CN113869166A - Substation outdoor operation monitoring method and device - Google Patents
Substation outdoor operation monitoring method and device Download PDFInfo
- Publication number
- CN113869166A CN113869166A CN202111101042.0A CN202111101042A CN113869166A CN 113869166 A CN113869166 A CN 113869166A CN 202111101042 A CN202111101042 A CN 202111101042A CN 113869166 A CN113869166 A CN 113869166A
- Authority
- CN
- China
- Prior art keywords
- monitoring
- moving object
- target
- corner
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/22—Status alarms responsive to presence or absence of persons
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/24—Reminder alarms, e.g. anti-loss alarms
Abstract
The application provides a substation outdoor operation monitoring method and device, wherein a monitoring image captured by target monitoring equipment is obtained in real time; identifying a moving object in the monitoring image of the current frame aiming at the monitoring image of the current frame; determining whether to initiate job monitoring for the moving object; if the operation monitoring aiming at the moving object is determined to be started, determining whether the moving object meets the high-altitude outdoor operation criterion of the transformer substation; and if the moving object does not meet the high-altitude outdoor operation rule of the transformer substation, generating an alarm signal, wherein the alarm signal is used for indicating that an event violating the high-altitude outdoor operation rule of the transformer substation occurs in the monitoring range of the target monitoring equipment. The method can identify the operator in the monitoring picture, and screen and filter the moving target near the operator, thereby eliminating the object which is mistakenly reported due to the limb action of the operator.
Description
Technical Field
The application relates to the technical field of substation operation monitoring, in particular to a substation outdoor operation monitoring method and device.
Background
The method is characterized in that the throwing and losing equipment of the operating personnel from high altitude to the ground is forbidden in the construction specification of the transformer substation, and in order to solve the problem of throwing objects from high altitude in the outdoor site construction of the transformer substation, the throwing and losing equipment of the operating personnel from high altitude to the ground is definitely forbidden in the construction specification.
In the prior art, a moving target is usually extracted by using algorithms such as background modeling, moving target detection and the like, and features of the moving target are extracted to judge whether the moving target is a high-altitude parabola or not. However, in a transformer substation scene, the visual field of the camera is wide, and the rapid limb movement of an operator during working is easily recognized as a parabola, so that misjudgment is generated. Therefore, an effective solution is needed to be provided for eliminating the false alarm of the object throwing caused by the limb movement of the staff.
Disclosure of Invention
In view of this, an object of the present application is to provide a substation outdoor operation monitoring method and device, which can identify an operator in a monitoring picture, and filter and screen a moving object near the operator, so as to eliminate a false alarm object caused by the limb movement of the operator, and improve the substation outdoor operation monitoring accuracy.
In a first aspect, an embodiment of the present application provides a substation outdoor operation monitoring method, including: acquiring a monitoring image captured by target monitoring equipment in real time; identifying a moving object in the monitoring image of the current frame aiming at the monitoring image of the current frame; determining whether to initiate job monitoring for the moving object; if the operation monitoring aiming at the moving object is determined to be started, determining whether the moving object meets the high-altitude outdoor operation criterion of the transformer substation; and if the moving object does not meet the high-altitude outdoor operation rule of the transformer substation, generating an alarm signal, wherein the alarm signal is used for indicating that an event violating the high-altitude outdoor operation rule of the transformer substation occurs in the monitoring range of the target monitoring equipment.
Preferably, the step of determining whether to start job monitoring for the moving object specifically includes: identifying whether a human body object exists in the monitoring image of the current frame; if no human body object exists in the monitoring image of the current frame, determining to start operation monitoring for the moving object; if the human body object exists in the monitoring image of the current frame, determining the relative position between the moving object and the human body object; determining to start the operation monitoring for the moving object if the relative position between the moving object and the human body object belongs to a first position relation; and if the relative position between the moving object and the human body object belongs to the second position relation, determining not to start the operation monitoring for the moving object.
Preferably, the step of determining the relative position between the moving object and the human object specifically comprises: determining the marking range of the human body object in the monitoring image of the current frame; determining the image position of a moving object in a monitoring image of a current frame; if the image position of the moving object is located within the mark range of the human body object, determining that the relative position relationship between the moving object and the human body object belongs to a first position relationship; if the image position of the moving object is outside the marker range of the human object, it is determined that the relative positional relationship between the moving object and the human object belongs to the second positional relationship.
Preferably, the moving object in the monitoring image of the current frame is identified by: determining at least one first corner target in the monitoring image of the current frame through a corner detection algorithm; respectively calculating the characteristic distance of the corner target between each first corner target and each second corner target in the monitoring image of the previous frame aiming at each first corner target; and determining two corner point targets with the characteristic distance between the corner point targets larger than zero and smaller than a preset threshold value as the same corner point target, and determining the corner point target as a moving object in the monitoring image of the current frame.
Preferably, a ratio of a height value of the marker range of the human subject to a height value of the monitoring image is calculated; and if the ratio is smaller than the preset ratio, generating a control signal to adjust the shooting focal length of the target monitoring equipment until the ratio is equal to the preset ratio.
Preferably, the feature distance of the corner object between the first corner object and any one of the second corner objects is calculated by: extracting a first preset feature vector of a first corner target and a second preset feature vector of any second corner target; and calculating the Euclidean distance between a first preset feature vector of the first corner point target and a second preset feature vector of any second corner point target, and determining the Euclidean distance as the feature distance of the corner point target.
Preferably, counting the number of times of generating the alarm signal within a preset time period; and sending out different alarm information according to the counted times of the alarm signals.
In a second aspect, an embodiment of the present application further provides a substation outdoor operation detection device, including:
the acquisition module is used for acquiring a monitoring image captured by the target monitoring equipment in real time;
the first identification module is used for identifying a moving object in the monitoring image of the current frame aiming at the monitoring image of the current frame;
the system comprises a first judgment module, a second judgment module and a monitoring module, wherein the first judgment module is used for determining whether to start operation monitoring aiming at a moving object;
the second judgment module is used for determining whether the moving object meets the high-altitude outdoor operation criterion of the transformer substation if the operation monitoring aiming at the moving object is determined to be started;
and the signal module is used for generating an alarm signal if the moving object does not meet the high-altitude outdoor operation rule of the transformer substation, and the alarm signal is used for indicating that an event violating the high-altitude outdoor operation rule of the transformer substation occurs in the monitoring range of the target monitoring equipment.
In a third aspect, an embodiment of the present application further provides an electronic device, including: the monitoring device comprises a processor, a memory and a bus, wherein the memory stores machine readable instructions executable by the processor, when the electronic device runs, the processor and the memory are communicated through the bus, and the processor executes the machine readable instructions to execute the steps of the substation outdoor operation monitoring method.
In a fourth aspect, embodiments of the present application further provide a computer-readable storage medium, where a computer program is stored on the storage medium, and when the computer program is executed by a processor, the steps of the substation outdoor operation monitoring method are performed.
According to the substation outdoor operation monitoring method provided by the embodiment of the application, the monitoring images captured by the target monitoring equipment are obtained in real time, the moving object in the monitoring image of the current frame is identified according to each frame of monitoring image, whether operation monitoring aiming at the moving object is started or not is determined, whether the moving object meets the substation high-altitude outdoor operation criterion or not is determined if the operation monitoring aiming at the moving object is started, and if the operation monitoring aiming at the moving object does not meet the substation high-altitude outdoor operation criterion, an alarm signal is generated to indicate that an event violating the substation high-altitude outdoor operation criterion occurs in the monitoring range of the target monitoring equipment, so that the problem that a human body is mistakenly judged as a high-altitude object when the substation high-altitude outdoor operation is monitored is solved, and the false alarm is generated, and the substation outdoor operation monitoring precision is improved.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments are briefly described below, it should be understood that the following drawings are only some embodiments of the present application, and therefore should not be considered as limiting the scope, and it is obvious for those skilled in the art that other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is a flowchart of a substation outdoor operation monitoring method according to an embodiment of the present application;
FIG. 2 is a flowchart of a method for determining to initiate job monitoring according to another embodiment of the present disclosure;
FIG. 3 is a flowchart of a method for determining a relative position between a moving object and a human object according to an embodiment of the present disclosure;
FIG. 4 is a flow chart of a method for identifying a moving object provided by an embodiment of the present application;
fig. 5 is a schematic structural diagram of a substation outdoor operation monitoring device provided in an embodiment of the present application;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. Every other embodiment that can be obtained by a person skilled in the art without making creative efforts based on the embodiments of the present application falls within the protection scope of the present application.
The method is characterized in that the throwing and losing equipment of the operating personnel from high altitude to the ground is forbidden in the construction specification of the transformer substation, and in order to solve the problem of throwing objects from high altitude in the outdoor site construction of the transformer substation, the throwing and losing equipment of the operating personnel from high altitude to the ground is definitely forbidden in the construction specification.
In the prior art, a moving target is usually extracted by using algorithms such as background modeling, moving target detection and the like, and features of the moving target are extracted to judge whether the moving target is a high-altitude parabola or not. However, in a transformer substation scene, the visual field of the camera is wide, and the rapid limb movement of an operator during working is easily recognized as a parabola, so that misjudgment is generated. Therefore, an effective solution is needed to be provided for eliminating the false alarm of the object throwing caused by the limb movement of the staff.
In order to facilitate understanding of the present embodiment, a method and an apparatus for monitoring outdoor operations of a substation provided in the embodiments of the present application are described in detail below.
Referring to fig. 1, a transformer substation outdoor operation monitoring method provided in an embodiment of the present application includes:
and S101, acquiring a monitoring image captured by the target monitoring equipment in real time.
The target monitoring device may be a camera installed at an outdoor job site of the substation, the target monitoring device is configured to obtain an image of the job site in real time, a screen size of the monitoring image is 1920 × 1080 pixels, and the monitoring image is a side view of the job site.
S102, aiming at the monitoring image of the current frame, identifying a moving object in the monitoring image of the current frame.
And identifying whether a moving object exists in the monitored image or not aiming at each frame of monitored image. The moving object is a corner object identified by a corner identification algorithm, which may include a corner object determined on an actually moving object or a corner object determined on a stationary object. In one frame of the monitored image, a plurality of corner point objects can be identified. The current frame refers to a frame of monitoring image obtained at the current moment. The corner point target identified here can be understood as a point which causes great changes in the direction and amplitude of the gradient map of the region when the monitoring image moves slightly in any direction; or the points are points of intense change of gray scale brightness information in different directions in the two-dimensional gray scale image of the monitoring image; or curvature maximum points on all edge contour lines in the monitored image.
S103, determining whether to start the job monitoring for the moving object.
Determining whether to start operation monitoring for the moving object, which may be determining whether a human body object exists in the monitored image, and if a human body object exists in the monitored image while the moving object is identified in the monitored image of the current frame, the operation monitoring for the moving object needs to be started. The human body object refers to a human body in the monitored image, and can be obtained by identification through the existing human body identification algorithm.
And S104, if the operation monitoring aiming at the moving object is determined to be started, determining whether the moving object meets the high-altitude outdoor operation criterion of the transformer substation.
The criterion of the substation high-altitude outdoor operation is a judgment condition for judging whether a moving object is a high-altitude parabola or not, and here, the judgment may be to judge whether the speed or the acceleration of the moving object is close to a preset speed or a preset gravitational acceleration, for example, if the acceleration of the moving object is equal to the gravitational acceleration, the moving object is an angular point target on an object thrown aloft. Through the judgment process, the corner point target on the static object in the identified moving object can be filtered out.
Specifically, the high-altitude outdoor operation criterion of the transformer substation is to judge whether the acceleration of the moving object in the vertical direction is smaller than half of the gravity acceleration, and if so, the object is judged not to be a high-altitude thrown object, and an angular point target is obtained.
In particular, canThe preset velocity or the preset gravitational acceleration is adjusted to improve the sensitivity of the monitoring. For example, the preset acceleration is set as the acceleration of gravity, i.e., g-9.780 m/s2At this time, the sensitivity of identifying the moving object is the highest.
Further, the speed or acceleration of the moving object can be calculated by a commonly used velocity measurement algorithm. Here, in the process of identifying a moving object by an optical flow method, the velocity or acceleration corresponding to the angular point object can be obtained.
And S105, if the moving object does not meet the high-altitude outdoor operation rule of the transformer substation, generating an alarm signal, wherein the alarm signal is used for indicating that an event violating the high-altitude outdoor operation rule of the transformer substation occurs in the monitoring range of the target monitoring equipment.
Under the condition that the moving object does not meet the high-altitude outdoor operation rule of the transformer substation, the moving object is judged to be an angular point target on an object thrown aloft, and at the moment, an alarm signal is generated in the system to indicate that the moving object violating the high-altitude outdoor operation rule of the transformer substation exists in the monitoring image of the current frame in the monitoring range of the target monitoring equipment.
In the embodiment, the monitoring images captured by the target monitoring equipment are acquired in real time, the moving object in the monitoring image of the current frame is identified aiming at each monitoring image, whether operation monitoring aiming at the moving object is started is determined, if the operation monitoring aiming at the moving object is started, whether the moving object meets the high-altitude outdoor operation criterion of the transformer substation is determined, if the operation object does not meet the high-altitude outdoor operation criterion, an alarm signal is generated to indicate that an event violating the high-altitude outdoor operation criterion of the transformer substation occurs in the monitoring range of the target monitoring equipment, and the problem that when the high-altitude outdoor operation of the transformer substation is monitored, a human body is mistakenly judged as a high-altitude object, so that false alarm is generated is solved.
Fig. 2 is a flowchart of a method for determining to start job monitoring according to an embodiment of the present application. In an optional example, the specific step of determining whether to start job monitoring for the moving object specifically includes:
s201, identifying whether a human body object exists in the monitoring image of the current frame.
Specifically, human body object detection is performed through a YOLOv5s deep learning model, and a human body object in a monitoring image is identified. The human body object is a complete human body, and if a human body with more than one third of the human body transversely shielded or a human body with the head shielded exists in the monitored image, the human body object cannot be identified. The detected human body object marks the outline range through the bar-shaped frame.
S202, if the human body object does not exist in the monitoring image of the current frame, determining to start the operation monitoring for the moving object.
If no human body object exists in the monitoring image of the current frame, the situation that the limb movement of the human body is misjudged as the moving object does not occur, but the moving object still needs to be monitored in operation to determine whether the situation of high altitude parabolic exists.
S203, if the human body object exists in the monitoring image of the current frame, determining the relative position between the moving object and the human body object.
If the human body object exists in the monitoring image of the current frame, the relative position relationship between the moving object and the human body object needs to be judged.
And S204, if the relative position between the moving object and the human body object belongs to the first position relation, determining to start the operation monitoring aiming at the moving object.
The first positional relationship is used to indicate that there is an intersection between the moving object and the human body, and at this time, it is easy to determine that the body motion of the human body is misjudged as the moving object, so that it is necessary to first screen the moving object of the current frame and then determine whether there is a high-altitude parabolic situation in the remaining moving objects.
Specifically, the moving objects which belong to the first position relation with the human body object in the moving objects detected by the current frame can be deleted, and only the remaining moving objects are reserved for judging whether high-altitude parabolas exist, so that a more accurate high-altitude parabolas detection result can be obtained.
And S205, if the relative position between the moving object and the human body object belongs to the second position relation, determining not to start the operation monitoring for the moving object.
The second position relation is used for indicating that no intersection exists between the moving object and the human body object, and whether the moving object has a high-altitude parabolic condition or not is directly judged.
Fig. 3 is a flowchart of a method for determining a relative position between a moving object and a human object according to an embodiment of the present application. In an optional example, the step of determining the relative position between the moving object and the human object specifically includes:
s301, determining the marking range of the human body object in the monitoring image of the current frame.
The range of the human body object in the monitoring image, which is identified by the human body object detection through the YOLOv5s deep learning model, is obtained and is circled through a bar-shaped frame.
S302, determining the image position of the moving object in the monitoring image of the current frame.
And acquiring the image position of the moving object in the monitoring image of the current frame, which is obtained by the optical flow method.
S303, if the image position of the moving object is located in the mark range of the human body object, determining that the relative position relationship between the moving object and the human body object belongs to the first position relationship.
If the image position of the moving object is within the range enclosed by the bar-shaped frame of the human body object, the intersection of the moving object and the human body object is indicated, and the moving object within the marking range of the human body object needs to be deleted, so that the limb action of the human body is prevented from being judged as an object thrown off at high altitude by mistake.
S304, if the image position of the moving object is out of the mark range of the human body object, determining that the relative position relationship between the moving object and the human body object belongs to a second position relationship.
And if the image position of the moving object is not in the marking range of the human body object, directly judging whether the part of the moving object meets the high-altitude outdoor operation criterion of the transformer substation.
Fig. 4 is a flowchart illustrating a method for identifying a moving object according to an embodiment of the present application. In an alternative example, a moving object in the monitoring image of the current frame is identified by:
s401, determining at least one first corner target in the monitoring image of the current frame through a corner detection algorithm.
Specifically, at least one corner target in the monitored image of the current frame is extracted by using a Shi-Tomasi corner detection algorithm. The first corner targets are all corner targets extracted by a corner detection algorithm from the monitoring image of the current frame.
S402, aiming at each first corner target, respectively calculating a corner target characteristic distance between the first corner target and each second corner target in the monitoring image of the previous frame.
The second corner point targets are all corner point targets extracted by a corner point detection algorithm in the previous frame of monitoring image.
And respectively calculating the characteristic distance of the corner target between each first corner target identified by the current frame and each second corner target in the monitoring image of the previous frame. Wherein the second corner target in the previous frame of the monitored image comprises all the corner targets identified in the previous frame of the monitored image.
The angular point target feature distance may be a distance between preset feature vectors of angular point targets. The preset feature vector here may be a vector for describing a feature point position, a direction, scale information, or adjacent pixel information.
Specifically, the feature distance of the corner target between the first corner target and any one of the second corner targets is calculated in the following manner: extracting a first preset feature vector of a first corner target and a second preset feature vector of any second corner target; and calculating the Euclidean distance between a first preset feature vector of the first corner point target and a second preset feature vector of any second corner point target, and determining the Euclidean distance as the feature distance of the corner point target.
S403, determining two corner point targets with the characteristic distance between the corner point targets larger than zero and smaller than a preset threshold value as the same corner point target, and determining the corner point target as a moving object in the monitoring image of the current frame.
And determining the two corner targets with the target characteristic distance larger than zero and smaller than a preset threshold value as two matched corner targets, and determining the first corner target in the two corner targets as a moving object in the monitoring image of the current frame. The moving object determined here may be a corner target on a moving object or a corner target on a stationary object.
In an alternative example, a ratio of a height value of the mark range of the human subject to a height value of the monitored image is calculated, and if the ratio is less than a preset ratio, a control signal is generated to adjust a photographing focal length of the target monitoring apparatus until the ratio is equal to the preset ratio.
It can be understood that the size of the monitoring image of the target monitoring device is 1920 × 1080 pixels, that is, the height value of the monitoring image is 1080 pixels, and the height of the mark range of the human object in the monitoring picture needs to be 400 pixels, so as to ensure that the recognition effect is better and more accurate when the human object is detected through the YOLOv5s deep learning model.
When the ratio of the height value of the marking range of any human body object in the monitoring picture to the height value of the monitoring image is smaller than the preset ratio, the height of the marking range of the human body object in the monitoring picture is smaller than 400 pixels, and at the moment, a control signal is generated to adjust the shooting focal length of the target monitoring equipment until the ratio is equal to the preset ratio. At this time, if the height of the mark range of other human body objects in the current monitoring image is less than 400 pixels, the steps are repeated. Through the shooting focal length adjustment, each human body object in the monitoring picture can be accurately identified, so that the running objects are screened more carefully, and the phenomenon that the limb actions of the human body are mistakenly judged as high-altitude objects is avoided.
In an optional example, the times of generating the alarm signals in the preset time period are counted, and different alarm information is sent out according to the counted times of the alarm signals.
It can be understood that an alarm signal is correspondingly generated for each moving object detected in each frame of monitoring image, and in order to avoid the situation of repeated alarm, the times of alarm generation in a preset time period can be counted, and different alarm information can be sent out according to the number of times of alarm generation. The alarm information may be text information of the high altitude parabolic event generated by the terminal device and sent to the user, or may be language information sent by a preset prompt sound.
Specifically, when the number of times of generation of the alarm signal in the preset time period is greater than a certain threshold, it can be considered that a plurality of high-altitude falling objects or a high-altitude falling object with a large surface area and the like are dangerous in the current monitoring picture, so that a larger prompt sound or character information such as a first-level high-altitude parabolic event can be sent out to represent the level of the current high-altitude parabolic event, and the high-altitude parabolic events with different damage degrees can be distinguished.
In an alternative implementation, a monitoring alarm device is provided, which is operated with a substation outdoor operation monitoring system, and the system is used for realizing the following steps:
step 0: based on the target detection of the YOLOv5s deep learning model, various human objects in the picture are identified.
Specifically, a large amount of picture data in daily service can be collected, targets such as a human body can be labeled, and a data set is made for training. In order to improve the identification precision and robustness of the model, the data is expanded by using an IMGAUG data enhancement tool, and the modes of fuzzification, plane rotation, mirror image inversion, Gaussian noise, scaling and the like of a data set picture are included. And trains the YOLOv5s target detection algorithm model used in the present invention using the data set, thereby improving the accuracy of the target detection algorithm.
Step 1: tracking and predicting a moving object (namely a corner object) by utilizing an optical flow method.
Step 2: and judging whether a moving object exists according to the identification result in the step 1. If yes, entering step 3; if not, the detection of the current round is finished.
And step 3: and (3) deleting the corner point target which has intersection with the human body object in the step (1) by using the target frame (namely the mark range) of the human body object in the detection result of the step (0) as a screening condition.
And 4, step 4: and (4) calculating the motion characteristics of the motion object screened in the step (3), namely the motion speed or acceleration in the y direction (vertical direction).
And 5: judging whether the motion characteristics extracted in the step 4 meet the judgment condition of high altitude parabolic, if so, entering a step 6; if not, the detection of the current round is finished.
Specifically, the condition for judging the high altitude parabola is to judge whether the falling acceleration of the moving object in the y direction in the picture is larger than half of the gravity acceleration. According to actual conditions in the field, the camera needs to be focused in advance to the size of about 400 pixels in the y direction of the screen (1080P of the screen) of the operator.
Step 6: and 5, generating alarm information if the moving target meets the condition of being judged to be a high-altitude object throwing object according to the judgment result of the step 5. The alarm information is used for reminding a monitoring manager that an operator is carrying out illegal parabolic behavior in the current monitoring range.
Wherein, the step 1 is realized by the following steps:
step (1): and extracting the corner target of the current video frame by using a Shi-Tomasi corner detection algorithm.
Step (2): and (3) calculating the Euclidean distance from the corner point of the previous frame according to the corner point obtained in the step (1).
And (3): and (4) deleting the feature points (namely corner point targets) with the distance larger than 2 according to the Euclidean distance calculated in the step (2). Where 2 is the distance threshold and the dimension is the pixel.
And (4): and (4) updating the feature point container (namely emptying the feature point container) according to the screening result in the step (3). Specifically, the feature points screened in the step (3) are stored in a feature point container, and the matching is performed after the feature points are extracted from the next frame.
Based on the same inventive concept, the substation outdoor operation monitoring device corresponding to the substation outdoor operation monitoring method is further provided in the embodiment of the present application, and as the principle of solving the problem of the substation outdoor operation monitoring device in the embodiment of the present application is similar to that of the substation outdoor operation monitoring method in the embodiment of the present application, the implementation of the substation outdoor operation monitoring device can refer to the implementation of the method, and repeated parts are not described again.
Referring to fig. 5, fig. 5 is a schematic structural diagram of a substation outdoor operation monitoring device according to an embodiment of the present disclosure. As shown in fig. 5, the monitoring device 600 includes:
an obtaining module 610, configured to obtain a monitoring image captured by a target monitoring device in real time;
a first identifying module 620, configured to identify a moving object in the monitoring image of the current frame according to the monitoring image of the current frame;
a first determination module 630, configured to determine whether to initiate job monitoring for a moving object;
a second judging module 640, configured to determine whether the moving object meets the criteria of the substation high-altitude outdoor operation if it is determined that the operation monitoring for the moving object is started;
and the signal module 650 is used for generating an alarm signal if the moving object does not meet the high-altitude outdoor operation rule of the transformer substation, wherein the alarm signal is used for indicating that an event violating the high-altitude outdoor operation rule of the transformer substation occurs in the monitoring range of the target monitoring equipment.
In a preferred embodiment, the first determining module 630 is specifically configured to: identifying whether a human body object exists in the monitoring image of the current frame; if no human body object exists in the monitoring image of the current frame, determining to start operation monitoring for the moving object; if the human body object exists in the monitoring image of the current frame, determining the relative position between the moving object and the human body object; determining to start the operation monitoring for the moving object if the relative position between the moving object and the human body object belongs to a first position relation; and if the relative position between the moving object and the human body object belongs to the second position relation, determining not to start the operation monitoring for the moving object.
In a preferred embodiment, the first determining module 630 is further configured to: determining the marking range of the human body object in the monitoring image of the current frame; determining the image position of a moving object in a monitoring image of a current frame; if the image position of the moving object is located within the mark range of the human body object, determining that the relative position relationship between the moving object and the human body object belongs to a first position relationship; if the image position of the moving object is outside the marker range of the human object, it is determined that the relative positional relationship between the moving object and the human object belongs to the second positional relationship.
In a preferred embodiment, the first determining module 630 specifically identifies the moving object in the monitored image of the current frame by: determining at least one first corner target in the monitoring image of the current frame through a corner detection algorithm; respectively calculating the characteristic distance of the corner target between each first corner target and each second corner target in the monitoring image of the previous frame aiming at each first corner target; and determining two corner point targets with the characteristic distance between the corner point targets larger than zero and smaller than a preset threshold value as the same corner point target, and determining the corner point target as a moving object in the monitoring image of the current frame.
In a preferred embodiment, the system further comprises a focusing module (not shown in the figure) for calculating a ratio of the height value of the marking range of the human body object to the height value of the monitoring image; and if the ratio is smaller than the preset ratio, generating a control signal to adjust the shooting focal length of the target monitoring equipment until the ratio is equal to the preset ratio.
In a preferred embodiment, the first determining module 630 specifically calculates the feature distance of the corner object between the first corner object and any one of the second corner objects by: extracting a first preset feature vector of a first corner target and a second preset feature vector of any second corner target; and calculating the Euclidean distance between a first preset feature vector of the first corner point target and a second preset feature vector of any second corner point target, and determining the Euclidean distance as the feature distance of the corner point target.
In a preferred embodiment, the device further comprises a counting module (not shown in the figure) for counting the number of times of generating the alarm signal within a preset time period; and sending out different alarm information according to the counted times of the alarm signals.
Referring to fig. 6, fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. As shown in fig. 6, the electronic device 800 includes a processor 810, a memory 820, and a bus 830.
The memory 820 stores machine-readable instructions executable by the processor 810, when the electronic device 800 runs, the processor 810 and the memory 820 communicate through the bus 830, and when the machine-readable instructions are executed by the processor 810, the steps of the substation outdoor operation monitoring method in the above embodiment may be executed.
The embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored on the storage medium, and when the computer program is executed by a processor, the steps of the substation outdoor operation monitoring method in the foregoing embodiments may be executed.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions, if implemented in software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer readable memory executable by a processor. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a memory, and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned memory comprises: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present application, and are used for illustrating the technical solutions of the present application, but not limiting the same, and the scope of the present application is not limited thereto, and although the present application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope disclosed in the present application; such modifications, changes or substitutions do not depart from the spirit and scope of the exemplary embodiments of the present application, and are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A substation outdoor operation monitoring method is characterized by comprising the following steps:
acquiring a monitoring image captured by target monitoring equipment in real time;
identifying a moving object in the monitoring image of the current frame aiming at the monitoring image of the current frame;
determining whether to initiate job monitoring for the moving object;
if the operation monitoring aiming at the moving object is determined to be started, determining whether the moving object meets the high-altitude outdoor operation criterion of the transformer substation;
and if the moving object does not meet the high-altitude outdoor operation rule of the transformer substation, generating an alarm signal, wherein the alarm signal is used for indicating that an event violating the high-altitude outdoor operation rule of the transformer substation occurs in the monitoring range of the target monitoring equipment.
2. The method according to claim 1, wherein the step of determining whether to initiate job monitoring for the moving object specifically comprises:
identifying whether a human body object exists in the monitoring image of the current frame;
if no human body object exists in the monitoring image of the current frame, determining to start operation monitoring for the moving object;
if the human body object exists in the monitoring image of the current frame, determining the relative position between the moving object and the human body object;
determining to start the operation monitoring for the moving object if the relative position between the moving object and the human body object belongs to a first position relation;
and if the relative position between the moving object and the human body object belongs to the second position relation, determining not to start the operation monitoring for the moving object.
3. The method according to claim 2, characterized in that the step of determining the relative position between the moving object and the human object comprises in particular:
determining the marking range of the human body object in the monitoring image of the current frame;
determining the image position of a moving object in a monitoring image of a current frame;
if the image position of the moving object is located within the mark range of the human body object, determining that the relative position relationship between the moving object and the human body object belongs to a first position relationship;
if the image position of the moving object is outside the marker range of the human object, it is determined that the relative positional relationship between the moving object and the human object belongs to the second positional relationship.
4. The method of claim 1, wherein the moving object in the monitored image of the current frame is identified by:
determining at least one first corner target in the monitoring image of the current frame through a corner detection algorithm;
respectively calculating the characteristic distance of the corner target between each first corner target and each second corner target in the monitoring image of the previous frame aiming at each first corner target;
determining two corner point targets with the characteristic distance between the corner point targets larger than zero and smaller than a preset threshold value as the same corner point target, and determining the corner point targets as moving objects in the monitoring image of the current frame.
5. The method of claim 3, further comprising:
calculating the ratio of the height value of the marking range of the human body object to the height value of the monitoring image;
and if the ratio is smaller than a preset ratio, generating a control signal to adjust the shooting focal length of the target monitoring equipment until the ratio is equal to the preset ratio.
6. The method according to claim 4, characterized in that the corner object feature distance between a first corner object and any second corner object is calculated by:
extracting a first preset feature vector of a first corner target and a second preset feature vector of any one second corner target;
and calculating the Euclidean distance between a first preset feature vector of the first corner point target and a second preset feature vector of any one second corner point target, and determining the Euclidean distance as the feature distance of the corner point target.
7. The method of claim 1, further comprising:
counting the times of generating the alarm signal in a preset time period;
and sending out different alarm information according to the counted times of the alarm signals.
8. The utility model provides a transformer substation outdoor operation detection device which characterized in that includes:
the acquisition module is used for acquiring a monitoring image captured by the target monitoring equipment in real time;
the first identification module is used for identifying a moving object in the monitoring image of the current frame aiming at the monitoring image of the current frame;
the system comprises a first judgment module, a second judgment module and a monitoring module, wherein the first judgment module is used for determining whether to start operation monitoring aiming at a moving object;
the second judgment module is used for determining whether the moving object meets the high-altitude outdoor operation criterion of the transformer substation if the operation monitoring aiming at the moving object is determined to be started;
and the signal module is used for generating an alarm signal if the moving object does not meet the high-altitude outdoor operation rule of the transformer substation, wherein the alarm signal is used for indicating that an event violating the high-altitude outdoor operation rule of the transformer substation occurs in the monitoring range of the target monitoring equipment.
9. An electronic device, comprising: a processor, a memory and a bus, the memory storing machine readable instructions executable by the processor, the processor and the memory communicating over the bus when the electronic device is running, the processor executing the machine readable instructions to perform the steps of the substation outdoor operations monitoring method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that the storage medium has stored thereon a computer program which, when being executed by a processor, performs the steps of the substation outdoor operation monitoring method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111101042.0A CN113869166A (en) | 2021-09-18 | 2021-09-18 | Substation outdoor operation monitoring method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111101042.0A CN113869166A (en) | 2021-09-18 | 2021-09-18 | Substation outdoor operation monitoring method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113869166A true CN113869166A (en) | 2021-12-31 |
Family
ID=78992914
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111101042.0A Pending CN113869166A (en) | 2021-09-18 | 2021-09-18 | Substation outdoor operation monitoring method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113869166A (en) |
-
2021
- 2021-09-18 CN CN202111101042.0A patent/CN113869166A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6144656B2 (en) | System and method for warning a driver that visual recognition of a pedestrian may be difficult | |
| US9754160B2 (en) | Method and device for detecting gathering of objects based on stereo vision as well as non-transitory computer-readable medium | |
| CN101167086A (en) | Human detection and tracking for security applications | |
| CN107657244B (en) | Human body falling behavior detection system based on multiple cameras and detection method thereof | |
| CN109448326B (en) | Geological disaster intelligent group defense monitoring system based on rapid image recognition | |
| EA018349B1 (en) | Method for video analysis | |
| CN104966304A (en) | Kalman filtering and nonparametric background model-based multi-target detection tracking method | |
| CN113112480B (en) | Video scene change detection method, storage medium and electronic device | |
| CN109145696B (en) | Old people falling detection method and system based on deep learning | |
| CN116152863B (en) | Personnel information identification method and device, electronic equipment and storage medium | |
| CN111382610B (en) | Event detection method and device and electronic equipment | |
| CN113505638B (en) | Method and device for monitoring traffic flow and computer readable storage medium | |
| CN112673377A (en) | Monitoring device and method for monitoring man overboard | |
| CN111383248A (en) | Method and device for judging red light running of pedestrian and electronic equipment | |
| KR102259981B1 (en) | Visual range measurement and alarm system based on video analysis and method thereof | |
| CN113505643A (en) | Violation target detection method and related device | |
| CN108111802B (en) | Video monitoring method and device | |
| CN117132768A (en) | License plate and face detection and desensitization method and device, electronic equipment and storage medium | |
| CN111753587B (en) | Ground falling detection method and device | |
| CN114556449A (en) | Obstacle detection and re-identification method and device, movable platform and storage medium | |
| CN114821978B (en) | Method, device and medium for eliminating false alarm | |
| CN113869166A (en) | Substation outdoor operation monitoring method and device | |
| US20210304417A1 (en) | Observation device and observation method | |
| CN115115978A (en) | Object identification method and device, storage medium and processor | |
| JP7243372B2 (en) | Object tracking device and object tracking method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |