A method and system for finding the optimal monitoring point of a video surveillance terminal

Abstract

This invention discloses a method and system for determining the optimal monitoring point of a video surveillance terminal. Based on the equipment location data in the substation to be monitored, a substation spatial model is established. Based on the lighting conditions, shading conditions, shooting distance, and shooting angle at the video surveillance terminal, a video surveillance terminal model is established. Based on the substation spatial model and the video surveillance terminal model, a two-stage strategy is used to obtain the optimal terminal point of the substation video surveillance terminal. Considering the four major factors affecting the working quality of the video surveillance terminal—shooting distance, shooting angle, lighting intensity, and shading—the method balances the influence of the main body of the equipment and key components, thereby achieving the acquisition of the optimal terminal point.

Description

Technical Field

[0001] This invention relates to the field of video surveillance technology, and in particular to a method and system for finding the optimal monitoring point of a video surveillance terminal. Background Technology

[0002] Video surveillance is a crucial component of security systems. Traditional surveillance systems consist of front-end cameras, transmission cables, and a video monitoring platform. Cameras can be categorized into network digital cameras and analog cameras, serving as the front-end for acquiring video image signals. It is a comprehensive system with strong preventative capabilities. Video surveillance is widely used in many situations due to its intuitiveness, accuracy, timeliness, and rich information content. In recent years, with the rapid development of computer, network, and image processing and transmission technologies, video surveillance technology has also made significant progress.

[0003] According to statistics from the State Grid Corporation of China, even with accurate positioning, video surveillance has a low accuracy rate in identifying substation equipment, highlighting the crucial importance of obtaining high-quality visible light and infrared inspection images. Besides the performance of the video surveillance terminal, the setting of the shooting point has the greatest impact on image quality. Different shooting points not only result in different spatial relationships between the equipment and the camera, directly affecting the size and orientation of the target equipment in the image, but also cause the camera to be affected differently by environmental factors such as sunlight, indirectly impacting image quality. Summary of the Invention

[0004] The purpose of this section is to outline some aspects of embodiments of the present invention and to briefly describe some preferred embodiments. Simplifications or omissions may be made in this section, as well as in the abstract and title of this application, to avoid obscuring the purpose of these documents; however, such simplifications or omissions should not be construed as limiting the scope of the invention.

[0005] In view of the aforementioned existing problems, the present invention is proposed.

[0006] Therefore, this invention provides a method and system for finding the optimal monitoring point of a video surveillance terminal, which can solve the problems of high cost of manual point setting and the ineffectiveness of preset points when the environment changes.

[0007] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a method for solving the optimal monitoring point of a video surveillance terminal, comprising:

[0008] Based on the equipment location data in the substation to be detected, a spatial model of the substation is established.

[0009] A video surveillance terminal model is established based on the lighting conditions, shading conditions, shooting distance, and shooting angle at the video surveillance terminal.

[0010] Based on the substation spatial model and the video surveillance terminal model, the optimal terminal location of the substation video surveillance terminal is obtained by combining a two-stage strategy.

[0011] As a preferred embodiment of the video surveillance terminal location autonomous generation method described in this invention, the two-stage strategy includes:

[0012] In the first stage, the suitability of spatial points as terminal points and shooting points is quantitatively calculated based on the shooting potential model;

[0013] In the second stage, points that meet the quality requirements are selected, and the optimal subset that can complete the detection task is chosen as the final solution.

[0014] As a preferred embodiment of the video surveillance terminal location autonomous generation method described in this invention, the two-stage strategy further includes:

[0015] Select a set of candidate points at the initial available detection locations;

[0016] Determine if there are any points in the initial candidate set whose potential matrix is ​​non-zero;

[0017] The point with the largest sum of the potential matrix elements in the candidate set is added to the inspection point set and removed from the candidate set;

[0018] Record the coordinates of the non-zero elements of the potential matrix of the selected point, and set the elements of these coordinates in the potential matrix of other points in the candidate set to zero;

[0019] Determine whether the inspection point set can meet the minimum face count requirement of certain equipment;

[0020] If the condition is not met, the process continues to determine whether there are points with a non-zero potential matrix.

[0021] If the condition is met, the elements in the rows of the potential matrices of other points in the candidate set containing these devices are set to zero, and then the process of determining whether there are points with non-zero potential matrices continues.

[0022] As a preferred embodiment of the video surveillance terminal location autonomous generation method described in this invention, the lighting conditions at the video surveillance terminal include:

[0023]

[0024]

[0025] in, This indicates the factors affecting illumination; different angles of illumination correspond to different influencing factors. It is the illumination angle, w ij Indicates device surface F ijThe influence function of illumination, μ1, μ2, These are constants. μ is the illumination influence coefficient, which means that the illumination influence coefficient is a constant within a certain illumination angle range, but the coefficient is different in different ranges.

[0026] As a preferred embodiment of the video surveillance terminal location autonomous generation method described in this invention, the optimal terminal locations include:

[0027]

[0028] in, For intelligent equipment to capture the target image, the illumination angle is η, where η is the backlighting rate, and F is the backlighting angle. k The effective pixel value of point K. This represents the effective pixel value of points on the target image captured by the intelligent equipment when the illumination angle is greater than 90°.

[0029] As a preferred embodiment of the video surveillance terminal location autonomous generation method described in this invention, the optimal terminal location further includes:

[0030] The relative area ratio of inspection points:

[0031]

[0032] in, This indicates the relative area ratio of the inspection points. This indicates that the intelligent equipment is capturing images of the device surface F at point k. ij At that time, face F ij The area in the camera frame, This indicates that the smart device is positioned at a safe distance from the device surface and directly facing the camera when shooting. ij Area within the camera frame.

[0033] As a preferred embodiment of the video surveillance terminal location autonomous generation method described in this invention, the optimal terminal location further includes:

[0034] The average relative area ratio of the inspection points is expressed as:

[0035]

[0036] Among them, using This indicates that the intelligent equipment is at point P. k The average relative area ratio of all equipment surfaces inspected is given by the number of inspection points (K).

[0037] As a preferred embodiment of the video surveillance terminal location autonomous generation method described in this invention, the optimal terminal location further includes:

[0038] if Sij ≠0, then S ij ≥Q ij Q ij =f i0 f ij q ij

[0039]

[0040] Among them, C1 ensures that the scheme can meet the quality requirements of the detection task, and C2 ensures that the scheme given by the automatic algorithm can meet the quantity requirements of the detection task, that is, the video surveillance terminal can capture all the equipment and their faces that need to be detected in a single flight mission.

[0041] This invention also proposes a system for finding the optimal monitoring point of a video surveillance terminal, characterized by comprising:

[0042] A substation spatial model generation module generates a substation spatial model based on the equipment location data to be detected in the substation.

[0043] A video surveillance terminal model generation module generates a video surveillance terminal model based on data such as the lighting conditions at the video surveillance terminal, the shading conditions at the video surveillance terminal, the shooting distance at the video surveillance terminal, and the shooting angle at the video surveillance terminal.

[0044] The optimal terminal location calculation module is used to calculate the optimal terminal location for the video surveillance terminal in the substation.

[0045] As a preferred embodiment of the video surveillance terminal location autonomous generation system described in this invention, the two-stage strategy further includes:

[0046]

[0047] Among them, u' PS This represents the projection potential of surface S onto point P. The concentration of pheromones representing the excitation potential on the equipment surface is used to characterize the difference in the importance of different areas for inspection and imaging. θ represents the imaging angle, and σ represents the pheromone concentration on the equipment surface. s Represents a surface micro-element.

[0048] The beneficial effects of this invention: This invention proposes a method and system for determining the optimal monitoring point of a video surveillance terminal. Considering four major factors affecting the working quality of the video surveillance terminal—including shooting distance, shooting angle, illuminance, and occlusion—the method weighs the impact of the main body of the equipment and key components to obtain the optimal terminal point. Specifically, it considers the four major factors affecting the working quality of the video surveillance terminal: the distance between the terminal and the monitored equipment, the angle between the location of the monitoring terminal and the equipment surface, the degree of influence of lighting and occlusion on the real-time monitoring image, and weighs the importance of different devices to obtain the optimal terminal deployment point. Attached Figure Description

[0049] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein:

[0050] Figure 1 A flowchart of a method and system for solving the optimal monitoring point of a video surveillance terminal is provided in one embodiment of the present invention;

[0051] Figure 2 This invention provides a method for finding the optimal monitoring point of a video surveillance terminal and a system point selection strategy diagram, as an embodiment of the present invention.

[0052] Figure 3 This invention provides a method for finding the optimal monitoring point of a video surveillance terminal and a diagram showing the relationship between the system's shooting angle and image quality, as part of one embodiment of the present invention.

[0053] Figure 4 This invention provides a method for determining the optimal monitoring point of a video surveillance terminal and a diagram showing the relationship between system shooting distance and quality;

[0054] Figure 5 A method and system for determining the optimal monitoring point of a video surveillance terminal, and a sunlight vector V, are provided in one embodiment of the present invention. sun1 Schematic diagram;

[0055] Figure 6 A method and system for determining the optimal monitoring point of a video surveillance terminal, and a sunlight vector V, are provided in one embodiment of the present invention. sun2 Schematic diagram; Detailed Implementation

[0056] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0057] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0058] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0059] This invention is described in detail with reference to the schematic diagrams. When detailing the embodiments of this invention, for ease of explanation, the cross-sectional views illustrating the device structure may be partially enlarged, not adhering to the usual scale. Furthermore, the schematic diagrams are merely examples and should not be construed as limiting the scope of protection of this invention. In actual fabrication, the three-dimensional spatial dimensions of length, width, and depth should be included.

[0060] Furthermore, in the description of this invention, it should be noted that the terms "upper," "lower," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are used solely for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. In addition, the terms "first," "second," or "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0061] Unless otherwise explicitly specified and limited, the terms "installation," "connection," and "joining" in this invention should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; similarly, they can refer to mechanical connections, electrical connections, or direct connections, or indirect connections through an intermediate medium, or internal connections between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0062] Example 1

[0063] Reference Figure 1-3This is the first embodiment of the present invention, which provides a method for solving the optimal monitoring point of a video surveillance terminal, including:

[0064] Step 102: Based on the equipment location data in the substation to be detected, establish a spatial model of the substation;

[0065] Furthermore, substations contain a wide variety and large number of electrical devices, with interconnecting cables. Calculating them entirely based on their actual form and dimensions would be unimaginably complex. Therefore, we constructed a simplified mathematical model of three components related to the detection point generation problem: the substation space, the electrical equipment, and the video detection terminal.

[0066] It should be noted that the substation space R in this invention S It consists of three parts: the space occupied by the electrical equipment, denoted as R. E No-fly zone, also known as safe distance between video detection terminals and equipment, is denoted as R. NF The space available for inspection by the video inspection terminal is denoted as R. F Obviously, located in R Equ Region and R NF Points within a region cannot be set as checkpoints, so all points that can be selected as inspection points are in region R. F area.

[0067] It should be noted that a charged object generates an electric field in space, and the magnitude of the electric potential can characterize the difference in potential energy of charges at different locations within that field. Inspired by this, if a shooting field is generated around the target to be photographed, the degree to which different points in space are suitable for shooting can be described by the shooting potential.

[0068] Furthermore, similar to electric potential, we naturally assume that at infinite distance from the target, the shooting potential is zero, and the closer to the target, the higher the shooting potential, because close-up shooting usually means that the target occupies a larger proportion of the frame, and the risk of distortion due to magnification is smaller.

[0069] Furthermore, the electric potential at a point in space is the result of superposition. For example, for a plane with a finite charge, the electric potential at that point can be considered as the superposition of the electric potentials generated by all charges on that plane. The proposed radio potential has similar properties. On the one hand, the radio field can be considered to be excited by information elements on the surface of the device, and the radio potential is the superposition of the radio potentials generated by all information elements. On the other hand, the radio potential at a point in space also reflects the superposition of potentials favorable and unfavorable to radio emission, similar to the superposition of potentials generated by positive and negative charges. The following section will introduce the expression form and superposition of radio potential.

[0070] It should be noted that, without considering image distortion, the more effective pixels the tar device occupies in the image captured by the video detection terminal, the better. The effective pixel count of the target is affected by the shooting distance, shooting angle, illumination, and occlusion, so the shooting potential model of this invention only considers these four factors, and it is obviously expandable. First, the shooting potential generated by the information elements on the device surface is discussed, and the method for calculating the potential of spatial points around a finite charged plane is as follows.

[0071]

[0072] Where, ρ σ S represents the surface charge density of the plane.

[0073] Furthermore, similar to the distribution of shooting potential, according to the lens imaging formula, when the distance becomes twice the original, the image size becomes 1 / 4. Therefore, when only the influence of shooting distance is considered, the shooting potential is the same as the potential.

[0074]

[0075] Where u PS σs represents the imaging potential from surface S to point P, ρ represents the information element on the device surface, and ρ represents the imaging potential from surface S to point P. σ s represents the information concentration of the information element, and d represents the distance from the element to point P.

[0076] It should be noted that different locations on the equipment surface have different levels of importance to the detection task. For some key local areas, such as the area where the instrument is located on the equipment surface, the quality requirements are higher. Similar to charge density, the information concentration parameter is a weighted approach that allows the video detection terminal to take into account both the entire surface and important local areas when selecting shooting points.

[0077] Furthermore, unlike electric charge and electromotive force, the facial information elements that generate radio potentials come from the projected facial micro-elements, because the shape of a three-dimensional object in a two-dimensional image is a projection result that takes into account the influence of the angle of incidence.

[0078]

[0079] Where Θ represents the angle between the connection vector between the video detection terminal and the in-plane component and the in-plane normal vector.

[0080] Furthermore, the shooting potential model reflects the impact of factors such as occlusion and lighting on shooting quality through the superposition of potential. When a part of the device surface is occluded, the shooting potential generated by the occluded part does not participate in the superposition of potentials, while sunlight is considered another source of shooting potential, denoted as u. PL Therefore, the total shooting potential is

[0081]

[0082] Among them, U p It is the overall shooting momentum of a spatial point, U' ps The shooting potential is generated by the device surface, U pl The shooting momentum is created by the light. It is the angle of illumination. This indicates that the magnitude of the shooting potential is related to the angle of illumination.

[0083] It should be noted that, by analogy with electric fields and potentials, a shooting potential model is proposed. By quantifying abstract and subjective shooting quality, different influencing factors can be superimposed numerically.

[0084] Step 104: Based on the lighting conditions, shading conditions, shooting distance, and shooting angle at the video surveillance terminal, establish a video surveillance terminal model;

[0085] Furthermore, since we are not concerned with the motion and control of the video detection terminal, we treat it as a point that can move between points in the model. To ensure the quality of the detected images, the video detection terminal should not capture images of devices at a distance, so a visual distance is set to ensure that the video detection terminal only captures images of devices appearing on the horizon.

[0086] Furthermore, this invention proposes that the target of the video detection terminal's photography is the six faces of a rectangular device. Let N = {1, 2, ..., n, ... N} be the set of devices.

[0087] It should be noted that the set F of device surfaces is denoted as F0. ij ={f ij |i∈N,j∈{1,2,..6}}.

[0088] Furthermore, based on the proposed substation scenario model, a model of four factors affecting the shooting quality of the video detection terminal is presented. Assuming that the video detection terminal can quickly reach the predetermined position and work stably, when the video detection terminal shoots from different positions, the distance from the camera to the equipment surface is different, the angle between the camera's line of sight and the equipment surface is different, and the degree to which the line of sight is blocked by other equipment is also different. These three factors can be regarded as different spatial relationships between the video detection terminal and the equipment due to different shooting positions.

[0089] Furthermore, the impact of sunlight on video detection terminal photography varies under different spatiotemporal conditions; therefore, this invention treats sunlight as an environmental effect. (Vector) d represents the line of sight of the video detection terminal, and d represents the shooting distance.

[0090] Furthermore, the substation video detection terminal model includes,

[0091]

[0092] Where, vector d represents the line of sight of the video detection terminal, and d represents the shooting distance.

[0093] Furthermore, the substation video detection terminal model also includes,

[0094]

[0095] in, Let e ​​represent the normal vector of surface BCGF, and e represent the shooting angle.

[0096] Furthermore, the substation video detection terminal model also includes,

[0097]

[0098] Here, γ represents sunlight, which is one of a set of parallel vectors. This indicates the angle between sunlight and the inspection robot's line of sight. The vector is the line-of-sight vector of the camera and the device.

[0099] Step 106: Based on the substation spatial model and the video surveillance terminal model, and combining the two-stage strategy, obtain the optimal terminal location of the substation video surveillance terminal.

[0100] Furthermore, ensure that the generated point set covers all internal detection targets. In each selection, prioritize matrix S. Pk The point with the largest sum has two characteristics. At this point, the video inspection terminal captures as many device surfaces as possible. The overall quality of the targets captured by the video inspection terminal at this point is the highest; for example, given two points that allow the video inspection terminal to capture the same number of device surfaces, the point with higher capture quality is preferred. The above steps also ensure that the inspection procedure is not repetitive or redundant. Thus, the final point set P is obtained. opt We have obtained matrix S. Pk The middle corresponds to point P k The non-zero element represents the surface of the device to be photographed at that point.

[0101] Furthermore, a candidate point set is selected from the initial available detection locations; a shooting potential distribution matrix is ​​established, and the maximum shooting potential matrix is ​​obtained; a point is selected and its relative shooting potential matrix is ​​solved; it is determined whether the relative face shooting potential meets the threshold requirement; if there are still unselected points in the candidate point set, the elements in the matrix that do not meet the threshold are set to zero; if there are no unselected points in the candidate points, the solution process ends.

[0102] It should be noted that, to ensure detection quality, the drone photographs each surface of the device to be inspected. Based on the calculation results of the first stage, the potential value of any point within the flyable area can be obtained. Since different device surfaces have different sizes and different densities of information elements, the relative magnitude of the potential value, rather than its absolute magnitude, is used to determine whether the drone is suitable for inspecting a particular device surface at a certain point. When the relative photographed potential value is below a threshold, the target surface at that point is considered unsuitable for inspection.

[0103]

[0104]

[0105] Where t (0≤t≤1) represents the threshold percentage, points with shooting potential below the threshold are excluded from the initial screening, P km The device surface F is among the candidate points. ij The point with the maximum shooting potential is argmax, where S is the shooting potential and q represents the relative shooting quality threshold.

[0106] Furthermore, different substation topologies and detection tasks lead to differences in the distribution of spatial imaging potential. The generation of hovering points and imaging points is a multi-optimization objective problem. Therefore, this invention uses the entropy weight method and the ladder technique, which are similar to the performance of the ideal solution, to determine the value of t.

[0107] Furthermore, the inspection work requires intelligent equipment to avoid shooting in low light as much as possible, and the target device should occupy as many pixels as possible in the inspection image. Therefore, this invention uses the average illumination angle when the intelligent equipment shoots the target. The backlight shooting rate η and the relative size E of the target device in the picture are used as evaluation indicators. In addition, considering the battery life of intelligent equipment, the inspection time T of intelligent equipment is also included in the evaluation indicators. The inspection point generation method is evaluated from three aspects.

[0108]

[0109] in, For intelligent equipment to capture the target image, the illumination angle is η, where η is the backlighting rate, and F is the backlighting angle. k The effective pixel value of point K. This represents the effective pixel value of points on the target image captured by the intelligent equipment when the illumination angle is greater than 90°.

[0110] Furthermore, the relative area ratio of the inspection points:

[0111]

[0112] in, This indicates the relative area ratio of the inspection points. This indicates that the intelligent equipment is capturing images of the device surface F at point k. ij At that time, face F ij The area in the camera frame, This indicates that the smart device is positioned at a safe distance from the device surface and directly facing the camera when shooting. ij Area within the camera frame.

[0113] Furthermore, the average relative area ratio of the inspection points is expressed as:

[0114]

[0115] Among them, using This indicates that the intelligent equipment is at point P. k The average relative area ratio of all equipment surfaces inspected is given by the number of inspection points (K).

[0116] For the inspection time T, this invention mainly considers the three aspects of time loss that have the greatest impact on energy consumption: the time for the intelligent equipment to adjust its posture at the inspection point, the time for the intelligent equipment to stop and take pictures, and the time for the intelligent equipment to move between inspection points.

[0117] T = T a +T m +T s

[0118] Where T a =3s,T s =5s, the inspection route is automatically generated by the ant colony algorithm based on the generated inspection point set.

[0119] Example 2

[0120] Reference Figure 3-6 This invention provides a method and system for finding the optimal monitoring point of a video surveillance terminal, as one embodiment of the present invention. To verify the beneficial effects of the present invention, scientific demonstration is carried out through experiments.

[0121] Table 1. Relative size differences of images generated by different methods.

[0122]

[0123] Since other methods do not consider the impact of lighting on shooting, the point sets generated are the same under different lighting conditions. When the sunlight vector is 0 (cloudy), the proposed method generates the point set with the highest average effective pixel ratio, 6.5 times higher than the random method and 10 times higher than the energy-optimal method that does not consider the camera's zoom capability. When the PAS of the critical region is 10 times higher than that of the device surface, the effective pixel ratio of the critical region of the proposed method is 11 times that of the random method and 52.5 times that of the energy-optimal method. In contrast, the energy-optimal method tends to complete all detection tasks on fewer detection points, resulting in most generated points being far from the device group and having a large tilt of the shooting line of sight, while the shooting quality of points generated by the random method is somewhere in between.

[0124] Figure 5 and Figure 6 This means that when the sunlight vector is v sun1 and v sun2 The proposed method adjusted the generated points, and compared with no sunlight conditions, the effective pixel ratio of the device surface decreased by 18.7% and 15.9%, and the effective pixel ratio of the key area decreased by 23.7% and 12.1%, but the illumination angle remained at around 60° (<90°), indicating that the proposed method has good sunlight adaptability. In contrast, under certain lighting conditions, the points generated by the other two methods may cause the drone to shoot against the light, resulting in poor photo quality.

[0125] In some embodiments, it also includes a system for determining the optimal monitoring point of a video surveillance terminal, comprising:

[0126] A substation spatial model generation module generates a substation spatial model based on the equipment location data to be detected in the substation.

[0127] A video surveillance terminal model generation module generates a video surveillance terminal model based on data such as the lighting conditions at the video surveillance terminal, the shading conditions at the video surveillance terminal, the shooting distance at the video surveillance terminal, and the shooting angle at the video surveillance terminal.

[0128] The optimal terminal location calculation module is used to calculate the optimal terminal location for the video surveillance terminal in the substation.

[0129] The optimal terminal location calculation module employs a two-stage strategy for calculation, including:

[0130] In the first stage, the suitability of spatial points as terminal points and shooting points is quantitatively calculated based on the shooting potential model;

[0131] In the second stage, points that meet the quality requirements are selected, and the optimal subset that can complete the detection task is chosen as the final solution.

[0132] The two-stage strategy also includes,

[0133] Select a set of candidate points at the initial available detection locations;

[0134] Determine if there are any points in the initial candidate set whose potential matrix is ​​non-zero;

[0135] The point with the largest sum of the potential matrix elements in the candidate set is added to the inspection point set and removed from the candidate set;

[0136] Record the coordinates of the non-zero elements of the potential matrix of the selected point, and set the elements of these coordinates in the potential matrix of other points in the candidate set to zero;

[0137] Determine whether the inspection point set can meet the minimum face count requirement of certain equipment;

[0138] If the condition is not met, the process continues to determine whether there are points with a non-zero potential matrix.

[0139] If the condition is met, the elements in the rows of the potential matrices of other points in the candidate set containing these devices are set to zero, and then the process of determining whether there are points with non-zero potential matrices continues.

[0140] The lighting conditions at the video surveillance terminal proposed by the video surveillance terminal model generation module include:

[0141]

[0142]

[0143] in, This indicates the factors affecting illumination; different angles of illumination correspond to different influencing factors. It is the illumination angle, w ij Indicates device surface F ij The influence function of illumination, μ1, μ2, These are constants. μ is the illumination influence coefficient, which means that the illumination influence coefficient is a constant within a certain illumination angle range, but the coefficient is different in different ranges.

[0144] The optimal terminal point calculation module provides the following optimal terminal point locations:

[0145]

[0146]

[0147] Where t (0≤t≤1) represents the threshold percentage, points with shooting potential below the threshold are excluded from the initial screening, P km The device surface F is among the candidate points. ij The point with the maximum shooting potential is argmax, where S is the shooting potential and q represents the relative shooting quality threshold.

[0148] The optimal terminal location also includes,

[0149] if S ij ≠0, then S ij ≥Q ij Q ij =f i0 f ij q ij

[0150]

[0151] Among them, C1 ensures that the scheme can meet the quality requirements of the detection task, and C2 ensures that the scheme given by the automatic algorithm can meet the quantity requirements of the detection task, that is, the video surveillance terminal can capture all the equipment and their faces that need to be detected in a single flight mission.

[0152] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

[0153] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of this application can be implemented in various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0154] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0155] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0156] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0157] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0158] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for determining the optimal monitoring point of a video surveillance terminal, characterized in that: include, Select a set of candidate points at the initial available detection locations; Determine whether there are candidate points in the initial candidate point set whose potential matrix is ​​non-zero; The shooting potential matrix of each candidate point is composed of different elements; Add the candidate point with the largest sum of potential matrix elements in the candidate point set to the inspection point set, and remove the corresponding candidate point from the candidate point set. Record the coordinates of the non-zero elements of the potential matrix of the selected candidate points, and set the elements of these coordinates in the potential matrix of other points in the candidate point set to zero; Determine whether the set of inspection points can meet the minimum number of faces required for the target equipment; If the condition is not met, the process continues to determine whether there are candidate points with a non-zero potential matrix. When the condition is met, the elements in the row corresponding to the target device in the imaging potential matrix of other candidate points in the candidate set are set to zero, and then the judgment of whether there are candidate points with non-zero imaging potential matrix continues. Based on the equipment location data in the substation to be detected, a spatial model of the substation is established. A video surveillance terminal model is established based on the lighting conditions, shading conditions, shooting distance, and shooting angle at the video surveillance terminal. Based on the substation spatial model and the video surveillance terminal model, the optimal terminal location of the substation video surveillance terminal is obtained by combining a two-stage strategy. The two-stage strategy includes, The first-stage strategy is to quantify the rationality of spatial points as terminal points and shooting points based on the shooting potential model. The shooting potential model is the total shooting potential. The second-stage strategy involves selecting points that meet the quality requirements and then choosing the optimal subset from these points that can complete the detection task as the final solution. The lighting conditions at the video surveillance terminal include, in, This indicates the factors affecting illumination; different angles of illumination correspond to different influencing factors. It is the illumination angle, w ij Indicates device surface F ij The influence function of illumination, μ1, μ2, These are constants. μ is the illumination influence coefficient, which represents a constant value within a certain illumination angle range, but the coefficient differs in different ranges. m This represents the illumination influence coefficient of the m-th segment. Indicates the illumination angle of the m-th segment; The optimal terminal locations include: in, For intelligent equipment to capture the target image, the illumination angle is η, where η is the backlighting rate, and F is the backlighting angle. k The effective pixel value of point K. This represents the effective pixel value of points on the target image captured by the intelligent equipment when the illumination angle is greater than 90°.

2. The method for finding the optimal monitoring point of a video surveillance terminal as described in claim 1, characterized in that: The optimal terminal location also includes, The relative area ratio of inspection points: in, This indicates the relative area ratio of the inspection points. This indicates that the intelligent equipment is capturing images of the device surface F at point k. ij At that time, face F ij The area in the camera frame, This indicates that the smart device is positioned at a safe distance from the device surface and directly facing the camera when shooting. ij In the camera's view, the intelligent equipment refers to the equipment used for inspection, and the equipment surface refers to the surface of the equipment being inspected.

3. The method for finding the optimal monitoring point of a video surveillance terminal as described in claim 2, characterized in that: The optimal terminal location also includes, The average relative area ratio of the inspection points is expressed as: Among them, using This indicates that the intelligent equipment is at point P. k The average relative area ratio of all equipment surfaces inspected is given by K inspection points, which are the points where the inspection points are concentrated.

4. The method for finding the optimal monitoring point of a video surveillance terminal as described in claim 3, characterized in that: The optimal terminal location also includes, if S ij ≠0,then S ij ≥Q ij Q ij =f i0 f ij q ij Among them, S ij Q represents the shooting potential of the j-th device surface from the i-th monitoring point; ij f represents the minimum image quality requirement for the j-th device surface at the i-th monitoring point; io f represents the initial shooting capability factor for the i-th monitoring point; ij q represents the relative shooting capability factor of the i-th monitoring point to the j-th device surface; ij This represents the image quality coefficient of the j-th device surface viewed from the i-th monitoring point; m i This represents the number of times the i-th monitoring point is selected as the final monitoring point; m ki This indicates whether the k-th device surface is covered by the ith monitoring point; N represents the total number of candidate monitoring points; K represents the total number of device surfaces that need to be monitored. C2 ensures that the solution provided by the automatic algorithm can meet the quantity requirements of the detection task, that is, the video surveillance terminal can capture all the devices and their faces that need to be detected in a single flight mission.

5. A system for determining the optimal monitoring point of a video surveillance terminal using the method described in claim 1, characterized in that: include, A substation spatial model generation module generates a substation spatial model based on the equipment location data to be detected in the substation. A video surveillance terminal model generation module generates a video surveillance terminal model based on data such as the lighting conditions at the video surveillance terminal, the shading conditions at the video surveillance terminal, the shooting distance at the video surveillance terminal, and the shooting angle at the video surveillance terminal. The optimal terminal location calculation module is used to calculate the optimal terminal location of the substation video monitoring terminal. Based on the equipment location data in the substation to be detected, a spatial model of the substation is established. A video surveillance terminal model is established based on the lighting conditions, shading conditions, shooting distance, and shooting angle at the video surveillance terminal. Based on the substation spatial model and the video surveillance terminal model, the optimal terminal location of the substation video surveillance terminal is obtained by combining a two-stage strategy.

6. The optimal monitoring point solution system for a video surveillance terminal as described in claim 5, characterized in that: The two-stage strategy includes, Among them, u' PS Let p represent the projective potential of surface S through point P. s The pheromone concentration represents the pheromone concentration at the device surface, which is a function related to the spatial coordinates (x′, y′, z′). It describes the pheromone concentration at different locations on the surface S. The pheromone concentration is understood as the importance of that location for inspection photography, reflecting the difference in importance of different areas to the inspection task. θ represents the shooting angle, σs represents the surface element, and x... P ,y P ,z P Let x and x represent the coordinates of point P in three-dimensional space, respectively. P′ ,y P′ ,z P′ These represent the coordinates of point P after it is mapped onto surface S.

Images