Abnormality determination method, device, electronic device and storage medium

Abstract

The present invention provides an abnormality determination method, device, electronic device, and storage medium, which relate to the field of computer technology and solve the technical problem that determining whether an abnormal situation exists by manual monitoring may require a long period of high concentration of attention, which affects the effectiveness of abnormality determination. The method includes: obtaining an image to be identified included in a video stream to be identified corresponding to a target task; inputting the image to be identified into a first target detection model to obtain the area where each first detection frame is located in at least one first detection frame; inputting the image to be identified into a second target detection model to obtain the area where each second detection frame is located in at least one second detection frame; when the first number and the second number are equal, determining the matching parameters of each object based on the area where each first detection frame is located and the area where each second detection frame is located; when the matching parameters do not meet a preset condition, determining the target task as an abnormal task.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to an abnormality determination method, device, electronic device and storage medium. Background Art

[0002] Currently, manual monitoring can be used to determine whether there are any abnormalities in the operators or the operation site.

[0003] However, the above-mentioned manual monitoring method may require high concentration for a long time, which may cause visual fatigue and affect the effectiveness of abnormality determination. Summary of the Invention

[0004] The present invention provides an abnormality determination method, device, electronic device and storage medium, which solves the technical problem that manual monitoring to determine whether an abnormal situation exists may require a long period of high concentration of attention, affecting the effectiveness of abnormality determination.

[0005] In a first aspect, the present invention provides an abnormality determination method, comprising: obtaining an image to be identified included in a video stream to be identified corresponding to a target task; inputting the image to be identified into a first target detection model to obtain at least one first detection frame and the area where each first detection frame in the at least one first detection frame is located, and each first detection frame is used to characterize each target object; inputting the image to be identified into a second target detection model to obtain at least one second detection frame and the area where each second detection frame in the at least one second detection frame is located, and each second detection frame is used to characterize each object; when the first number is equal to the second number, determining the matching parameter of each object according to the area where each first detection frame is located and the area where each second detection frame is located, the first number is the number of the at least one first detection frame, and the second number is the number of the at least one second detection frame; when the matching parameter does not meet the preset conditions, determining the target task as an abnormal task.

[0006] Optionally, the above-mentioned determining the matching parameters of each object based on the area where each first detection frame is located and the area where each second detection frame is located specifically includes: determining a first intersection and a first union, the first intersection being the intersection of the first area and the second area, the first union being the union of the first area and the second area, the first area being the area where the i-th first detection frame in the at least one first detection frame is located, the second area being the area where the i-th second detection frame in the at least one second detection frame is located, and i is a positive integer greater than or equal to 1; determining the matching parameters of the i-th object based on the first intersection and the first union, the i-th object being the object represented by the i-th second detection frame.

[0007] Optionally, determining the matching parameter of the i-th object based on the first intersection and the first union specifically includes: determining that the matching parameter of the i-th object satisfies the following formula:

[0008]

[0009] Among them, O i represents the matching parameter of the i-th object, S1 represents the first intersection, S1' represents the first union, and i is a positive integer greater than or equal to 1.

[0010] Optionally, the abnormality determination method further includes: when the first number is smaller than the second number, determining that the target task is an abnormal task.

[0011] Optionally, the abnormality determination method further includes: determining that the target task is an abnormal task when the duration for which the target object is continuously absent in the video stream to be identified is greater than or equal to a duration threshold.

[0012] In a second aspect, the present invention provides an abnormality determination device, comprising: an acquisition module, a processing module, and a determination module; the acquisition module is used to acquire an image to be identified included in a video stream to be identified corresponding to a target task; the processing module is used to input the image to be identified into a first target detection model to obtain at least one first detection frame and the area where each first detection frame in the at least one first detection frame is located, and each first detection frame is used to characterize each target object; the processing module is also used to input the image to be identified into a second target detection model to obtain at least one second detection frame and the area where each second detection frame in the at least one second detection frame is located, and each second detection frame is used to characterize each object; the determination module is used to determine the matching parameters of each object based on the area where each first detection frame is located and the area where each second detection frame is located when the first number is equal to the second number, the first number being the number of the at least one first detection frame, and the second number being the number of the at least one second detection frame; the determination module is also used to determine that the target task is an abnormal task when the matching parameters do not meet a preset condition.

[0013] Optionally, the determination module is specifically used to determine a first intersection and a first union, the first intersection being the intersection of the first area and the second area, the first union being the union of the first area and the second area, the first area being the area where the i-th first detection frame in the at least one first detection frame is located, and the second area being the area where the i-th second detection frame in the at least one second detection frame is located, where i is a positive integer greater than or equal to 1; the determination module is also specifically used to determine the matching parameters of the i-th object based on the first intersection and the first union, the i-th object being the object represented by the i-th second detection frame.

[0014] Optionally, the determining module is further configured to determine whether the matching parameter of the i-th object satisfies the following formula:

[0015]

[0016] Among them, O i represents the matching parameter of the i-th object, S1 represents the first intersection, S1' represents the first union, and i is a positive integer greater than or equal to 1.

[0017] Optionally, the determination module is further configured to determine that the target task is an abnormal task when the first number is smaller than the second number.

[0018] Optionally, the determination module is further configured to determine that the target task is an abnormal task if a duration during which the target object is continuously absent from the video stream to be identified is greater than or equal to a duration threshold.

[0019] In a third aspect, the present invention provides an electronic device comprising: a processor and a memory configured to store processor-executable instructions; wherein the processor is configured to execute the instructions to implement any one of the optional abnormality determination methods in the first aspect above.

[0020] In a fourth aspect, the present invention provides a computer-readable storage medium having instructions stored thereon. When the instructions in the computer-readable storage medium are executed by an electronic device, the electronic device is enabled to execute any one of the optional abnormality determination methods in the first aspect above.

[0021] The present invention provides an abnormality determination method, device, electronic device and storage medium. The electronic device can obtain an image to be identified included in a video stream to be identified corresponding to a target task; then the electronic device inputs the image to be identified into a first target detection model to obtain at least one first detection frame and the area where each first detection frame in the at least one first detection frame is located, and inputs the image to be identified into a second target detection model to obtain at least one second detection frame and the area where each second detection frame in the at least one second detection frame is located; when the first number is equal to the second number, it means that each object included in the image to be identified is a target object, and the electronic device can then determine whether the matching parameters of each object meet a preset condition; when the matching parameters do not meet the preset condition, it means that the degree of matching between the area where the second detection frame corresponding to an object is located and the area where the first detection frame corresponding to the target object corresponding to the object is located is low, that is, the object and the target object are not the same object, and at this time the electronic device can determine that the target task is an abnormal task, can accurately determine whether the target task is an abnormal task, and can improve the effectiveness of abnormality determination. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for describing the embodiments or the prior art.

[0023] Figure 1 A schematic diagram of a flow chart of an abnormality determination method provided by an embodiment of the present invention;

[0024] Figure 2 A schematic flow chart of another abnormality determination method provided by an embodiment of the present invention;

[0025] Figure 3 A schematic flow chart of another abnormality determination method provided by an embodiment of the present invention;

[0026] Figure 4 A schematic flow chart of another abnormality determination method provided by an embodiment of the present invention;

[0027] Figure 5 A schematic flow chart of another abnormality determination method provided by an embodiment of the present invention;

[0028] Figure 6 A schematic structural diagram of an abnormality determination device provided by an embodiment of the present invention;

[0029] Figure 7 A schematic structural diagram of another abnormality determination device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0030] The following describes in detail the abnormality determination method, device, electronic device, and storage medium provided by the embodiments of the present invention with reference to the accompanying drawings.

[0031] The terms "first" and "second" in the specification and drawings of this application are used to distinguish different objects rather than to describe a specific order of objects. For example, the first area and the second area are used to distinguish different areas rather than to describe a specific order of areas.

[0032] Furthermore, the terms "including," "having," and any variations thereof, mentioned in the description of this application are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or units is not limited to the listed steps or units, but may optionally include other steps or units not listed, or may optionally include other steps or units inherent to the process, method, product, or apparatus.

[0033] It should be noted that in the embodiments of the present invention, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present invention should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0034] The term "and / or" used in this application includes using either of the two methods or using both methods simultaneously.

[0035] In the description of the present application, unless otherwise specified, “plurality” means two or more.

[0036] Based on the description in the background technology, in the related art, determining whether there is an abnormality in the operator or the operation site through manual monitoring may require a long period of high concentration of attention, which will cause visual fatigue and affect the effectiveness of abnormality determination. Based on this, an embodiment of the present invention provides an abnormality determination method, device, electronic device and storage medium. When the matching parameters of the object do not meet the preset conditions, it means that the area where the second detection frame corresponding to the object is located and the area where the first detection frame corresponding to the target object corresponding to the object is located have a low degree of matching, that is, the object and the target object are not the same object. At this time, the electronic device can determine that the target task is an abnormal task, can accurately determine whether the target task is an abnormal task, and can improve the effectiveness of abnormality determination.

[0037] Exemplarily, the electronic device that performs the abnormality determination method provided in the embodiment of the present invention can be a mobile phone, a tablet computer, a desktop computer, a laptop computer, a handheld computer, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a cellular phone, a personal digital assistant (PDA), an augmented reality (AR) or virtual reality (VR) device. The embodiment of the present invention does not impose any special restrictions on the specific form of the electronic device. It can interact with the user through one or more methods such as a keyboard, a touchpad, a touch screen, a remote control, voice interaction, or a handwriting device.

[0038] like Figure 1 As shown, the abnormality determination method provided by the embodiment of the present invention may include S101-S105.

[0039] S101: The electronic device obtains an image to be recognized included in a video stream to be recognized corresponding to a target task.

[0040] It should be understood that the video stream to be identified is a video stream generated (or corresponding) when the target task is executed, and the video stream to be identified may be one or more video streams corresponding to the target task.

[0041] It is understandable that the above-mentioned image to be recognized may be one or more images included in the video stream to be recognized. The electronic device may perform frame extraction processing on the video stream to be recognized to obtain the image to be recognized.

[0042] For example, the target task may be an oil unloading task at an oil unloading site.

[0043] S102: The electronic device inputs the image to be recognized into a first object detection model to obtain at least one first detection frame and an area where each first detection frame in the at least one first detection frame is located.

[0044] Each first detection frame is used to represent each target object.

[0045] It should be understood that the first target detection model is used to identify the region where each target object included in an image (e.g., the image to be identified) is located. Specifically, one of the at least one first detection frame is used to represent (or correspond to) a target object included in the image to be identified, and the region where the first detection frame is located can also be understood as the region where the target object is located.

[0046] Exemplarily, the target objects in the embodiments of the present disclosure may include carrier drivers and oil unloading employees.

[0047] S103: The electronic device inputs the image to be recognized into a second object detection model to obtain at least one second detection frame and an area where each second detection frame in the at least one second detection frame is located.

[0048] Each second detection frame is used to represent each object.

[0049] It should be understood that the second object detection model is used to identify the region where each object included in an image (e.g., the image to be identified) is located. Specifically, one of the at least one second detection frame is used to represent (or correspond to) an object included in the image to be identified, and the region where the second detection frame is located can also be understood as the region where the object is located.

[0050] S104: When the first number is equal to the second number, the electronic device determines a matching parameter for each object according to the area where each first detection frame is located and the area where each second detection frame is located.

[0051] The first number is the number of the at least one first detection frame, and the second number is the number of the at least one second detection frame.

[0052] In conjunction with the description of the above embodiment, it should be understood that one first detection box is used to represent one target object, and one second detection box is used to represent one object. The first number can also be understood as the number of target objects included in the image to be recognized, and the second number can also be understood as the number of objects included in the image to be recognized.

[0053] In an embodiment of the present invention, the electronic device can determine whether the first number is equal to the second number. If the first number is equal to the second number, it indicates that the number of target objects included in the image to be identified is equal to the number of objects included in the image to be identified, and the target objects included in the image to be identified are the objects included in the image to be identified, that is, one target object corresponds to one object, and each object included in the image to be identified is a target object. In this case, the electronic device can determine the matching parameters for each object based on the area where each first detection frame is located and the area where each second detection frame is located.

[0054] In conjunction with the description of the above embodiment, it should be understood that the area within a first detection frame is the area within a target object, and the area within a second detection frame is the area within an object. The electronic device determines the matching parameters for each object based on the area within each first detection frame and the area within each second detection frame. This can also be understood as the electronic device determining the matching parameters for each object based on the area within each target object and the area within each object.

[0055] It can be understood that when the first number and the second number are equal, it indicates that each object included in the image to be recognized is a target object. That is, the electronic device determines the matching parameters for each object based on the area where each first detection frame is located and the area where each second detection frame is located. It can also be understood that the electronic device determines the matching parameters for each target object based on the area where each first detection frame is located and the area where each second detection frame is located.

[0056] S105: When the matching parameters do not meet the preset conditions, the electronic device determines that the target task is an abnormal task.

[0057] It should be understood that the matching parameters are matching parameters for each object (or each target object) described above. The matching parameters of an object are used to represent the degree of match between the area where the object is located in the image to be identified (or the area where the second detection frame corresponding to the object is located) and the area where the target object corresponding to the object is located in the image to be identified (i.e., the area where the first detection frame corresponding to the target object is located). The electronic pen can determine whether the matching parameters meet the preset conditions.

[0058] When the above matching parameters do not meet the preset conditions, it means that the degree of matching between the area where the second detection frame corresponding to an object is located and the area where the first detection frame corresponding to the target object corresponding to the object is located is low, that is, the object and the target object are not the same object. At this time, the electronic device can determine that the target task is an abnormal task.

[0059] In an optional implementation, when the matching parameters meet the preset conditions, it indicates that the degree of matching between the area where the second detection frame corresponding to the object is located and the area where the first detection frame corresponding to the target object corresponding to the object is located is high, that is, the object and the target object are the same object. At this time, the electronic device can determine that the target task is a normal task.

[0060] The technical solution provided by the above embodiment can at least bring the following beneficial effects: It can be seen from S101-S105 that: the electronic device can obtain the image to be identified included in the video stream to be identified corresponding to the target task; then the electronic device inputs the image to be identified into the first target detection model to obtain at least one first detection frame and the area where each first detection frame is located in the at least one first detection frame, and inputs the image to be identified into the second target detection model to obtain at least one second detection frame and the area where each second detection frame is located in the at least one second detection frame; when the first number is equal to the second number, it means that each object included in the image to be identified is a target object, and at this time the electronic device can determine whether the matching parameter of each object meets the preset condition; when the matching parameter does not meet the preset condition, it means that the degree of matching between the area where the second detection frame corresponding to an object is located and the area where the first detection frame corresponding to the target object corresponding to the object is located is low, that is, the object and the target object are not the same object, and at this time the electronic device can determine that the target task is an abnormal task, can accurately determine whether the target task is an abnormal task, and can improve the effectiveness of abnormal determination.

[0061] Combine Figure 1 ,like Figure 2 As shown, in one implementation of the embodiment of the present invention, the electronic device determines the matching parameters of each object according to the area where each first detection frame is located and the area where each second detection frame is located, which may specifically include S1041-S1042.

[0062] S1041: The electronic device determines a first intersection and a first union.

[0063] Among them, the first intersection is the intersection of the first area and the second area, the first union is the union of the first area and the second area, the first area is the area where the i-th first detection frame in the above-mentioned at least one first detection frame is located, and the second area is the area where the i-th second detection frame in the above-mentioned at least one second detection frame is located, and i is a positive integer greater than or equal to 1.

[0064] It should be understood that i≤M, where M is the first number (or second number) mentioned above.

[0065] It can be understood that the first intersection is used to represent the overlapping portion of the first area and the second area, and the first union is used to represent the portion composed of the first area and the second area.

[0066] S1042: The electronic device determines a matching parameter of the i-th object according to the first intersection and the first union.

[0067] The i-th object is the object represented by the i-th second detection frame.

[0068] In an embodiment of the present invention, since the above-mentioned first number is equal to the second number, the matching parameter of the i-th object can also be understood as the matching parameter of the i-th target object, and the i-th target object is the target object represented by the above-mentioned i-th first detection frame.

[0069] In combination with the description of the above embodiments, it should be understood that since the first intersection is used to represent the overlapping part of the first area and the second area, and the first union is used to represent the part composed of the first area and the second area, the electronic device can accurately determine the matching parameters of the i-th object based on the first intersection and the first union, and thus can accurately determine whether the target task is an abnormal task.

[0070] At this point, the electronic device can determine the matching parameters of each of the above objects (or each target object) based on the description in the above embodiments.

[0071] Combine Figure 2 ,like Figure 3 As shown, in one implementation of the embodiment of the present invention, the electronic device determines the matching parameter of the i-th object based on the first intersection and the first union, specifically including S1042a. S1042a, the electronic device determines that the matching parameter of the i-th object satisfies the following formula:

[0072]

[0073] Among them, O i represents the matching parameter of the i-th object, S1 represents the first intersection, S1' represents the first union, and i is a positive integer greater than or equal to 1.

[0074] It should be understood that the matching parameter of the i-th object can be understood as the intersection over union (IOU) of the i-th object.

[0075] It is understandable that, when the matching parameter of the i-th object is the IOU of the i-th object, the above-mentioned preset condition may be an IOU threshold. When the IOU of the i-th object is less than the IOU threshold, the electronic device may determine that the matching parameter of the i-th object does not meet the preset condition.

[0076] In an optional implementation manner, the electronic device may also determine the product of the first intersection and the first union as the matching parameter of the i-th object.

[0077] Combine Figure 1 ,like Figure 4 As shown, the abnormality determination method provided by the embodiment of the present invention further includes S106.

[0078] S106: When the first number is smaller than the second number, the electronic device determines that the target task is an abnormal task.

[0079] In conjunction with the description of the above embodiment, it should be understood that the first number is the number of the at least one first detection frame, which can also be understood as the number of target objects included in the image to be recognized. The second number is the number of the at least one second detection frame, which can also be understood as the number of objects included in the image to be recognized.

[0080] In this embodiment of the present invention, if the first number is less than the second number, it indicates that the number of target objects included in the image to be recognized is less than the number of objects included in the image to be recognized. That is, the image to be recognized includes not only the target object but also other objects (i.e., objects included in the image to be recognized other than the target object). These other objects can also be understood as abnormal objects. In this case, the electronic device can determine that the target task is an abnormal task.

[0081] Combine Figure 1 ,like Figure 5 As shown, the abnormality determination method provided by the embodiment of the present invention further includes S107.

[0082] S107: When the target object is not continuously present in the video to be identified for a period greater than or equal to a duration threshold, the electronic device determines that the target task is an abnormal task.

[0083] In conjunction with the description of the above embodiment, it should be understood that the video to be identified may include one or more images. The continuous absence of the target object in the video to be identified indicates that the target object is not present in at least two consecutive images in the video to be identified. When the duration of the continuous absence of the target object in the video to be identified is greater than or equal to the duration threshold, it indicates that the continuous absence of the target object in the video to be identified is long, that is, the target object has not appeared for a long time. At this time, the electronic device can determine that the target task is an abnormal task.

[0084] In the embodiments of the present invention, electronic devices, etc., can be divided into functional modules according to the above-mentioned method examples. For example, each functional module can be divided according to each function, or two or more functions can be integrated into a processing module. The above-mentioned integrated modules can be implemented in the form of hardware or software functional modules. It should be noted that the division of modules in the embodiments of the present invention is schematic and is only a logical functional division. In actual implementation, other division methods may be used.

[0085] In the case of dividing each functional module into corresponding functional modules, Figure 6 A possible structural diagram of the abnormality determination device involved in the above embodiment is shown. Figure 6 As shown, the abnormality determination device 10 may include: an acquisition module 101 , a processing module 102 and a determination module 103 .

[0086] The acquisition module 101 is used to acquire the image to be recognized included in the video stream to be recognized corresponding to the target task.

[0087] The processing module 102 is configured to input the image to be identified into a first target detection model to obtain at least one first detection frame and an area where each first detection frame in the at least one first detection frame is located, wherein each first detection frame is used to represent each target object.

[0088] The processing module 102 is further configured to input the image to be identified into a second target detection model to obtain at least one second detection frame and an area where each second detection frame in the at least one second detection frame is located, wherein each second detection frame is used to represent each object.

[0089] Determination module 103 is used to determine the matching parameters of each object based on the area where each first detection frame is located and the area where each second detection frame is located when the first number is equal to the second number, the first number being the number of the at least one first detection frame, and the second number being the number of the at least one second detection frame.

[0090] The determination module 103 is further configured to determine that the target task is an abnormal task when the matching parameter does not meet a preset condition.

[0091] Optionally, the determination module 103 is specifically used to determine a first intersection and a first union, where the first intersection is the intersection of the first area and the second area, the first union is the union of the first area and the second area, the first area is the area where the i-th first detection frame in the at least one first detection frame is located, and the second area is the area where the i-th second detection frame in the at least one second detection frame is located, where i is a positive integer greater than or equal to 1.

[0092] The determination module 103 is further configured to determine a matching parameter of an i-th object according to the first intersection and the first union, where the i-th object is the object represented by the i-th second detection frame.

[0093] Optionally, the determination module 103 is further configured to determine whether the matching parameter of the i-th object satisfies the following formula:

[0094]

[0095] Among them, O i represents the matching parameter of the i-th object, S1 represents the first intersection, S1' represents the first union, and i is a positive integer greater than or equal to 1.

[0096] Optionally, the determination module 103 is further configured to determine that the target task is an abnormal task when the first number is smaller than the second number.

[0097] Optionally, the determination module 103 is further configured to determine that the target task is an abnormal task if the duration for which the target object is continuously absent in the video stream to be identified is greater than or equal to a duration threshold.

[0098] In the case of an integrated unit, Figure 7 FIG. 1 shows a possible structural diagram of the abnormality determination device involved in the above embodiment. Figure 7 As shown, the abnormality determination device 20 may include: a processing module 201 and a communication module 202. The processing module 201 may be used to control and manage the actions of the abnormality determination device 20. The communication module 202 may be used to support the communication between the abnormality determination device 20 and other entities. Figure 7 As shown, the abnormality determination device 20 may further include a storage module 203 for storing program codes and data of the abnormality determination device 20 .

[0099] The processing module 201 may be a processor or a controller, the communication module 202 may be a transceiver, a transceiver circuit or a communication interface, etc., and the storage module 203 may be a memory.

[0100] When the processing module 201 is a processor, the communication module 202 is a transceiver, and the storage module 203 is a memory, the processor, the transceiver, and the memory can be connected via a bus. The bus can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc.

[0101] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0102] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0103] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0104] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0105] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using a software program, 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 one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more media integrated therewith. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a DVD), or a semiconductor medium (eg, a solid state disk (SSD)).

[0106] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A method for determining an abnormality, characterized in that: The method comprises: Obtaining an image to be identified included in a video stream to be identified corresponding to a target task; Inputting the image to be recognized into a first target detection model to obtain at least one first detection frame and an area where each first detection frame in the at least one first detection frame is located, wherein each first detection frame is used to represent each target object; Inputting the image to be recognized into a second object detection model to obtain at least one second detection frame and an area where each second detection frame in the at least one second detection frame is located, wherein each second detection frame is used to represent each object; When the first number and the second number are equal, determining the matching parameter of each object based on the area where each first detection frame is located and the area where each second detection frame is located, the first number being the number of the at least one first detection frame, and the second number being the number of the at least one second detection frame; determining the matching parameter of each object based on the area where each first detection frame is located and the area where each second detection frame is located includes: Determine a first intersection and a first union, where the first intersection is the intersection of the first area and the second area, and the first union is the union of the first area and the second area, where the first area is the area where the i-th first detection frame in the at least one first detection frame is located, and the second area is the area where the i-th second detection frame in the at least one second detection frame is located, where i is a positive integer greater than or equal to 1; According to the first intersection and the first union, it is determined that the matching parameter of the i-th object satisfies the following formula: The i-th object is the object represented by the i-th second detection frame; Represents the matching parameters of the i-th object, represents the first intersection, represents the first union, i is a positive integer greater than or equal to 1; When the matching parameters do not meet the preset conditions, the target task is determined to be an abnormal task.

2. The abnormality determination method according to claim 1, characterized in that: The method further comprises: When the first number is smaller than the second number, the target task is determined to be an abnormal task.

3. The abnormality determination method according to claim 1, characterized in that: The method further comprises: When the duration for which the target object is continuously absent in the video stream to be identified is greater than or equal to a duration threshold, the target task is determined to be an abnormal task.

4. An abnormality determination device, characterized in that: include: Acquisition module, processing module and determination module; The acquisition module is used to acquire the image to be identified included in the video stream to be identified corresponding to the target task; The processing module is configured to input the image to be recognized into a first target detection model to obtain at least one first detection frame and an area within each of the at least one first detection frame, wherein each first detection frame is used to represent each target object; The processing module is further configured to input the image to be recognized into a second object detection model to obtain at least one second detection frame and an area within each second detection frame, wherein each second detection frame is used to represent each object; The determining module is configured to determine the matching parameter of each object based on the area where each first detection frame is located and the area where each second detection frame is located when a first number and a second number are equal, the first number being the number of the at least one first detection frame, and the second number being the number of the at least one second detection frame; The determination module is specifically configured to determine a first intersection and a first union, where the first intersection is the intersection of a first area and a second area, the first union is the union of the first area and the second area, the first area is the area where the i-th first detection frame in the at least one first detection frame is located, and the second area is the area where the i-th second detection frame in the at least one second detection frame is located, where i is a positive integer greater than or equal to 1; and based on the first intersection and the first union, determine whether the matching parameter of the i-th object satisfies the following formula: The i-th object is the object represented by the i-th second detection frame; Represents the matching parameters of the i-th object, represents the first intersection, represents the first union, i is a positive integer greater than or equal to 1; The determining module is further configured to determine that the target task is an abnormal task when the matching parameter does not satisfy a preset condition.

5. The abnormality determination device according to claim 4, characterized in that: The determining module is further configured to determine that the target task is an abnormal task when the first number is smaller than the second number.

6. The abnormality determination device according to claim 4, characterized in that: The determination module is further configured to determine that the target task is an abnormal task when a duration for which the target object is continuously absent in the video stream to be identified is greater than or equal to a duration threshold.

7. An electronic device, characterized in that: The electronic device comprises: processor; a memory configured to store instructions executable by the processor; The processor is configured to execute the instructions to implement the abnormality determination method according to any one of claims 1 to 3.

8. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions in the computer-readable storage medium are executed by an electronic device, the electronic device is enabled to execute the abnormality determination method according to any one of claims 1 to 3.

Images