Abnormality monitoring method, device, computer equipment and storage medium for target object

Abstract

The present application relates to a method, device, computer equipment and storage medium for monitoring abnormalities of a target object, wherein the method comprises: obtaining a monitoring image in real time based on a monitoring video; when there is a marker on the target object in the monitoring image, determining the abnormal state of the target object based on the change in the proportion of the marker in the detection area; the detection area is the area covering the target object in the monitoring image, and the detection area is a fixed area. Through this application, the problem of the inability to monitor the opening state in a timely and accurate manner in the related art due to the influence of the accuracy and sensitivity of the mechanical sensor is solved, and the change in the proportion of the marker in the detection area in the monitoring image is used to achieve accurate detection of the abnormal state of the target object and ensure the timeliness of monitoring.

Description

Technical Field

[0001] The present application relates to the field of machine vision technology, and in particular to a method, device, computer equipment and storage medium for abnormality monitoring of a target object. Background Art

[0002] With the development of information technology, the use of modern means to monitor active target objects such as warehouse doors and windows has been widely used. For warehouse doors, existing warehouse door monitoring mainly uses a mechanical sensor installed on the warehouse door to monitor whether the warehouse door is open. This solution is affected by the accuracy and sensitivity of the mechanical sensor and cannot monitor the opening status in a timely and accurate manner.

[0003] There is currently no effective solution to the problem in related technologies that the opening state cannot be monitored in a timely and accurate manner due to the accuracy and sensitivity of mechanical sensors. Summary of the invention

[0004] In this embodiment, a method, device, computer equipment and storage medium for abnormal monitoring of a target object are provided to solve the problem in the related art that the accuracy and sensitivity of mechanical sensors affect the status of warehouse doors and cannot be monitored in a timely and accurate manner.

[0005] In a first aspect, a method for monitoring an abnormality of a target object is provided in this embodiment, comprising:

[0006] Acquire surveillance images in real time based on surveillance videos;

[0007] When there is a marker on the target object in the monitoring image, the abnormal state of the target object is determined based on the change in the proportion of the marker in the detection area; the detection area is the area in the monitoring image covering the target object, and the detection area is a fixed area.

[0008] In some embodiments, determining the abnormal state of the target object based on the change in the proportion of the marker in the detection area includes:

[0009] Based on the monitoring image, obtaining in real time a first proportion of the marker in the detection area;

[0010] The difference between the second proportion and the first proportion is taken as the proportion change; the second proportion is the proportion of the marker in the detection area when the target object is in a closed state;

[0011] According to the change in the proportion, a preset first abnormality threshold and a preset first opening threshold, it is determined that the abnormal state of the target object is an abnormal state or an opening state.

[0012] In some embodiments, the method further comprises:

[0013] When the marker is not on the target object in the monitoring image, the abnormal state of the target object is determined based on the similarity between the image features in the monitoring image and the baseline image features; the image features are the features of the specified area on the target object in the monitoring image; the baseline image features are the features of the specified area when the target object is in a closed state.

[0014] In some of the embodiments, determining the abnormal state of the target object based on the similarity of image features in the monitoring image includes:

[0015] Based on the monitoring image, image features in the monitoring image are acquired in real time;

[0016] Determining a similarity between the image feature and the reference image feature;

[0017] According to the similarity, a preset second abnormality threshold and a preset second opening threshold, it is determined that the abnormal state of the target object is an abnormal state or an opening state.

[0018] In some embodiments, determining whether the abnormal state of the target object is an abnormal state or an open state according to the similarity, a preset second abnormal state threshold, and a preset second open state threshold includes:

[0019] Compare the similarity with the second abnormality threshold and the second opening threshold;

[0020] If the similarity is greater than or equal to the second opening threshold, and the similarity is less than the second abnormality threshold, it is considered that the abnormal state of the target object is the opening state;

[0021] If the similarity is greater than or equal to the second abnormality threshold, the abnormal state of the target object is considered to be the abnormal state.

[0022] In some embodiments, the method further comprises:

[0023] Determine a corresponding alarm type according to the abnormal state of the target object;

[0024] The alarm device is triggered to sound an alarm according to the alarm type.

[0025] In some embodiments, the method further comprises:

[0026] Identify the scale lines in the first frame of the monitoring image to obtain first scale information;

[0027] Identify the scale line in the second frame of the monitoring image to obtain second scale information; the frame number difference between the second frame and the first frame is less than a preset frame number threshold;

[0028] Determine a corresponding scale difference according to the first scale information and the second scale information;

[0029] When the scale difference exceeds a preset update threshold, the tolerance of the corresponding warehouse capacity is determined based on the scale difference and reported.

[0030] In some embodiments, determining and reporting the tolerance of the corresponding warehouse capacity based on the scale difference includes:

[0031] Selecting a corresponding warehouse capacity calculation formula based on the type of warehouse in the monitoring image;

[0032] According to the selected warehouse capacity calculation formula and the scale difference, the tolerance of the corresponding warehouse capacity is determined and reported.

[0033] In a second aspect, in this embodiment, a target object abnormality monitoring device is provided, including: an acquisition module and a first monitoring module;

[0034] The acquisition module is used to acquire the monitoring image in real time based on the monitoring video;

[0035] The first monitoring module is used to determine the abnormal state of the target object based on the change in the proportion of the marker in the detection area when there is a marker on the target object in the monitoring image; the detection area is the area covering the target object in the monitoring image, and the detection area is a fixed area.

[0036] In a third aspect, a computer device is provided in this embodiment, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for abnormality monitoring of a target object as described in the first aspect above is implemented.

[0037] In a fourth aspect, a storage medium is provided in this embodiment, on which a computer program is stored, and when the program is executed by a processor, the abnormality monitoring method of the target object described in the first aspect is implemented.

[0038] In a fifth aspect, a computer program product is provided in this embodiment, including a computer program, and when the computer program is executed by a processor, the method for abnormality monitoring of a target object described in the first aspect above is implemented.

[0039] Compared with the related art, the abnormal monitoring method, device, computer equipment and storage medium of the target object provided in this embodiment obtain the monitoring image in real time based on the monitoring video; when there is a marker on the target object in the monitoring image, the abnormal state of the target object is determined based on the change in the proportion of the marker in the detection area; the detection area is the area covering the target object in the monitoring image, and the detection area is a fixed area, which solves the problem in the related art that the opening state cannot be monitored in time and accurately due to the influence of the accuracy and sensitivity of the mechanical sensor, and utilizes the change in the proportion of the marker in the detection area in the monitoring image to achieve accurate detection of the abnormal state of the target object and ensure the timeliness of monitoring.

[0040] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0042] Figure 1 It is a hardware structure block diagram of a terminal device of a method for monitoring abnormality of a target object provided by an embodiment of the present application;

[0043] Figure 2 is a flow chart of a method for monitoring anomalies of a target object provided by an embodiment of the present application;

[0044] Figure 3 is a flowchart of step S220;

[0045] Figure 4 is a flow chart of a method for monitoring an abnormality of a target object provided by another embodiment of the present application;

[0046] Figure 5 is a flowchart of step S230;

[0047] Figure 6 is a flow chart of a method for calculating tolerance provided in an embodiment of the present application;

[0048] Figure 7 It is a structural block diagram of an abnormality monitoring device for a target object provided in one embodiment of the present application.

[0049] In the figure: 102, processor; 104, memory; 106, transmission device; 108, input and output device; 210, acquisition module; 220, first monitoring module. DETAILED DESCRIPTION

[0050] In order to more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0051] Unless otherwise defined, the technical terms or scientific terms involved in this application shall have the general meaning understood by people with general skills in the technical field to which this application belongs. The words "one", "a", "the", "these" and the like in this application do not indicate a quantitative limitation, and they may be singular or plural. The terms "include", "comprise", "have" and any variants thereof involved in this application are intended to cover non-exclusive inclusions; for example, a process, method and system, product or device comprising a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (units) inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships, for example, "A and / or B" may mean: A exists alone, A and B exist at the same time, and B exists alone. Generally, the character " / " indicates that the objects associated with each other are in an "or" relationship. The terms "first", "second", "third", etc. in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0052] The method embodiment provided in this embodiment can be executed in a terminal, a computer or a similar computing device. For example, running on a terminal, Figure 1 is a hardware structure block diagram of a terminal of the target object abnormality monitoring method of this embodiment. Figure 1 As shown, the terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 and a memory 104 for storing data, wherein the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA. The above terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0053] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the abnormal monitoring method of the target object in the present embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0054] The transmission device 106 is used to receive or send data via a network. The above network includes a wireless network provided by a communication provider of the terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0055] In this embodiment, a method for detecting abnormalities of a target object is provided. Figure 2 is a flow chart of the method for monitoring abnormality of a target object in this embodiment. Figure 2 As shown, the process includes the following steps:

[0056] Step S210, acquiring a monitoring image in real time based on the monitoring video;

[0057] Step S220, when there is a marker on the target object in the monitoring image, determine the abnormal state of the target object based on the change in the proportion of the marker in the detection area; the detection area is the area covering the target object in the monitoring image, and the detection area is a fixed area.

[0058] Specifically, the target object is a door, window, or other movable object. The target object may be determined based on the scene used in the embodiment of the method, and there is no limitation on this. For example, if the embodiment of the method is used to monitor the abnormal state of the door of a granary, such as movement or opening and closing, the target object is the door; the monitoring video is taken by a monitoring device, and the field of view of the monitoring device needs to cover the target object; the monitoring device is preferably installed in a position facing the target object.

[0059] The monitoring equipment will shoot in real time to obtain monitoring videos, and each frame of monitoring images can be obtained by decoding the monitoring videos. The monitoring images are identified by image processing technology to determine whether there are markers on the target object in the monitoring image; image processing technology includes but is not limited to image recognition network models, AI image processing algorithms, etc., and there is no restriction on this.

[0060] When there is a marker on the target object in the monitoring image, the abnormal state of the target object will be determined based on the change in the proportion of the marker in the detection area. Among them, the detection area is pre-specified by the user in the monitoring image, which is the area covering the target object in the monitoring image, and the detection area is a fixed area; the detection area will not change with the change of the position of the target object. For example: the detection area is the area corresponding to the target object in the monitoring image. Of course, the detection area can also be a larger or smaller area than the target object; so that the detection area can be selected in a targeted manner without performing subtle detection on the objects within the entire field of view, thereby improving the monitoring accuracy. When the target object is not moving, since the target object and the monitoring equipment are relatively fixed, the proportion of the marker in the detection area will not change; once the proportion of the marker in the detection area changes (proportion change), it means that the target object has abnormal movement or opening and closing, so the abnormal state of the target object can be accurately and timely determined. Because it is real-time monitoring, slight changes in proportion can be detected, so that the abnormal state or opening state can be discovered in a timely and accurate manner. The abnormal state is a slight change in the target object.

[0061] In the related art, the solution adopted is to install a mechanical sensor on the door of the warehouse, and monitor whether the door is open through the mechanical sensor. After long-term use, the accuracy and sensitivity of the mechanical sensor will decrease; then due to the influence of the accuracy and sensitivity of the mechanical sensor, it is impossible to accurately and timely detect the abnormal state of the target object. In this embodiment, the monitoring image is acquired in real time based on the monitoring video; when there is a marker on the target object in the monitoring image, the abnormal state of the target object is determined based on the change in the proportion of the marker in the detection area; the detection area is the area covering the target object in the monitoring image, and the detection area is a fixed area, which solves the problem in the related art that the opening state cannot be monitored in a timely and accurate manner due to the influence of the accuracy and sensitivity of the mechanical sensor, and the change in the proportion of the marker in the detection area in the monitoring image is used to accurately detect the abnormal state of the target object and ensure the timeliness of monitoring.

[0062] The following is a detailed description of each of the above steps:

[0063] In some of the embodiments, Figure 3As shown, the abnormal state of the target object is determined based on the change in the proportion of the marker in the detection area in step S220, including the following steps:

[0064] Step S221, based on the monitoring image, obtaining in real time a first proportion of the marker in the detection area;

[0065] Step S222, taking the difference between the second proportion and the first proportion as the proportion change; the second proportion is the proportion of the marker in the detection area when the target object is in the closed state;

[0066] Step S223, determining whether the abnormal state of the target object is an abnormal state or an open state according to the change in the proportion, a preset first abnormal threshold, and a preset first open threshold.

[0067] It should be noted that markers include but are not limited to warning signs, indicator signs, etc. Markers will be affixed to target objects only on important channels. By utilizing the changes in the proportion of markers in the detection area, important channels can be monitored. For example: a monitoring device can detect multiple target objects at the same time, one of which has a marker, and the other two target objects have no markers. Then the target object with the marker is monitored first, and if there is an abnormal state, it is likely to occur in this channel. The other two target objects can be monitored simultaneously using relevant monitoring methods without markers, and there is no restriction on this.

[0068] Specifically, the proportion of the marker in the detection area when the target object is in a closed state is pre-stored as the second proportion; at this time, it can be considered that the proportion of the marker in the detection area is the largest. If the angle or area of ​​the target object changes during the opening process, the first proportion of the marker in the detection area can be calculated in real time based on the monitoring image. The absolute value of the difference between the second proportion and the second proportion is taken as the proportion change. Based on the proportion change, the preset first abnormal movement threshold and the preset first opening threshold, it can be determined whether the abnormal state of the target object is an abnormal movement state or an opening state. In this embodiment, the opening method of the target object includes but is not limited to translation opening, push-pull opening and other methods.

[0069] In this embodiment, the determination of whether the abnormal state of the target object is an abnormal state or an open state can be as follows: comparing the proportion change with the first abnormal threshold and the second open threshold; if the proportion change is greater than or equal to the first abnormal threshold and less than the second open threshold, the abnormal state is considered to be an abnormal state; if the proportion change is greater than or equal to the first open threshold, the abnormal state is considered to be an open state. Among them, the first abnormal threshold is smaller than the first open threshold, and the specific reference of the first abnormal threshold and the first open threshold can be set according to the use scenario, and there is no restriction on this. For example: the first abnormal threshold is 0.1; the first open threshold is 0.8. The abnormal state and the open state are two different states. The abnormal state can be understood as only a slight opening (such as: someone prying the target object and other similar situations), and the open state is the state where the target object is completely or mostly opened (such as: the state of the target object when feeding or discharging grain). The different types of alarms triggered facilitate the staff to make reasonable decisions. In other embodiments, other comparison methods can also be used to determine whether the abnormal state of the target object is an abnormal state or an open state, and there is no restriction on this.

[0070] For example: the first proportion is 70%; the second proportion is 90%, then the proportion change (the difference between the second proportion and the first proportion) is 0.2; since the first abnormal threshold 0.1 < proportion change 0.2 < the first opening threshold 0.8, it is determined to be an abnormal state. When the first proportion is 10%; then the proportion change (the difference between the second proportion and the first proportion) is 0.8; since the proportion change 0.8 is equal to the first opening threshold 0.8, it is determined that the abnormal state is the opening state.

[0071] Through this embodiment, there is no need to use a large number of sensor devices, which can avoid the problem of inaccurate detection due to the long-term insensitivity of the sensors, and can greatly reduce the maintenance cost of the equipment; and the first abnormal movement threshold and the first opening threshold can be adjusted according to the applicable scenario to effectively distinguish whether it is an abnormal state or an opening state, expand the applicable scenarios, ensure the accuracy of monitoring, and reduce the false alarm rate.

[0072] In some of the embodiments, Figure 4 As shown in the figure, the abnormal monitoring method of the target object is Figure 2 On this basis, the following steps are also included:

[0073] Step S230, when there is no marker on the target object in the monitoring image, determine the abnormal state of the target object based on the similarity between the image features in the monitoring image and the baseline image features; the image features are the features of the specified area on the target object in the monitoring image; the baseline image features are the features of the specified area when the target object is in a closed state.

[0074] Specifically, in the case where there is no marker on the target object, the abnormal state of the target object will be determined based on the similarity of the image features in the monitoring images at different times. Among them, the image feature is the feature of the specified area on the target object in the monitoring image. At this time, it can be arbitrarily specified in the monitoring image, for example: the image feature is the feature of the area corresponding to the target object in the monitoring image. Of course, the image feature is smaller than the feature of the area of ​​the target object at this time. The reference image feature is the feature of the specified area when the target object is in a closed state; it can input the monitoring image (the target object in the monitoring image is in a closed state) into the target detection model to obtain the image feature. Affected by the change in angle or area of ​​the target object during the opening process, the similarity between the image feature and the reference image feature can be calculated in real time based on the monitoring image. When the target object is not moving, since the target object and the monitoring device are relatively fixed, the similarity of the image features at different time points is within a certain range; if the similarity of the image feature exceeds a certain range, it means that the target object has abnormal movement or opening and closing, so the abnormal state of the target object can be accurately and timely determined.

[0075] Through this embodiment, the similarity of image features is utilized to realize the monitoring of abnormal state of any target object, thereby improving the accuracy and timeliness of recognition.

[0076] In some of the embodiments, Figure 5 As shown, determining the abnormal state of the target object based on the similarity of the image features in the monitoring image in step S230 includes the following steps:

[0077] Step S231, based on the monitoring image, obtaining image features in the monitoring image in real time;

[0078] Step S232, determining the similarity between the image feature and the reference image feature;

[0079] Step S233: determining whether the abnormal state of the target object is an abnormal state or an open state according to the similarity, a preset second abnormal state threshold and a preset second open state threshold.

[0080] Specifically, the image features acquired in real time are similarly calculated with the reference image features to obtain the similarity between the image features and the reference image features. Then, based on the similarity, the preset second abnormality threshold and the preset second opening threshold, it can be determined whether the abnormal state of the target object is an abnormal state or an opening state. In this embodiment, the opening method of the target object includes but is not limited to translation opening, push-pull opening, and the like.

[0081] In this embodiment, determining whether the abnormal state of the target object is an abnormal state or an open state can be as follows: comparing the similarity with the second abnormal threshold and the second open threshold; if the similarity is greater than or equal to the second open threshold, and less than the second abnormal threshold, the abnormal state is considered to be an open state; if the similarity is greater than or equal to the second abnormal threshold, the abnormal state is considered to be an abnormal state. Among them, the second abnormal threshold is greater than the second open threshold, and the specific reference of the second abnormal threshold and the second open threshold can be set according to the usage scenario, and there is no restriction on this. For example: the second abnormal threshold is 0.8; the second open threshold is 0.1. In other embodiments, other comparison methods can also be used to determine whether the abnormal state of the target object is an abnormal state or an open state, and there is no restriction on this.

[0082] For example: when the similarity is 0.2, since the second opening threshold 0.1 < similarity 0.2 < second abnormal threshold 0.8, it is determined to be an opening state. When the similarity is 0.8, since the similarity 0.8 is equal to the second abnormal threshold 0.8, it is determined to be an abnormal state.

[0083] Through this embodiment, there is no need to use a large number of sensor devices, which can avoid the problem of inaccurate detection due to long-term insensitivity of sensors, and can greatly reduce the maintenance cost of the equipment; and the first abnormal movement threshold and the first opening threshold can be adjusted according to the applicable scenario to effectively distinguish whether it is an abnormal state or an opening state, meet the scenario without markers, ensure the accuracy of monitoring, and reduce the false alarm rate.

[0084] In some of the embodiments, the method for monitoring abnormality of a target object further includes the following steps:

[0085] Determine the corresponding alarm type according to the abnormal state of the target object;

[0086] The alarm device is triggered to sound an alarm according to the alarm type.

[0087] Specifically, the alarm type is determined by the abnormal state of the target object, and then the alarm device will be triggered to alarm according to the alarm type. For example: if the abnormal state of the target object is a change state, the alarm type is a change alarm, which triggers the alarm device to alarm according to the change alarm, so that the corresponding processing personnel can be notified to quickly go to the scene to handle the situation accordingly. If the abnormal state of the target object is a door opening state, the alarm type is a door opening alarm, which triggers the alarm device to alarm according to the door opening alarm, so that the corresponding processing personnel can be notified to quickly go to the scene to handle the situation accordingly.

[0088] In some of the embodiments, Figure 6 As shown, the method for monitoring the abnormality of the target object also includes the following steps:

[0089] Step S610, identifying scale lines in a first frame of monitoring image to obtain first scale information;

[0090] Step S620, identifying the scale line in the second frame of the monitoring image to obtain second scale information; the frame number difference between the second frame and the first frame is less than a preset frame number threshold;

[0091] Step S630, determining a corresponding scale difference according to the first scale information and the second scale information;

[0092] Step S640: When the scale difference exceeds the preset update threshold, the tolerance of the corresponding warehouse capacity is determined based on the scale difference and reported.

[0093] Specifically, the surveillance video captured by the monitoring device is first decoded, denoised, enhanced, and processed to obtain each frame of the surveillance image. It can be considered that if the surveillance image can capture the target object and the scale at the same time, then the surveillance image of this embodiment is the same as the surveillance image in step S210, and it can be performed simultaneously with the abnormal movement monitoring of the target object. The surveillance image of the first frame is selected as the initial image information, and a time interval is set, that is, a frame of current image information is saved every time this time interval passes, and the surveillance image of the second frame is obtained; the scale lines in the first frame surveillance image and the second frame surveillance image are identified by the target detection model or computer vision technology, and the corresponding first scale information and second scale information are obtained by the scale line identification method, and the scale difference between the two is calculated; if the scale difference exceeds the update threshold, the tolerance of the warehouse capacity is calculated according to the scale difference and reported to the user, and the second frame surveillance image is used as the first frame surveillance image, so that the user can make a decision. If the scale difference is lower than the update threshold, the warehouse tolerance value will not be calculated for reporting. The frame number difference between the second frame and the first frame is less than a preset frame number threshold; if the frame number threshold is 0, the second frame is considered to be the next frame of the first frame.

[0094] Through this embodiment, the tolerance of the warehouse capacity can be automatically calculated twice and updated and reported to the user, so that the user can make reasonable decisions based on accurate data.

[0095] Among them, the process of accurately and quickly identifying the scale of the monitoring image through computer vision technology is:

[0096] 1. Scale line detection: Use edge detection algorithms, such as Canny edge detection, to detect scale lines in surveillance images. In this process, edge features with obvious details can be extracted by setting a suitable edge detection threshold; 2. Line detection, screening, and grouping: Use a line detection algorithm to detect line parameters (slope and intercept) from a set of edge features, screen the detected lines, remove lines that do not meet the scale features (shorter or longer lines that differ greatly from the horizontal or vertical direction), group the screened lines, and find lines that are close to each other to form scale lines; 3. Scale value extraction: According to the standard scale basic unit and the interval between scale lines, the scale value corresponding to the scale line is calculated by calculating the intersection position of the straight line and the scale line; 4. Scale line matching: Match the identified scale lines, sort and correct the scale values ​​to reduce errors and improve accuracy; 5. Scale line calibration: According to specific application requirements, calibrate or sample the identified scale lines to obtain accurate scale values.

[0097] In some embodiments, determining and reporting the tolerance of the corresponding warehouse capacity based on the scale difference includes:

[0098] Select the corresponding warehouse capacity calculation formula based on the type of warehouse in the surveillance image;

[0099] Based on the selected warehouse capacity calculation formula and scale difference, determine the tolerance of the corresponding warehouse capacity and report it.

[0100] Specifically, the warehouse capacity calculation formula refers to the warehouse capacity calculation standard, which is usually determined based on factors such as the type of granary, design parameters, grain density, etc. In this embodiment, the types of granaries are divided into flat warehouses and cylindrical warehouses.

[0101] The calculation formula for the storage capacity of a flat warehouse is: storage capacity = building area × grain surface height × grain density × 95%;

[0102] The calculation formula for the storage capacity of a cylindrical silo is: storage capacity = π × inner diameter radius 2 × grain surface height × grain density.

[0103] The building area is the actual floor area of ​​the granary; the grain surface height is the vertical height of the granary after it is filled with grain (scale information); the inner radius is the inner radius of the cylindrical granary; the grain density is usually 750kg / m 3 .

[0104] Based on this, according to the selected warehouse capacity calculation formula and scale difference, the tolerance of the corresponding warehouse capacity can be accurately calculated and reported.

[0105] Through this embodiment, the warehouse capacity calculation formula can be selected according to different types of warehouses to calculate the tolerance of the warehouse capacity, thereby further improving the accuracy of the tolerance calculation, so that users can make corresponding decisions in a timely manner.

[0106] It should be noted that the steps shown in the above process or the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0107] In this embodiment, a device for monitoring abnormalities of a target object is also provided, and the device is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. The terms "module", "unit", "subunit", etc. used below can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0108] Figure 7 is a structural block diagram of the abnormality monitoring device for the target object of this embodiment, such as Figure 7 As shown, the device includes: an acquisition module 210 and a first monitoring module 220;

[0109] An acquisition module 210 is used to acquire a surveillance image in real time based on the surveillance video;

[0110] The first monitoring module 220 is used to determine the abnormal state of the target object based on the change in the proportion of the marker in the detection area when there is a marker on the target object in the monitoring image; the detection area is the area covering the target object in the monitoring image, and the detection area is a fixed area.

[0111] The above-mentioned device solves the problem in related technologies that the opening status cannot be monitored in a timely and accurate manner due to the influence of the accuracy and sensitivity of mechanical sensors. By utilizing the changes in the proportion of markers in the detection area in the monitoring image, accurate detection of abnormal states of the target object can be achieved, thereby ensuring the timeliness of monitoring.

[0112] In some of the embodiments, the first monitoring module 220 is further used to obtain a first proportion of the marker in the detection area in real time based on the monitoring image;

[0113] The difference between the second proportion and the first proportion is taken as the proportion change; the second proportion is the proportion of the marker in the detection area when the target object is in the closed state;

[0114] According to the change in the proportion, the preset first abnormality threshold and the preset first opening threshold, it is determined that the abnormal state of the target object is an abnormal state or an opening state.

[0115] In some of the embodiments, the target object abnormality monitoring device further includes: a second monitoring module;

[0116] The second monitoring module is used to determine the abnormal state of the target object based on the similarity between the image features in the monitoring image and the reference image features when there is no marker on the target object in the monitoring image; the image features are the features of the specified area on the target object in the monitoring image; the reference image features are the features of the specified area when the target object is in a closed state.

[0117] In some of the embodiments, the second monitoring module is further used to obtain image features in the monitoring image in real time based on the monitoring image;

[0118] Determine the similarity between the image feature and the reference image feature; the reference image feature is a designated area when the target object is in a closed state;

[0119] According to the similarity, the preset second abnormality threshold and the preset second opening threshold, it is determined that the abnormal state of the target object is an abnormal state or an opening state.

[0120] In some of the embodiments, the second monitoring module is further used to compare the similarity with a second abnormality threshold and a second opening threshold;

[0121] If the similarity is greater than or equal to the second opening threshold, and the similarity is less than the second abnormality threshold, the abnormal state of the target object is considered to be the opening state;

[0122] If the similarity is greater than or equal to the second abnormality threshold, the abnormal state of the target object is considered to be an abnormal state.

[0123] In some of the embodiments, the target object abnormality monitoring device further includes: an alarm module;

[0124] An alarm module is used to determine the corresponding alarm type according to the abnormal state of the target object;

[0125] The alarm device is triggered to sound an alarm according to the alarm type.

[0126] In some of the embodiments, the target object abnormality monitoring device further includes: an identification module;

[0127] A recognition module, used to recognize scale lines in a first frame of monitoring image and obtain first scale information;

[0128] Identify the scale line in the second frame of the monitoring image to obtain second scale information; the frame number difference between the second frame and the first frame is less than a preset frame number threshold;

[0129] Determine a corresponding scale difference according to the first scale information and the second scale information;

[0130] When the scale difference exceeds the preset update threshold, the tolerance of the corresponding warehouse capacity is determined based on the scale difference and reported.

[0131] In some of the embodiments, the identification module is further used to select a corresponding warehouse capacity calculation formula based on the type of warehouse in the monitoring image;

[0132] Based on the selected warehouse capacity calculation formula and scale difference, determine the tolerance of the corresponding warehouse capacity and report it.

[0133] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. For modules implemented by hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0134] In this embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0135] Optionally, the computer device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0136] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0137] S1, real-time acquisition of surveillance images based on surveillance videos;

[0138] S2, when there is a marker on the target object in the monitoring image, the abnormal state of the target object is determined based on the change in the proportion of the marker in the detection area; the detection area is the area covering the target object in the monitoring image, and the detection area is a fixed area.

[0139] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and will not be repeated in this embodiment.

[0140] In addition, in combination with the target object abnormality monitoring method provided in the above embodiments, a storage medium can also be provided in this embodiment to implement the method. The storage medium stores a computer program; when the computer program is executed by a processor, any target object abnormality monitoring method in the above embodiments is implemented.

[0141] In addition, in combination with the target object abnormality monitoring method provided in the above embodiments, a computer program product can also be provided in this embodiment, including a computer program, which implements any target object abnormality monitoring method in the above embodiments when executed by a processor.

[0142] It should be understood that the specific embodiments described herein are only used to explain the application, rather than to limit it. Based on the embodiments provided in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the protection scope of this application.

[0143] Obviously, the drawings are only some examples or embodiments of the present application. For ordinary technicians in the field, the present application can also be applied to other similar situations based on these drawings without creative work. In addition, it is understandable that although the work done in this development process may be complicated and lengthy, for ordinary technicians in the field, certain changes in design, manufacturing or production based on the technical content disclosed in this application are only conventional technical means and should not be regarded as insufficient content disclosed in this application.

[0144] The term "embodiment" in this application refers to a specific feature, structure or characteristic described in conjunction with the embodiment that can be included in at least one embodiment of the present application. The appearance of this phrase in various locations in the specification does not necessarily mean the same embodiment, nor does it mean that it is mutually exclusive with other embodiments and is independent or optional. It is clearly or implicitly understood by those of ordinary skill in the art that the embodiments described in this application can be combined with other embodiments without conflict.

[0145] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of patent protection. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the scope of protection of the present application. Therefore, the scope of protection of the present application shall be subject to the attached claims.

Claims

1. A method for monitoring abnormality of a target object, characterized in that: include: Acquire surveillance images in real time based on surveillance videos; When there is a marker on the target object in the monitoring image, the abnormal state of the target object is determined based on the change in the proportion of the marker in the detection area; the detection area is the area in the monitoring image covering the target object, and the detection area is a fixed area; The target object is an active object; Wherein, determining the abnormal state of the target object based on the change in the proportion of the marker in the detection area includes: Based on the monitoring image, obtaining in real time a first proportion of the marker in the detection area; The difference between the second proportion and the first proportion is taken as the proportion change; the second proportion is the proportion of the marker in the detection area when the target object is in a closed state; According to the change in the proportion, a preset first abnormality threshold and a preset first opening threshold, it is determined that the abnormal state of the target object is an abnormal state or an opening state.

2. The method for detecting abnormalities of a target object according to claim 1, characterized in that: The method further comprises: When the marker is not on the target object in the monitoring image, the abnormal state of the target object is determined based on the similarity between the image features in the monitoring image and the baseline image features; the image features are the features of the specified area on the target object in the monitoring image; the baseline image features are the features of the specified area when the target object is in a closed state.

3. The method for detecting abnormality of a target object according to claim 2, characterized in that: Determining the abnormal state of the target object based on the similarity of the image features in the monitoring image includes: Based on the monitoring image, image features in the monitoring image are acquired in real time; Determining a similarity between the image feature and the reference image feature; According to the similarity, a preset second abnormality threshold and a preset second opening threshold, it is determined that the abnormal state of the target object is an abnormal state or an opening state.

4. The method for detecting abnormalities of a target object according to claim 3, characterized in that: Determining, according to the similarity, a preset second abnormality threshold and a preset second opening threshold, whether the abnormal state of the target object is an abnormal state or an opening state includes: Compare the similarity with the second abnormality threshold and the second opening threshold; If the similarity is greater than or equal to the second opening threshold, and the similarity is less than the second abnormality threshold, it is considered that the abnormal state of the target object is the opening state; If the similarity is greater than or equal to the second abnormality threshold, the abnormal state of the target object is considered to be the abnormal state.

5. The method for detecting abnormality of a target object according to claim 1, characterized in that: The method further comprises: Identify the scale lines in the first frame of the monitoring image to obtain first scale information; Identify the scale line in the second frame of the monitoring image to obtain second scale information; the frame number difference between the second frame and the first frame is less than a preset frame number threshold; Determine a corresponding scale difference according to the first scale information and the second scale information; When the scale difference exceeds a preset update threshold, the tolerance of the corresponding warehouse capacity is determined based on the scale difference and reported.

6. The method for detecting abnormalities of a target object according to claim 5, characterized in that: Determining the tolerance of the corresponding warehouse capacity based on the scale difference and reporting it, including: Selecting a corresponding warehouse capacity calculation formula based on the type of warehouse in the monitoring image; According to the selected warehouse capacity calculation formula and the scale difference, the tolerance of the corresponding warehouse capacity is determined and reported.

7. An abnormality monitoring device for a target object, characterized in that: include: An acquisition module and a first monitoring module; The acquisition module is used to acquire the monitoring image in real time based on the monitoring video; The first monitoring module is used to determine the abnormal state of the target object based on the change in the proportion of the marker in the detection area when there is a marker on the target object in the monitoring image; the detection area is the area covering the target object in the monitoring image, and the detection area is a fixed area; The target object is an active object; The first monitoring module is further used to obtain a first proportion of the marker in the detection area in real time based on the monitoring image; The difference between the second proportion and the first proportion is taken as the proportion change; the second proportion is the proportion of the marker in the detection area when the target object is in a closed state; According to the change in the proportion, a preset first abnormality threshold and a preset first opening threshold, it is determined that the abnormal state of the target object is an abnormal state or an opening state.

8. A computer device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps of the method for abnormality monitoring of a target object according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for abnormality monitoring of a target object according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method for abnormality monitoring of a target object according to any one of claims 1 to 6 are implemented.

Images