Substation image acquisition and analysis method, system, equipment and medium

Abstract

The invention discloses a transformer substation image acquisition and analysis method, which comprises the following steps of: acquiring distribution information of image acquisition devices in a transformer substation, determining an image acquisition area according to working parameters of the image acquisition devices, and inserting the image acquisition area into a transformer substation map; identifying the acquired image and positioning an abnormal object to obtain an identification and positioning result, and determining a motion parameter of the abnormal object; determining the frequency regulation variable containing the lag time of the adjacent image collector, and sending the frequency regulation variable and the abnormal characteristics of the abnormal object to the adjacent image collector; and for any image collector, the image acquisition frequency is determined in real time according to the identification and positioning result of the image collector and the frequency adjustment quantity sent to the image collector by the adjacent image collector. According to the method, the collection frequency is updated in real time and the collection frequency of the adjacent image collector is adjusted according to the positioning recognition result of the image collector, so that high-frequency collection is carried out in the time period where abnormal objects possibly exist, low-frequency collection is carried out under the normal condition, and the resource consumption is reduced while the recognition accuracy is ensured.

Description

Technical Field

[0001] This invention relates to the field of substation environmental monitoring technology, specifically to a substation image acquisition and analysis method, system, equipment, and medium. Background Technology

[0002] Image acquisition and analysis of substations is a technical means used in power systems to monitor, detect, and analyze the operating status of substations. By combining image acquisition technology with modern image processing and machine learning techniques, the status of substation equipment can be obtained in real time, anomalies can be detected, fault diagnosis and early warning can be performed, thereby improving the safety, reliability, and intelligence level of substations.

[0003] In a substation setting, under normal circumstances, all electrical equipment is in a stable state, and its operating data can be uploaded to the central terminal via the network for risk monitoring. However, for some external influencing factors, such as animals, it is necessary to use an image acquisition and analysis system for monitoring. Existing image acquisition and analysis systems are all fixed-frequency real-time monitoring systems, which consume a lot of resources. How to optimize the existing image acquisition and analysis system is the technical problem that this invention aims to solve. Summary of the Invention

[0004] The purpose of this invention is to provide a method, system, equipment, and medium for substation image acquisition and analysis, which ensures recognition accuracy while reducing resource consumption and solves the problems existing in the prior art.

[0005] This invention is achieved through the following technical solution: In a first aspect, the first embodiment of the present invention provides a substation image acquisition and analysis method, comprising: Obtain the distribution information of image acquisition devices in the substation, determine the image acquisition area based on the operating parameters of the image acquisition devices, and insert the acquisition area into the substation map; The image acquisition device acquires images, identifies and locates abnormal objects in the acquired images to obtain identification and location results, determines the motion parameters of the abnormal objects, and when an abnormal object is located, the image acquisition device locally retains the corresponding image and identification and location results for a preset retention time. The frequency adjustment amount, including the lag time, of the adjacent image acquisition devices is determined based on the motion parameters, and the frequency adjustment amount and the abnormal characteristics of the abnormal object are sent to the adjacent image acquisition devices. For any image acquisition device, the image acquisition frequency is determined in real time based on its identification and positioning results and the frequency adjustment amount sent to it by adjacent image acquisition devices.

[0006] Furthermore, the specific method for obtaining the distribution information of image acquisition devices in the substation and determining the image acquisition area based on the operating parameters of the image acquisition devices includes: Search the image acquisition device's installation location, acquisition angle, and acquisition wide angle in the registration database. The acquisition angle is the centerline direction of the image acquisition device. The observation area is calculated based on the installation location, acquisition angle, and acquisition wide-angle. The interface between the observation area and the horizontal plane is used as the image acquisition area.

[0007] Furthermore, the specific method for identifying and locating abnormal objects in the acquired images, and determining the motion parameters of the abnormal objects, includes: Anomalies are read from a pre-defined anomaly feature table, and the image is traversed based on the anomalies to calculate the matching degree in real time. The anomaly feature table contains anomaly object items and anomaly feature items. When the matching degree reaches a preset matching degree threshold, the image matches an abnormal feature, and the matched area is recorded as the location of the abnormal object. The positions of the same abnormal objects are arranged according to the image acquisition time, the displacement is determined based on the position, and the motion velocity and motion acceleration are determined based on the displacement as motion parameters.

[0008] Furthermore, after the step of recording the matched area as the location of the abnormal object when the matching degree reaches a preset matching degree threshold, the method further includes: Record the number of successful matches for each abnormal feature, and update the order of data items in the abnormal feature table based on the number of successful matches.

[0009] Furthermore, the specific method for determining the frequency adjustment amount containing lag time of adjacent image acquisition devices based on motion parameters includes: The motion parameters are input into a preset trajectory simulation model to determine the predicted trajectory; The required time to reach the acquisition area of ​​the adjacent image acquisition device is determined based on the predicted trajectory, and is used as the lag time; wherein, the adjacent image acquisition device is the nearest image acquisition device on the predicted trajectory; Determine the frequency adjustment amount based on the abnormal object; The frequency adjustment amount containing absolute time is determined based on the lag time.

[0010] Furthermore, the specific method for determining the image acquisition frequency in real time based on its identification and positioning results and the frequency adjustment amount sent to it by adjacent image acquisition devices includes: Determine the fundamental frequency based on the identified anomalous objects; Query the frequency adjustment values ​​sent to it by other image acquisition devices at the current moment; The image acquisition frequency is determined based on the fundamental frequency and the frequency adjustment.

[0011] Furthermore, the method also includes: A forwarding count item is inserted into the identification and positioning results. The forwarding count item is incremented by one each time the abnormal features of the abnormal object are forwarded. Receive the monitoring level input by the administrator and determine the number of times threshold based on the monitoring level; When the number of forwardings reaches the threshold, the image acquisition device reports abnormal features to the central terminal; The system broadcasts abnormal characteristics, reads the identification and positioning results of each image acquisition device, fits the motion trajectory on the substation map based on the identification and positioning results of each image acquisition device, and displays it.

[0012] Secondly, another embodiment of the present invention provides a substation image acquisition and analysis system, used in the substation image acquisition and analysis method described in the first embodiment, the system comprising: The map creation module is used to obtain the distribution information of image acquisition devices in the substation, determine the acquisition area based on the parameters of the image acquisition devices, and insert the substation map. The abnormal object recognition module is used to acquire images collected by the image acquisition device, identify and locate abnormal objects in the acquired images to obtain recognition and location results, determine the motion parameters of the abnormal objects, and when an abnormal object is located, the image acquisition device locally retains the corresponding image and recognition and location results for a preset duration. The adjustment amount determination module is used to determine the frequency adjustment amount containing lag time of the adjacent image acquisition device based on the motion parameters, and send the frequency adjustment amount and the abnormal features of the abnormal object to the adjacent image acquisition device. The frequency update module is used to determine the image acquisition frequency in real time for any image acquisition device based on its identification and positioning results and the frequency adjustment amounts sent to it by other image acquisition devices.

[0013] Thirdly, another embodiment of the present invention provides an electronic device comprising: a processor, an input device, an output device, and a memory, wherein the processor, the input device, the output device, and the memory are interconnected, the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to invoke the program instructions to execute the method described in the first embodiment above.

[0014] Fourthly, another embodiment of the present invention provides a computer-readable storage medium storing a computer program, the computer program including program instructions that, when executed by a processor, cause the processor to perform the method described in the first embodiment above.

[0015] Compared with the prior art, the present invention has the following advantages and beneficial effects: This invention provides a substation image acquisition and analysis method, system, device, and medium. The acquisition frequency is updated in real time based on the positioning and identification results of the image acquisition device. At the same time, the acquisition frequency of adjacent image acquisition devices is adjusted according to the positioning and identification results. Each image acquisition device, while autonomously determining its acquisition frequency, is also influenced by adjacent image acquisition devices, causing it to acquire at a high frequency during time periods when abnormal objects are more likely to exist, and at a low frequency under normal circumstances. This ensures recognition accuracy while reducing resource consumption. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of the present invention and should not be considered as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort. In the drawings: Figure 1 This is a flowchart of a substation image acquisition and analysis method provided in the first embodiment of the present invention; Figure 2 A structural block diagram of a substation image acquisition and analysis system is provided as another embodiment of the present invention. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the embodiments and accompanying drawings. The illustrative embodiments and descriptions of the present invention are only used to explain the present invention and are not intended to limit the present invention.

[0018] like Figure 1 As shown, the first embodiment of the present invention provides a substation image acquisition and analysis method, the method comprising the following steps: S100: Obtain the distribution information of image acquisition devices in the substation, determine the image acquisition area based on the parameters of the image acquisition devices, and insert the acquisition area into the substation map.

[0019] An image acquisition device is a device that acquires images, such as a camera. In this embodiment of the invention, a fixed-angle camera is generally used, which offers higher stability. Furthermore, a fixed-angle camera at the same cost provides higher resolution than an omnidirectional camera. For a fixed-angle camera, its acquisition area can be determined based on its operating parameters; this area is called the acquisition region. This application inserts the acquisition region into a substation map, using the map's own scale. Figure 1 It is usually a top view, which represents known data.

[0020] Methods for obtaining the distribution information of image acquisition devices in a substation and determining the image acquisition area based on the operating parameters of the image acquisition devices include: Search the image acquisition device's installation location, acquisition angle, and acquisition wide angle in the registration database. The acquisition angle is the direction of the image acquisition device's centerline. The observation area is calculated based on the installation location, acquisition angle, and acquisition wide-angle; the observation area is a cone-shaped area. Calculate the interface between the observation area and the horizontal plane, use it as the image acquisition area, and insert it into the substation map.

[0021] When the image acquisition device is installed, the installation location, acquisition angle, and acquisition wide angle are recorded simultaneously. The acquisition angle is the direction of the centerline of the image acquisition device. The observation area is calculated based on the installation location, acquisition angle, and acquisition wide angle. The observation area can be understood as a cone, which is a cone-shaped region. The interface between the observation area and the horizontal plane is calculated, thereby making the observation area two-dimensional and then inserting it into the substation map.

[0022] S200: Acquire images captured by the image acquisition device, identify and locate abnormal objects in the acquired images to obtain identification and location results, determine the motion parameters of the abnormal objects, and when an abnormal object is located, the image acquisition device locally retains the corresponding image and identification and location results for a preset retention time.

[0023] Each image acquisition device continuously acquires and identifies images during operation. The identification process generally relies on a convolutional recognition model. That is, the management pre-computes the convolutional features of various abnormal objects. Based on the pre-computed convolutional features of various abnormal objects, abnormal objects can be located in the images. The image acquisition device operates at a certain frequency, and the acquired images themselves have time labels. Therefore, the identified abnormal objects also have time labels. By arranging the identified abnormal objects according to their time labels, the motion parameters of the abnormal objects can be determined. The motion parameters include displacement, velocity, and acceleration.

[0024] It should be noted that the image acquisition device acquires many images. When an abnormal object is detected, the corresponding image and the identification and location results (identified abnormal object) need to be recorded. The recording duration is preset by the administrator, and the longer the recording time, the better, if storage space allows.

[0025] In one example of the technical solution of this invention, the abnormal objects are mostly animals that should not appear in the substation scene. The determined motion parameters are to determine where the abnormal object is moving and how fast it is moving. In practical applications, the probability of animals appearing in each location is relatively low. Therefore, the frequency of the image acquisition device is adjustable to optimize costs. Generally, the frequency will be higher when there are abnormal objects, and the frequency will decrease over time when there are no abnormal objects for a long time.

[0026] Specific methods for identifying and locating anomalous objects in acquired images and determining their motion parameters include: The system reads abnormal features from a pre-defined abnormal feature table, traverses the image based on the abnormal features, and calculates the matching degree in real time. The abnormal feature table contains abnormal object items and abnormal feature items. When the matching degree reaches the preset matching degree threshold, the matching area is recorded as the location of the abnormal object; The positions of the same abnormal objects are arranged according to the image acquisition time. The displacement is determined based on the position, and the motion velocity and acceleration are determined based on the displacement as motion parameters.

[0027] In one example of the technical solution of this invention, the process of identifying abnormal objects is described in detail. Based on the image acquisition device, the acquisition time is recorded during the image acquisition process. Abnormal features are read from a preset abnormal feature table. The image is traversed according to the abnormal features, and the matching degree is calculated in real time. Abnormal features are small image features, and their size is much smaller than the size of the image. Therefore, it is necessary to traverse and compare them. The traversal and matching process of the same image can obtain multiple matching degrees. Once a certain matching degree reaches a preset matching degree threshold, the current traversal position is recorded, and the matching area is obtained as the located abnormal object. The current traversal position is the location of the abnormal object.

[0028] Since the abnormal objects to be detected in this application are animals, and animals do not jump in space, from the perspective of images, once an abnormal object is detected in an image, there is a high probability that an abnormal object can also be detected in images at adjacent times, and the identified positions are continuous. The positions of the same abnormal object are arranged according to the acquisition time of the images, the displacement is determined according to the position, and the motion speed and motion acceleration are determined according to the displacement as motion parameters.

[0029] It should be noted that after the step of recording the matched area as the location of the abnormal object when the matching degree reaches the preset matching degree threshold, the method further includes: recording the number of successful matches for each abnormal feature, and updating the order of data items in the abnormal feature table according to the number of successful matches.

[0030] After identifying anomaly features, the number of successful matches for each feature is recorded, and the order of data items in the anomaly feature table is updated based on the number of successful matches. The purpose of this process is to improve matching efficiency, because there are multiple anomaly features in the anomaly feature table, and each feature needs to be matched once in the image. The anomaly features are then reordered based on the number of matches. The practical significance is that for an image acquisition device, the more frequently an anomalous object is identified, the earlier its corresponding anomaly features will be identified during the actual identification process. However, the effect is not significant, because regardless of the order, all anomaly features in the anomaly feature table need to participate in a matching process to prevent missed detections. However, if costs are limited or higher speed is required, the identification process of each image acquisition device may only select the first few anomaly features in the corresponding anomaly feature table for traversal matching. In this case, the traversal matching speed is extremely fast, and the identification accuracy is also relatively high (not 100%, slightly lower than global matching).

[0031] S300: Determines the frequency adjustment amount with lag time for adjacent image acquisition devices based on motion parameters, and sends the frequency adjustment amount and the abnormal features of abnormal objects to the adjacent image acquisition devices.

[0032] Motion parameters represent the movement of an abnormal object. Based on these parameters, it can be predicted how long it will take for the abnormal object to appear in adjacent image acquisition units. Adjacent image acquisition units are generally the nearest units in the four cardinal directions (north, south, east, and west). This time elapsed is called the lag time. The frequency adjustment is typically a positive value, indicating how much the adjacent image acquisition units should increase their frequency based on the elapsed time. The practical significance of this process is that it allows image acquisition units to increase their acquisition frequency when there is a high probability of detecting an abnormal object, thereby improving the real-time performance of abnormal object detection.

[0033] Specific methods for determining the frequency adjustment amount, including hysteresis time, of adjacent image acquisition devices based on motion parameters include: Input the motion parameters into the preset trajectory simulation model to determine the predicted trajectory; The required time to reach the acquisition area of ​​the adjacent image acquisition device is determined based on the predicted trajectory, and is used as the lag time; where the adjacent image acquisition device is the nearest image acquisition device on the predicted trajectory. Determine the frequency adjustment amount based on the abnormal object; The frequency adjustment amount containing absolute time is determined based on the lag time.

[0034] The abnormal objects in the technical solution of this invention mainly refer to animals, whose movements are predictable. The movement trajectories of various objects are statistically analyzed, and a small segment of the movement trajectory is extracted and converted into motion parameters (motion parameters exist at each time point, so the converted motion parameters are actually a time series) as features. The entire movement trajectory is used as a label to construct a sample set. A neural network model is trained based on the sample set. When the error rate of the neural network model is sufficiently small, the neural network model is output as a trajectory simulation model.

[0035] Specifically, motion parameters are input into a preset trajectory simulation model to determine the predicted trajectory. Based on the predicted trajectory, the required time to reach the acquisition area of ​​the adjacent image acquisition device is determined as the lag time. Based on the obtained predicted trajectory, the adjacent image acquisition devices are limited as described above. A search is performed along the direction of the predicted trajectory, and the nearest image acquisition device found is designated as the adjacent image acquisition device. Then, a frequency adjustment amount is determined based on abnormal objects. The relationship between abnormal objects and frequency adjustment amounts is predetermined. If multiple abnormal objects are detected, the obtained frequency adjustment amounts need to be superimposed. Regarding lag time and absolute time, the lag time represents a time period, such as one hour, while the absolute time is a specific set of time points, such as 13:00.

[0036] S400: For any image acquisition device, the image acquisition frequency is determined in real time based on its identification and positioning results and the frequency adjustment amount sent to it by other image acquisition devices.

[0037] In one embodiment of the technical solution of the present invention, for any image acquisition device, the image acquisition frequency is adjusted according to its own recognition and positioning results. At the same time, it may also receive frequency adjustment amounts sent to it by other image acquisition devices. By combining its own adjustment results and the frequency adjustment amounts sent to it by other image acquisition devices, the final image acquisition frequency can be obtained.

[0038] The specific methods for determining the image acquisition frequency in real time based on its identification and positioning results and the frequency adjustment values ​​sent to it by other image acquisition devices include: Determine the fundamental frequency based on the identified anomalous objects; Query the frequency adjustment values ​​sent to it by other image acquisition devices at the current moment; The image acquisition frequency is determined based on the fundamental frequency and the frequency adjustment.

[0039] In one example of the technical solution of the present invention, the process of adjusting the image acquisition frequency is specifically described. For any image acquisition device, the base frequency is determined based on the identified abnormal objects. The base frequency is generally related to the abnormality level of the abnormal objects and the number of abnormal objects. The abnormality level of the abnormal objects is an attribute value preset by the management and can be read directly. The higher the abnormality level, the more dangerous the corresponding abnormal object is. The higher the abnormality level, the higher the base frequency. The more abnormal objects there are, the higher the base frequency.

[0040] At the same time, query the frequency adjustment values ​​sent to it by other image acquisition devices at the current moment, sum the base frequency and the frequency adjustment values, and obtain the final image acquisition frequency.

[0041] It is worth mentioning that the method for determining the fundamental frequency is positively correlated with both the anomaly level and the number of anomalous objects. One such method is:

[0042] In the formula, f is the fundamental frequency. Here, N is the preset correction coefficient, and N is the number of abnormal objects. Let be the anomaly level of the i-th anomalous object; t represents the time span since the last detection of an anomalous object. This represents the base frequency at the time the anomalous object was last detected. In this scheme, the effect of quantity is exponential, meaning that quantity has a greater impact on the base frequency. Generally, the quantity is one; if the quantity is large, the base frequency will increase exponentially until it reaches its highest frequency. Furthermore, if no anomalous object is detected, the difference between the current time and the time when the anomalous object was last detected is calculated; the larger the difference, the higher the frequency. The smaller the value, the smaller the calculated fundamental frequency. This means that if no abnormal object is detected for a long time, the fundamental frequency will continue to decrease.

[0043] As a preferred embodiment of the technical solution of the present invention, the method further includes: Insert a forwarding count item into the identification and location results. The forwarding count item increments by one each time the abnormal features of the abnormal object are forwarded. Receive the monitoring level input by the administrator and determine the number of times threshold based on the monitoring level; When the number of forwards reaches the threshold, the image acquisition device reports abnormal features to the central terminal; The system broadcasts abnormal characteristics, reads the identification and positioning results of each image acquisition device, fits the motion trajectory on the substation map based on the identification and positioning results of each image acquisition device, and displays it.

[0044] In one example of the technical solution of the present invention, a recording tag is added during the positioning and identification process of all image acquisition devices to record the number of times it is forwarded. In layman's terms, it means how many image acquisition devices forwarded the abnormal object to the adjacent image acquisition devices. Its meaning is that when a certain image acquisition device detects an abnormal object, how many image acquisition devices detected it before that.

[0045] Based on this, the monitoring level input by the administrator is received, and the number of forwardings thresholds is determined according to the monitoring level. The higher the monitoring level, the more stringent the detection needs to be, and the lower the number of forwardings thresholds are, making it easier to reach the threshold. When the number of forwardings reaches the threshold, the image acquisition unit reports the abnormal features to the central terminal. After receiving the abnormal features, the central terminal sends the abnormal features to all image acquisition units, reads the identification and positioning results of each image acquisition unit, and displays all identification and positioning results with the help of the substation map. This can intuitively show what abnormal objects are in and around the substation and what their trajectories are.

[0046] This invention provides a substation image acquisition and analysis method that updates the acquisition frequency in real time based on the positioning and recognition results of the image acquisition devices. At the same time, it adjusts the acquisition frequency of adjacent image acquisition devices based on the positioning and recognition results. Each image acquisition device, while autonomously determining its acquisition frequency, is also influenced by adjacent image acquisition devices, causing it to acquire at a high frequency during time periods when abnormal objects are more likely to exist, and at a low frequency under normal circumstances. This ensures recognition accuracy while reducing resource consumption.

[0047] like Figure 2 As shown, another embodiment of the present invention provides a substation image acquisition and analysis system, the system 10 comprising: The map creation module 11 is used to obtain the distribution information of image acquisition devices in the substation, determine the acquisition area according to the parameters of the image acquisition devices, and insert the substation map. The abnormal object recognition module 12 is used to acquire images collected by the image acquisition device, identify and locate abnormal objects in the acquired images to obtain recognition and location results, determine the motion parameters of the abnormal objects, and when an abnormal object is located, the image acquisition device locally retains the corresponding image and recognition and location results for a preset duration. The adjustment amount determination module 13 is used to determine the frequency adjustment amount containing lag time of the adjacent image acquisition device according to the motion parameters, and send the frequency adjustment amount and the abnormal features of the abnormal object to the adjacent image acquisition device. The frequency update module 14 is used to determine the image acquisition frequency in real time for any image acquisition device based on its identification and positioning results and the frequency adjustment amount sent to it by other image acquisition devices.

[0048] The map creation module 11 includes: The information query unit is used to query the installation location, acquisition angle, and acquisition wide angle of the image acquisition device in the filing database; the acquisition angle is the direction of the centerline of the image acquisition device. An observation area calculation unit is used to calculate the observation area based on the installation location, acquisition angle, and acquisition wide-angle; the observation area is a cone-shaped area. The data acquisition area determination unit is used to calculate the interface between the data acquisition area and the horizontal plane, which is then used as the data acquisition area and inserted into the substation map.

[0049] The abnormal object recognition module 12 includes: An image acquisition unit is used to acquire images based on an image collector. The traversal matching unit is used to read abnormal features from a preset abnormal feature table, traverse the image based on the abnormal features, and calculate the matching degree in real time; wherein, the abnormal feature table contains abnormal object items and abnormal feature items; The region recording unit is used to record the matched region as the location of the abnormal object when the matching degree reaches a preset matching degree threshold. The displacement analysis unit is used to arrange the positions of the same abnormal object according to the image acquisition time, determine the displacement based on the position, and determine the motion velocity and motion acceleration based on the displacement as motion parameters. After an abnormal feature is matched, the number of successful matches for each abnormal feature is recorded, and the order of data items in the abnormal feature table is updated according to the number of successful matches.

[0050] The adjustment amount determination module 13 includes: The trajectory prediction unit is used to input the motion parameters into a preset trajectory simulation model to determine the predicted trajectory; The lag time calculation unit is used to determine the required time to reach the acquisition area of ​​the adjacent image acquisition device based on the predicted trajectory, as the lag time; wherein, the adjacent image acquisition device is the nearest image acquisition device on the predicted trajectory; The frequency query unit is used to determine the frequency adjustment amount based on abnormal objects. The data transmission unit is used to determine the frequency adjustment amount containing absolute time based on the lag time, and to send the frequency adjustment amount containing absolute time and the abnormal features of the abnormal object to the adjacent image acquisition unit.

[0051] The substation image acquisition and analysis system provided in this invention updates the acquisition frequency in real time based on the positioning and recognition results of the image acquisition devices. At the same time, it adjusts the acquisition frequency of adjacent image acquisition devices based on the positioning and recognition results. While each image acquisition device autonomously determines its acquisition frequency, it is also influenced by the adjacent image acquisition devices, causing it to acquire at a high frequency during time periods when abnormal objects are more likely to exist, and at a low frequency under normal circumstances. This ensures recognition accuracy while reducing resource consumption.

[0052] Another embodiment of the present invention provides an electronic device, which includes a processor, an input device, an output device, and a memory. The processor, the input device, the output device, and the memory are interconnected. The memory is used to store a computer program, which includes program instructions. The processor is configured to call the program instructions to execute the method described in the first embodiment above.

[0053] It should be understood that, in the embodiments of the present invention, the processor may be a Central Processing Unit (CPU), but it may also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0054] Input devices may include touchpads, microphones, etc., and output devices may include displays (LCDs, etc.), speakers, etc.

[0055] The memory may include read-only memory and random access memory, and provides instructions and data to the processor. A portion of the memory may also include non-volatile random access memory. For example, the memory may also store information about the device type.

[0056] In specific implementations, the processor, input device, and output device described in the embodiments of the present invention can execute the implementation of the method embodiments described in the embodiments of the present invention, or they can execute the implementation of the system embodiments described in the embodiments of the present invention, which will not be repeated here.

[0057] The present invention also provides an embodiment of a computer-readable storage medium storing a computer program, the computer program including program instructions, which, when executed by a processor, cause the processor to perform the method described in the first embodiment above.

[0058] The computer-readable storage medium can be an internal storage unit of the terminal described in the foregoing embodiments, such as the terminal's hard drive or memory. The computer-readable storage medium can also be an external storage device of the terminal, such as a plug-in hard drive, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card equipped on the terminal. Furthermore, the computer-readable storage medium can include both internal storage units and external storage devices of the terminal. The computer-readable storage medium is used to store the computer program and other programs and data required by the terminal. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0059] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0060] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the terminals and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0061] In the several embodiments provided in this application, it should be understood that the disclosed terminals and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices or units, or may be electrical, mechanical or other forms of connection.

[0062] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the claims and specification of the present invention.

Claims

1. A method for image acquisition and analysis in a substation, characterized in that, include: Obtain the distribution information of image acquisition devices in the substation, determine the image acquisition area based on the operating parameters of the image acquisition devices, and insert the acquisition area into the substation map; The image acquisition device acquires images, identifies and locates abnormal objects in the acquired images to obtain identification and location results, determines the motion parameters of the abnormal objects, and when an abnormal object is located, the image acquisition device locally retains the corresponding image and identification and location results for a preset duration. The frequency adjustment amount, including the lag time, of the adjacent image acquisition devices is determined based on the motion parameters, and the frequency adjustment amount and the abnormal characteristics of the abnormal object are sent to the adjacent image acquisition devices. For any image acquisition device, the image acquisition frequency is determined in real time based on its identification and positioning results and the frequency adjustment amount sent to it by adjacent image acquisition devices.

2. The method according to claim 1, characterized in that, The specific method for obtaining the distribution information of image acquisition devices in a substation and determining the image acquisition area based on the operating parameters of the image acquisition devices includes: Search the image acquisition device's installation location, acquisition angle, and acquisition wide angle in the registration database. The acquisition angle is the centerline direction of the image acquisition device. The observation area is calculated based on the installation location, acquisition angle, and acquisition wide-angle. The interface between the observation area and the horizontal plane is used as the image acquisition area.

3. The method according to claim 1, characterized in that, The specific methods for identifying and locating abnormal objects in the acquired images, and determining the motion parameters of the abnormal objects, include: Anomalies are read from a pre-defined anomaly feature table, and the image is traversed based on the anomalies to calculate the matching degree in real time. The anomaly feature table contains anomaly object items and anomaly feature items. When the matching degree reaches a preset matching degree threshold, the image matches an abnormal feature, and the matched area is recorded as the location of the abnormal object. The positions of the same abnormal objects are arranged according to the image acquisition time, the displacement is determined based on the position, and the motion velocity and motion acceleration are determined based on the displacement as motion parameters.

4. The method according to claim 3, characterized in that, After the step of recording the matched area as the location of the abnormal object when the matching degree reaches a preset matching degree threshold, the method further includes: Record the number of successful matches for each abnormal feature, and update the order of data items in the abnormal feature table based on the number of successful matches.

5. The method according to claim 1, characterized in that, The specific method for determining the frequency adjustment amount containing hysteresis time of adjacent image acquisition devices based on motion parameters includes: The motion parameters are input into a preset trajectory simulation model to determine the predicted trajectory; The required time to reach the acquisition area of ​​the adjacent image acquisition device is determined based on the predicted trajectory, and is used as the lag time; wherein, the adjacent image acquisition device is the nearest image acquisition device on the predicted trajectory; Determine the frequency adjustment amount based on the abnormal object; The frequency adjustment amount containing absolute time is determined based on the lag time.

6. The method according to claim 1, characterized in that, The specific method for determining the image acquisition frequency in real time based on its identification and positioning results and the frequency adjustment amount sent to it by adjacent image acquisition devices includes: Determine the fundamental frequency based on the identified anomalous objects; Query the frequency adjustment values ​​sent to it by other image acquisition devices at the current moment; The image acquisition frequency is determined based on the fundamental frequency and the frequency adjustment.

7. The method according to claim 1, characterized in that, The method further includes: A forwarding count item is inserted into the identification and positioning results. The forwarding count item is incremented by one each time the abnormal features of the abnormal object are forwarded. Receive the monitoring level input by the administrator and determine the number of times threshold based on the monitoring level; When the number of forwardings reaches the threshold, the image acquisition device reports abnormal features to the central terminal; The system broadcasts abnormal characteristics, reads the identification and positioning results of each image acquisition device, fits the motion trajectory on the substation map based on the identification and positioning results of each image acquisition device, and displays it.

8. A substation image acquisition and analysis system, characterized in that, The system is used to implement the substation image acquisition and analysis method as described in any one of claims 1-7, the system comprising: The map creation module is used to obtain the distribution information of image acquisition devices in the substation, determine the acquisition area based on the parameters of the image acquisition devices, and insert the substation map. The abnormal object recognition module is used to acquire images collected by the image acquisition device, identify and locate abnormal objects in the acquired images to obtain recognition and location results, determine the motion parameters of the abnormal objects, and when an abnormal object is located, the image acquisition device locally retains the corresponding image and recognition and location results for a preset duration. The adjustment amount determination module is used to determine the frequency adjustment amount containing lag time of the adjacent image acquisition device based on the motion parameters, and send the frequency adjustment amount and the abnormal features of the abnormal object to the adjacent image acquisition device. The frequency update module is used to determine the image acquisition frequency in real time for any image acquisition device based on its identification and positioning results and the frequency adjustment amounts sent to it by other image acquisition devices.

9. An electronic device comprising a processor, an input device, an output device, and a memory, wherein the processor, input device, output device, and memory are interconnected, and the memory is used to store a computer program, the computer program comprising program instructions, characterized in that, The processor is configured to invoke the program instructions to perform the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, the computer program including program instructions that, when executed by a processor, cause the processor to perform the method as described in any one of claims 1-7.

Images