring devices are preset at a bank outlet, and the video monitoring devices can be appointed to monitor abnormal behaviors. The video monitoring device can be a gun type camera, a dome camera, a pen container type camera and the like, and is arranged according to actual needs, and the embodiment of the invention is not limited. The identification device may be a server or an edge computing terminal, and may be set according to actual needs, which is not limited in the embodiments of the present invention. The edge computing terminal can adopt terminal equipment such as Huacheng small stations and the like.
S102, decoding the video data and extracting multi-frame pictures;
specifically, after obtaining the video data, the identification device decodes the video, and extracts a plurality of pictures from the decoded video data, for example, 1 picture per second, and the setting is performed according to actual needs, which is not limited in the embodiment of the present invention.
S103, obtaining an identification result of each frame of picture according to each frame of picture and the abnormal behavior identification model; and the abnormal behavior recognition model is obtained by training according to the abnormal behavior training data and the corresponding behavior labels.
Specifically, each frame of picture is input into an abnormal behavior identification model by the identification device, and the identification result of each frame of picture can be output through the processing of the abnormal behavior identification model, wherein the identification result is that abnormal behavior exists or abnormal behavior does not exist. The abnormal behavior recognition model is obtained according to abnormal behavior training data and corresponding behavior labels, and the behavior labels are preset and comprise normal behaviors and abnormal behaviors. The abnormal behaviors include, but are not limited to, fighting, falling, violence and the like, and are set according to actual needs, and the embodiment of the invention is not limited.
The method for identifying the abnormal behaviors of the bank outlets, provided by the embodiment of the invention, comprises the steps of obtaining video data of a specified video monitoring device, decoding the video data, extracting multiple frames of pictures, obtaining the identification result of each frame of picture according to each frame of picture and an abnormal behavior identification model, and rapidly obtaining the identification result of each frame of picture through the abnormal behavior identification model, so that the identification efficiency of the abnormal behaviors is improved. In addition, the monitoring cost of the bank outlets is saved because the video data does not need to be checked manually.
Fig. 2 is a schematic flow chart of a method for identifying abnormal behaviors at a banking outlet according to another embodiment of the present invention, and as shown in fig. 2, on the basis of the foregoing embodiments, the step of obtaining an abnormal behavior identification model according to abnormal behavior training data and corresponding behavior label training further includes:
s201, acquiring the abnormal behavior training data and corresponding behavior labels, and dividing the abnormal behavior training data into a training set and a verification set;
specifically, a preset number of frame pictures may be obtained from historical video data through analysis and used as the abnormal behavior training data, the preset number of frame pictures are manually labeled, and a behavior tag corresponding to each frame of picture in the preset number of frame pictures is confirmed, that is, the behavior tag corresponding to each frame of picture is manually determined to be an abnormal behavior or a normal behavior. The identification device may obtain the abnormal behavior training data and the corresponding behavior labels, and then divide the abnormal behavior training data into a training set and a verification set, where the training set is used for training a model, and the verification set is used for verifying the model. The preset number is set according to actual needs, and the embodiment of the invention is not limited.
For example, 70% of the abnormal behavior training data is used as the training set, and 30% of the abnormal behavior training data is used as the validation set.
S202, training an initial model according to the training set and the behavior labels corresponding to the training set to obtain a to-be-determined abnormal behavior recognition model;
specifically, after obtaining the training set, the recognition device performs model training on an initial model according to the training set and a behavior label corresponding to the training set, so as to obtain a to-be-determined abnormal behavior recognition model. The initial model includes, but is not limited to, a retinet model, a ResNet18 model, and the like, and is set according to an actual situation, which is not limited in the embodiments of the present invention.
S203, verifying the to-be-determined abnormal behavior recognition model according to the verification set and the behavior tags corresponding to the verification set to obtain a model verification result;
specifically, after the identification device obtains the identification model of the undetermined abnormal behavior, the identification device inputs the verification set into the identification model of the undetermined abnormal behavior, and outputs an identification result corresponding to the verification set. And comparing the identification result corresponding to each frame of picture in the verification set with the behavior tag corresponding to each frame of picture in the verification set, and counting the number T matched with the corresponding behavior tag in the identification result corresponding to each frame of picture, wherein the number of the pictures in the verification set is Q, and the accuracy of the identification model of the to-be-determined abnormal behavior is T/Q. And if the accuracy rate of the identification model of the undetermined abnormal behavior is smaller than a threshold value, the model verification result is failed. And if the accuracy of the identification model of the undetermined abnormal behavior is greater than or equal to the threshold value, the model verification result is passed. The threshold is set according to practical experience, and the embodiment of the present invention is not limited.
And S204, if the model verification result is known to be passed, taking the identification model of the undetermined abnormal behavior as the identification model of the abnormal behavior.
Specifically, if the identification device learns that the model verification result is passed, the identification device takes the to-be-determined abnormal behavior identification model as the abnormal behavior identification model.
On the basis of the foregoing embodiments, further, the method for identifying an abnormal behavior of a banking outlet according to the embodiment of the present invention further includes:
and if the recognition result of the picture is known to be that abnormal behaviors exist, performing abnormal behavior early warning.
Specifically, if the recognition result is known to be abnormal behavior, the recognition device can notify the related personnel of the bank outlets of the recognition result in a short message or the like, so as to realize the early warning of the abnormal behavior. The related personnel of the bank outlets can process the abnormal behavior in time.
On the basis of the foregoing embodiments, further, the performing an abnormal behavior early warning includes:
and sending the monitoring area of the video monitoring device corresponding to the abnormal behavior.
Specifically, in order to facilitate the relevant personnel at the bank outlets to process the abnormal behavior occurring in time, the identification device may send the monitoring area of the video monitoring device corresponding to the abnormal behavior to the relevant personnel at the bank outlets in the form of short messages or the like, so that the relevant personnel at the bank outlets can know the place where the abnormal behavior occurs. The monitoring area of the video monitoring device is preset and is set according to the actual situation, and the embodiment of the invention is not limited.
Fig. 3 is a schematic structural diagram of an apparatus for identifying an abnormal behavior of a bank outlet according to an embodiment of the present invention, and as shown in fig. 3, the apparatus for identifying an abnormal behavior of a bank outlet according to an embodiment of the present invention includes an obtaining unit 301, an extracting unit 302, and an identifying unit 303, where:
the acquiring unit 301 is configured to acquire video data of a specified video monitoring apparatus; the extracting unit 302 is configured to decode the video data and extract multiple frames of pictures; the identification unit 303 is configured to obtain an identification result of each frame of picture according to each frame of picture and the abnormal behavior identification model; and the abnormal behavior recognition model is obtained by training according to the abnormal behavior training data and the corresponding behavior labels.
Specifically, the video monitoring apparatus sends the acquired video data to the obtaining unit 301, and the obtaining unit 301 receives the video data, so as to obtain the video data. A plurality of video monitoring devices are preset at a bank outlet, and the video monitoring devices can be appointed to monitor abnormal behaviors. The video monitoring device can be a gun type camera, a dome camera, a pen container type camera and the like, and is arranged according to actual needs, and the embodiment of the invention is not limited. The identification device may be a server or an edge computing terminal, and may be set according to actual needs, which is not limited in the embodiments of the present invention. The edge computing terminal can adopt terminal equipment such as Huacheng small stations and the like.
After obtaining the video data, the identifying unit 303 decodes the video, and extracts a plurality of frames of pictures from the decoded video data, for example, 1 frame of picture per second, and sets the pictures according to actual needs, which is not limited in the embodiment of the present invention.
The identification unit 303 inputs each frame of picture into the abnormal behavior identification model, and the identification result of each frame of picture can be output through the processing of the abnormal behavior identification model, wherein the identification result is that an abnormal behavior exists or no abnormal behavior exists. The abnormal behavior recognition model is obtained according to abnormal behavior training data and corresponding behavior labels, and the behavior labels are preset and comprise normal behaviors and abnormal behaviors. The abnormal behaviors include, but are not limited to, fighting, falling, violence and the like, and are set according to actual needs, and the embodiment of the invention is not limited.
The identification device for the abnormal behaviors of the bank outlets, provided by the embodiment of the invention, is used for acquiring the video data of the appointed video monitoring device, decoding the video data and extracting the multiple frames of pictures, acquiring the identification result of each frame of picture according to each frame of picture and the abnormal behavior identification model, and rapidly acquiring the identification result of each frame of picture through the abnormal behavior identification model, so that the identification efficiency of the abnormal behaviors is improved. In addition, the monitoring cost of the bank outlets is saved because the video data does not need to be checked manually.
Fig. 4 is a schematic structural diagram of an apparatus for identifying abnormal behavior of a bank outlet according to another embodiment of the present invention, as shown in fig. 4, on the basis of the foregoing embodiments, further, the apparatus for identifying abnormal behavior of a bank outlet according to an embodiment of the present invention further includes a dividing unit 304, a training unit 305, a verification unit 306, and an acting unit 307, where:
the dividing unit 304 is configured to obtain the abnormal behavior training data and corresponding behavior labels, and divide the abnormal behavior training data into a training set and a verification set; the training unit 305 is configured to train an initial model according to the training set and the behavior labels corresponding to the training set, and obtain a to-be-determined abnormal behavior recognition model; the verification unit 306 is configured to verify the to-be-determined abnormal behavior identification model according to the verification set and the behavior tag corresponding to the verification set, so as to obtain a model verification result; the acting unit 307 is configured to, after it is known that the model verification result is passed, use the pending abnormal behavior identification model as the abnormal behavior identification model.
Specifically, a preset number of frame pictures may be obtained from historical video data through analysis and used as the abnormal behavior training data, the preset number of frame pictures are manually labeled, and a behavior tag corresponding to each frame of picture in the preset number of frame pictures is confirmed, that is, the behavior tag corresponding to each frame of picture is manually determined to be an abnormal behavior or a normal behavior. The dividing unit 304 may obtain the abnormal behavior training data and the corresponding behavior labels, and then divide the abnormal behavior training data into a training set and a verification set, where the training set is used for training the model, and the verification set is used for verifying the model. The preset number is set according to actual needs, and the embodiment of the invention is not limited.
After obtaining the training set, the training unit 305 performs model training on the initial model according to the training set and the behavior labels corresponding to the training set, so as to obtain a to-be-determined abnormal behavior recognition model. The initial model includes, but is not limited to, a retinet model, a ResNet18 model, etc., and is set according to actual conditions, which is not limited in the embodiments of the present invention.
After obtaining the identification model of the pending abnormal behavior, the verification unit 306 inputs the verification set into the identification model of the pending abnormal behavior, and outputs an identification result corresponding to the verification set. And comparing the identification result corresponding to each frame of picture in the verification set with the behavior tag corresponding to each frame of picture in the verification set, and counting the number T matched with the corresponding behavior tag in the identification result corresponding to each frame of picture, wherein the number of the pictures in the verification set is Q, and the accuracy of the identification model of the to-be-determined abnormal behavior is T/Q. And if the accuracy rate of the identification model of the undetermined abnormal behavior is smaller than a threshold value, the model verification result is failed. And if the accuracy of the identification model of the undetermined abnormal behavior is greater than or equal to the threshold value, the model verification result is passed. The threshold is set according to practical experience, and the embodiment of the present invention is not limited.
If the model verification result is known to be passed as unit 307, the pending abnormal behavior recognition model is taken as the abnormal behavior recognition model.
Fig. 5 is a schematic structural diagram of an apparatus for identifying abnormal behavior of a bank outlet according to another embodiment of the present invention, as shown in fig. 5, on the basis of the foregoing embodiments, further, the apparatus for identifying abnormal behavior of a bank outlet according to the embodiment of the present invention further includes an early warning unit 308, where:
the early warning unit 308 is configured to perform early warning on an abnormal behavior after knowing that the identification result of the picture is that the abnormal behavior exists.
Specifically, if the early warning unit 308 learns that the identification result is the abnormal behavior, the identification result may be notified to relevant people of a bank outlet in a manner of a short message or the like, so as to implement early warning of the abnormal behavior. The related personnel of the bank outlets can process the abnormal behavior in time.
On the basis of the foregoing embodiments, further, the early warning unit 308 is specifically configured to:
and sending the monitoring area of the video monitoring device corresponding to the abnormal behavior.
Specifically, in order to facilitate the relevant personnel at the bank outlets to process the abnormal behavior occurring in time, the early warning unit 308 may send the monitoring area of the video monitoring device corresponding to the abnormal behavior to the relevant personnel at the bank outlets in a manner of short messages or the like, so that the relevant personnel at the bank outlets can know the place where the abnormal behavior occurs. The monitoring area of the video monitoring device is preset and is set according to the actual situation, and the embodiment of the invention is not limited.
The embodiment of the apparatus provided in the embodiment of the present invention may be specifically configured to execute the processing flows of the above method embodiments, and the functions of the apparatus are not described herein again, and refer to the detailed description of the above method embodiments.
Fig. 6 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 6, the electronic device may include: a processor (processor)601, a communication Interface (Communications Interface)602, a memory (memory)603 and a communication bus 604, wherein the processor 601, the communication Interface 602 and the memory 603 complete communication with each other through the communication bus 604. The processor 601 may call logic instructions in the memory 603 to perform the following method: acquiring video data of a designated video monitoring device; decoding the video data and extracting multi-frame pictures; obtaining an identification result of each frame of picture according to each frame of picture and the abnormal behavior identification model; and the abnormal behavior recognition model is obtained by training according to the abnormal behavior training data and the corresponding behavior labels.
In addition, the logic instructions in the memory 603 may be implemented in the form of software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The present embodiment discloses a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, enable the computer to perform the method provided by the above-mentioned method embodiments, for example, comprising: acquiring video data of a designated video monitoring device; decoding the video data and extracting multi-frame pictures; obtaining an identification result of each frame of picture according to each frame of picture and the abnormal behavior identification model; and the abnormal behavior recognition model is obtained by training according to the abnormal behavior training data and the corresponding behavior labels.
The present embodiment provides a computer-readable storage medium, which stores a computer program, where the computer program causes the computer to execute the method provided by the above method embodiments, for example, the method includes: acquiring video data of a designated video monitoring device; decoding the video data and extracting multi-frame pictures; obtaining an identification result of each frame of picture according to each frame of picture and the abnormal behavior identification model; and the abnormal behavior recognition model is obtained by training according to the abnormal behavior training data and the corresponding behavior labels.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In the description herein, reference to the description of the terms "one embodiment," "a particular embodiment," "some embodiments," "for example," "an example," "a particular example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method for identifying abnormal behaviors of bank outlets is characterized by comprising the following steps:
acquiring video data of a designated video monitoring device;
decoding the video data and extracting multi-frame pictures;
obtaining an identification result of each frame of picture according to each frame of picture and the abnormal behavior identification model; and the abnormal behavior recognition model is obtained by training according to the abnormal behavior training data and the corresponding behavior labels.
2. The method of claim 1, wherein the step of obtaining the abnormal behavior recognition model according to the abnormal behavior training data and the corresponding behavior label training comprises:
acquiring the abnormal behavior training data and corresponding behavior labels, and dividing the abnormal behavior training data into a training set and a verification set;
training an initial model according to the training set and the behavior labels corresponding to the training set to obtain a to-be-determined abnormal behavior recognition model;
verifying the to-be-determined abnormal behavior identification model according to the verification set and the behavior tags corresponding to the verification set to obtain a model verification result;
and if the model verification result is known to be passed, taking the identification model of the to-be-determined abnormal behavior as the identification model of the abnormal behavior.
3. The method of claim 1 or 2, further comprising:
and if the recognition result of the picture is known to be that abnormal behaviors exist, performing abnormal behavior early warning.
4. The method of claim 3, wherein the performing abnormal behavior pre-warning comprises:
and sending the monitoring area of the video monitoring device corresponding to the abnormal behavior.
5. An identification device for abnormal behaviors of bank outlets is characterized by comprising:
an acquisition unit configured to acquire video data of a specified video monitoring apparatus;
an extraction unit, configured to decode the video data and extract a plurality of frames of pictures;
the identification unit is used for acquiring an identification result of each frame of picture according to each frame of picture and the abnormal behavior identification model; and the abnormal behavior recognition model is obtained by training according to the abnormal behavior training data and the corresponding behavior labels.
6. The apparatus of claim 5, further comprising:
the dividing unit is used for acquiring the abnormal behavior training data and the corresponding behavior labels and dividing the abnormal behavior training data into a training set and a verification set;
the training unit is used for training an initial model according to the training set and the behavior labels corresponding to the training set to obtain a to-be-determined abnormal behavior recognition model;
the verification unit is used for verifying the to-be-determined abnormal behavior identification model according to the verification set and the behavior tags corresponding to the verification set to obtain a model verification result;
and the unit is used for taking the identification model of the undetermined abnormal behavior as the identification model of the abnormal behavior after the model verification result is known to be passed.
7. The apparatus of claim 5 or 6, further comprising:
and the early warning unit is used for carrying out early warning on the abnormal behaviors after knowing that the identification result of the picture is that the abnormal behaviors exist.
8. The device of claim 7, wherein the early warning unit is specifically configured to:
and sending the monitoring area of the video monitoring device corresponding to the abnormal behavior.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method of any of claims 1 to 4 are implemented when the computer program is executed by the processor.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010650509.6A CN111814669A (en) | 2020-07-08 | 2020-07-08 | Method and device for identifying abnormal behaviors of bank outlets |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010650509.6A CN111814669A (en) | 2020-07-08 | 2020-07-08 | Method and device for identifying abnormal behaviors of bank outlets |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111814669A true CN111814669A (en) | 2020-10-23 |
Family
ID=72843213
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010650509.6A Pending CN111814669A (en) | 2020-07-08 | 2020-07-08 | Method and device for identifying abnormal behaviors of bank outlets |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111814669A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113723169A (en) * | 2021-04-26 | 2021-11-30 | 中国科学院自动化研究所 | Behavior identification method, system and equipment based on SlowFast |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109241946A (en) * | 2018-10-11 | 2019-01-18 | 平安科技（深圳）有限公司 | Abnormal behaviour monitoring method, device, computer equipment and storage medium |
| CN109241418A (en) * | 2018-08-22 | 2019-01-18 | 中国平安人寿保险股份有限公司 | Abnormal user recognition methods and device, equipment, medium based on random forest |
| CN109993122A (en) * | 2019-04-02 | 2019-07-09 | 中国石油大学(华东) | A kind of pedestrian based on depth convolutional neural networks multiplies staircase anomaly detection method |
-
2020
- 2020-07-08 CN CN202010650509.6A patent/CN111814669A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109241418A (en) * | 2018-08-22 | 2019-01-18 | 中国平安人寿保险股份有限公司 | Abnormal user recognition methods and device, equipment, medium based on random forest |
| CN109241946A (en) * | 2018-10-11 | 2019-01-18 | 平安科技（深圳）有限公司 | Abnormal behaviour monitoring method, device, computer equipment and storage medium |
| CN109993122A (en) * | 2019-04-02 | 2019-07-09 | 中国石油大学(华东) | A kind of pedestrian based on depth convolutional neural networks multiplies staircase anomaly detection method |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113723169A (en) * | 2021-04-26 | 2021-11-30 | 中国科学院自动化研究所 | Behavior identification method, system and equipment based on SlowFast |
| CN113723169B (en) * | 2021-04-26 | 2024-04-30 | 中国科学院自动化研究所 | SlowFast-based behavior recognition method, system and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3451328B1 (en) | Method and apparatus for verifying information | |
| CN103209153B (en) | Message treatment method, Apparatus and system | |
| CN108923972B (en) | Weight-reducing flow prompting method, device, server and storage medium | |
| CN112200081A (en) | Abnormal behavior identification method and device, electronic equipment and storage medium | |
| CN106571942B (en) | Configuration data updating method, client and server | |
| CN110138794A (en) | A kind of counterfeit website identification method, device, equipment and readable storage medium storing program for executing | |
| CN112200556A (en) | Transfer processing method and device of automatic teller machine | |
| CN111126928A (en) | Method and device for auditing release content | |
| CN111814669A (en) | Method and device for identifying abnormal behaviors of bank outlets | |
| CN115208835A (en) | API classification method, device, electronic equipment, medium and product | |
| CN111325078A (en) | Face recognition method, face recognition device and storage medium | |
| CN110602483B (en) | Video fault determination method, device and computer readable storage medium | |
| CN110210215B (en) | Virus detection method and related device | |
| CN111814670A (en) | Special customer identification method and device for bank outlets | |
| CN115424253A (en) | License plate recognition method and device, electronic equipment and storage medium | |
| CN114140850A (en) | Face recognition method and device and electronic equipment | |
| CN111885354A (en) | Service improvement discrimination method and device for bank outlets | |
| CN112580344A (en) | Information supervision method, device, equipment, storage medium and program product | |
| CN112381058A (en) | Black and white list control method and device based on pedestrian re-identification | |
| CN110990665A (en) | Data processing method, device, system, electronic equipment and storage medium | |
| CN114782884B (en) | Enhanced identification method and device based on security video monitoring | |
| CN106547679B (en) | Script management method and script management platform | |
| CN113888054B (en) | Construction method and device of business model, storage medium and processor | |
| CN116561021A (en) | Video data processing method and device, electronic equipment and storage medium | |
| CN109299782B (en) | Data processing method and device based on deep learning model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |