Adjusting method of video monitoring area and camera assembly

Abstract

The invention discloses an adjusting method of a video monitoring area and a camera assembly. In the invention, the method for adjusting the video monitoring area comprises the following steps: acquiring a coordinate position of each camera; obtaining the current orientation of each camera, and obtaining the coverage area of the camera based on the current orientation of the camera; combining the coverage areas of the cameras to form an area union set; the area union set is subtracted from the area needing to be monitored, and the blind area is obtained; and adjusting the orientation of the cameras, repeating the steps to obtain a smaller blind area, stopping adjusting the orientation of each camera when the blind area is smaller than a preset threshold value or the number of times of repeating is used up, and enabling the orientation of each camera to be the orientation when the blind area is minimum. After the method is adopted, the orientation of the camera can be automatically adjusted, so that blind area residues are reduced, and the overall effectiveness of a monitoring system is improved.

Description

Technical Field

[0001] The present invention relates to the field of smart home, and particularly to a method for adjusting a video surveillance area and a camera assembly. Background Art

[0002] With the rapid development of intelligent security technology, video surveillance systems have become an important part of the security guarantee for modern families and public places.

[0003] Currently, in order to monitor the situation of a house as much as possible, users often install multiple cameras. When users install multiple cameras by themselves, they usually rely on manual experience to adjust the orientations of each camera one by one, and visually judge whether the coverage areas overlap or there are blind spots. For ordinary household users, the lack of professional security knowledge makes it difficult for them to achieve the optimal coverage of multiple cameras through manual debugging, and ultimately may reduce the overall effectiveness of the surveillance system due to the remaining blind spots. Summary of the Invention

[0004] The purpose of the present invention is to provide a method for adjusting a video surveillance area and a camera assembly, which can automatically adjust the camera to reduce blind spots.

[0005] To solve the above technical problems, an embodiment of the present invention provides a method for adjusting a video surveillance area, including:

[0006] Obtaining the coordinate positions of each camera;

[0007] Obtaining the current orientation of each of the cameras, and obtaining the coverage area of the camera based on the current orientation of the camera;

[0008] Merging the coverage areas of the cameras to form a union of areas;

[0009] Subtracting the union of areas from the area to be monitored to obtain the blind spot area;

[0010] Adjusting the orientation of the camera, repeating the above steps to obtain a smaller blind spot area, and terminating the adjustment of the orientation of each camera when the blind spot area is less than a preset threshold or the number of repetitions is exhausted, and the orientation of each camera is at the orientation when the blind spot area is the smallest.

[0011] In the embodiments of the present invention, compared with the prior art, after each camera is installed, the coordinate positions of each camera can be obtained, and at the same time, according to the coordinate positions of each camera and the current orientation, the coverage area of the camera can be obtained. After subtracting the coverage area from the area to be monitored, the blind area area can be formed. Adjust the orientation of each camera, repeat the above steps to calculate the blind area area. When the blind area area is less than a certain preset threshold, or after the number of repeated iterations is exhausted, the orientation of each camera when the blind area area is the smallest will be selected as the current orientation of each camera.

[0012] Therefore, after adopting the above method, the orientation of the camera can be automatically adjusted, thereby reducing the residual blind area and improving the overall effectiveness of the monitoring system.

[0013] In one embodiment, after one or more of the cameras rotate a preset angle, a new blind area area is obtained;

[0014] Among them, when the new blind area area is less than the previous blind area area, the orientation of each camera corresponding to the new blind area area is retained; when the new blind area area is greater than the previous blind area area, the orientation of each camera corresponding to the new blind area area is abolished.

[0015] In one embodiment, after one or more of the cameras rotate a preset angle, a new blind area area is obtained;

[0016] When the number of repetitions is exhausted, when the blind area area is the smallest, the orientation of each camera is selected as the current orientation of each camera.

[0017] In one embodiment, when one camera rotates, if the blind area area expands, one or more other cameras are synchronously rotated to reduce the blind area area.

[0018] In one embodiment, the UWB module is used to measure the relative distance between each pair of cameras to obtain the coordinates of each camera.

[0019] In one embodiment, after obtaining the distance between each pair of cameras, the relative positions of each camera are obtained by trilateration.

[0020] In one embodiment, the gradient descent or genetic algorithm is used to adjust the orientation of each camera to obtain a smaller blind area.

[0021] The embodiments of the present application also provide a camera assembly, including:

[0022] A plurality of cameras, each camera is arranged in the area to be monitored;

[0023] An acquisition module that acquires the current orientation of each of the cameras.

[0024] A processing module that, based on the current orientation of the cameras, acquires the coverage area of the cameras, merges the coverage areas of the cameras to form a union of areas, subtracts the union of areas from the area to be monitored to obtain the blind area area; adjusts the orientation of the cameras, and acquires the blind area area again. When the blind area area is less than a preset threshold or the number of repetitions is exhausted, the adjustment of the orientation of each camera is terminated, and the orientation of each camera is at the orientation when the blind area area is the smallest.

[0025] In one embodiment, the area to be monitored is the area around the house, and a plurality of the cameras are dispersedly arranged around the house.

[0026] In one embodiment, the camera is a rotating camera.

[0027] In one embodiment, the camera has a UWB module, and the UWB module is used to measure the relative distance between each pair of the cameras. Description of the Drawings

[0028] One or more embodiments are exemplarily illustrated by the pictures in the corresponding drawings. These exemplary illustrations do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings are represented as similar elements. Unless otherwise stated, the drawings in the figures do not constitute a scale limitation.

[0029] Figure 1 is a flowchart of the method for adjusting the video monitoring area in the embodiments of the present application;

[0030] Figure 2 is a schematic diagram when four cameras are distributed around a building in the embodiments of the present application.

[0031] Description of the reference numerals in the drawings: 1. Camera; 2. Coverage area; 3. Blind area area; 4. Building. Detailed Embodiments

[0032] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will elaborate on the various embodiments of the present invention with reference to the drawings. However, those of ordinary skill in the art can understand that in the various embodiments of the present invention, many technical details are proposed for the better understanding of the present application by the readers. However, even without these technical details and various changes and modifications based on the following embodiments, the technical solutions required to be protected by the present application can still be achieved.

[0033] In the following description, for the purpose of explaining various disclosed embodiments, certain specific details are set forth to provide a thorough understanding of the various disclosed embodiments. However, those skilled in the relevant art will recognize that the embodiments may be practiced without one or more of these specific details. In other instances, well-known devices, structures, and techniques associated with the present application may not be shown or described in detail so as not to unnecessarily obscure the description of the embodiments.

[0034] Unless the context requires otherwise, throughout the specification and claims, the word "comprising" and its variations such as "comprises" and "having" shall be understood in an open, inclusive sense, i.e., to be interpreted as "including, but not limited to".

[0035] The following will describe the embodiments of the present invention in detail with reference to the accompanying drawings so as to more clearly understand the purpose, features, and advantages of the present invention. It should be understood that the embodiments shown in the drawings are not limitations on the scope of the present invention, but are only for illustrating the essential spirit of the technical solution of the present invention.

[0036] References to "one embodiment" or "an embodiment" in the course of the specification mean that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment. Thus, the appearances of "in one embodiment" or "in an embodiment" in various places throughout the specification are not necessarily all referring to the same embodiment. Additionally, the particular features, structures, or characteristics may be combined in any manner in one or more embodiments.

[0037] As used in this specification and the appended claims, the singular forms "a" and "the" include plural referents unless the context clearly dictates otherwise. It should be noted that the term "or" is generally used in its inclusive sense of "and / or" unless the context clearly dictates otherwise.

[0038] In the following description, in order to clearly show the structure and working mode of the present invention, many directional terms will be used for description. However, words such as "front", "rear", "left", "right", "outer", "inner", "outward", "inward", "up", "down", etc. should be understood as convenient terms and should not be construed as limiting terms.

[0039] The Vatti algorithm is a geometric algorithm for vector polygon clipping, proposed by Bala R. Vatti in 1992, mainly used for calculating Boolean operations such as intersection, union, and difference of arbitrary polygons (including convex, non-convex, polygon with holes or self-intersecting polygons). Its core idea is based on the scan-line technique, and by processing the geometric relationships of polygon boundary vertices and intersection points, it efficiently generates clipping results. Shapely is an open-source library based on Python, focusing on the operation and analysis of planar geometric objects, widely used in fields such as Geographic Information System (GIS), spatial data analysis, computational geometry, etc. Its core functions are realized through the GEOS (Geometry Engine–Open Source) library to achieve efficient geometric calculations, supporting the creation, operation, and spatial relationship analysis of basic geometric types such as points, lines, and polygons

[0040] Embodiments of the present invention will be described below with reference to the accompanying drawings

[0041] Embodiments of the present invention provide a method for adjusting a video surveillance area, specifically including: obtaining the coordinate positions of each camera 1; obtaining the current orientation of each camera 1, and obtaining the coverage area 2 of each camera 1 based on the current orientation of the camera 1

[0042] After obtaining the coverage areas 2 of each camera 1, merge the coverage areas 2 of each camera 1 to form a regional union. Subtracting the regional union from the area to be monitored can obtain the blind area area 3

[0043] In order to obtain a smaller blind area area 3, adjust the orientation of the camera 1, and repeat the above steps, that is, obtain the current orientation of the camera 1, obtain the coverage area 2 of each camera 1 based on the current orientation of the camera 1. After obtaining the coverage areas 2 of each camera 1, merge the coverage areas 2 of each camera 1 to form a regional union. Subtracting the regional union from the area to be monitored can obtain the new blind area area 3

[0044] When the newly obtained blind area area 3 is less than a preset threshold or the number of repetitions is exhausted, the adjustment can be terminated. At this time, the orientation of each camera 1 is the orientation when the blind area area 3 is the smallest

[0045] In order to calculate the blind area angle and regional size between multiple cameras 1 through trigonometric geometry and adjust the orientation of the camera 1 to minimize the blind area, the following steps can be carried out

[0046] First, determine the position of camera 1. Measure the distance between each pair of cameras 1 using the UWB module (trilateration method), and determine the coordinates through geometric positioning. Calculate the coordinates of camera 1 using the trilateration method. Assume that the positions of three cameras 1A, B, and C are known, and the distances from camera 1D to A, B, and C are dAD, dBD, and dCD respectively. The coordinates (xD, yD) of D can be solved through the following equations:

[0047] Secondly, model the coverage area 2 of camera 1. The coverage area 2 of each camera 1 is a sector. Set the coordinate position as (x i， y i ), the angle of the direction of camera 1 is θ i (with due north as 0°), the viewing angle of camera 1 is φ i (such as 120°), and the effective radius of camera 1 is R i . Starting from the coordinate position (x i , y i ), the coverage angle range is: [θ i - φ i / 2, θ i + φ i / 2], and the area of the region with the above radius R i .

[0048] Calculate the area of the coverage area 2 covered by the above camera 1. Assume there is no occlusion and the coverage area is a complete sector. The area formula is: Among them, Convert the visual angle to radians.

[0049] If the coverage area 2 of camera 1 is blocked by building 4 or obstacles, the actual effective coverage area 2 needs to be calculated. The monitoring area can be defined. For example, input the boundary coordinates of building 4 (such as a rectangle or polygon) into the system, and use a computational geometry library (such as the Vatti algorithm or Shapely) to find the intersection of the sector and the monitoring area polygon. The area of the intersection polygon is the actual coverage area.

[0050] Then, obtain the union of the total coverage areas 2 of each camera 1. First, represent the coverage area 2 of each camera 1 as a sector, and use a computational geometry algorithm (such as the Vatti algorithm or Shapely) to merge all the sectors to obtain the union of the total coverage areas 2. Since the union of the total coverage areas 2 is taken, there is an overlap between the coverage areas 2 of two adjacent cameras 1, and the overlap area can only be calculated once. For example, directly calculate the union area using a geometry library (such as the Vatti algorithm or Shapely). Preferably, before calling the Shapely / Vatti algorithm, the polygon can be checked for legality (such as repairing self-intersection and closing the boundary), and buffer operations (such as buffer(0)) can be used to automatically repair invalid geometries.

[0051] Preset the area of the area to be monitored within the system. Of course, after inputting the boundary coordinates (such as a rectangle or a polygon) of the building 4 into the system, the area of the area to be monitored can be automatically calculated. Subtract the union area of the total coverage area 2 from the area of the area to be monitored to obtain the blind area 3. Preferably, when the monitoring area is completely separated from the coverage area 2, an alarm can be directly given to prompt deployment errors.

[0052] After obtaining the blind area 3, the orientation of the camera 1 can be adjusted. After one or more of the cameras 1 rotate a preset angle, a new blind area 3 is obtained. When the new blind area 3 is smaller than the previous blind area 3, the orientation of each camera 1 corresponding to the new blind area 3 is retained. When the new blind area 3 is larger than the previous blind area 3, the orientation of each camera 1 corresponding to the new blind area 3 is abolished. By using this method, the blind area 3 can be gradually reduced, so that each camera 1 is in a better orientation.

[0053] Alternatively, after one or more of the cameras 1 rotate a preset angle, a new blind area 3 is obtained, for example, repeating the adjustment of the orientation of each camera 1 500 times or 1000 times. When the repetition count is exhausted, the orientation of each camera 1 when the blind area 3 is the smallest is selected as the current orientation of each camera 1.

[0054] During the process of adjusting the orientation of each camera 1 as described above, when one camera 1 rotates, if the blind area 3 expands, synchronously rotate one or more other cameras 1 to reduce the blind area 3. Of course, the adjustment priority of the camera 1 can also be defined. For example, the camera 1 with greater coverage potential is given priority to rotate. As shown in the figure, the priority of the camera 1a can be set to be the highest, and the priority of the camera 1d can be set to be the lowest. Of course, in order to avoid the infinite expansion of the blind area, a maximum blind area 3 threshold can also be preset, and if it exceeds the threshold, it is determined as an infeasible solution.

[0055] In addition, gradient descent or genetic algorithms can also be adopted to adjust the orientation of each camera 1 to obtain a smaller blind area 3. In the problem of adjusting the orientation of the camera 1 to minimize the blind area, they can help gradually adjust the angle parameters (θ1, θ2,..., θ□) to minimize the blind area 3. Gradient Descent calculates the gradient (i.e., the derivative) of the objective function (such as the blind area 3) with respect to the parameter (the angle θ of the camera 1 i ) and gradually adjusts the parameter along the opposite direction of the gradient, gradually approaching the minimum value.

[0056] The genetic algorithm mimics the natural selection mechanism in biological evolution and gradually optimizes the parameter combination through population iteration (selection, crossover, and mutation). Specifically, the genetic algorithm can randomly generate multiple groups of camera 1 angle combinations (such as 100 groups), and each group is called an "individual"; calculate the objective function value (blind area 3) of each individual, and the smaller the blind area, the higher the fitness; screen out excellent individuals according to the fitness (such as retaining the top 20% of the individuals); randomly exchange some parameters of the angle combinations of the excellent individuals to generate new individuals (such as combining the angle θ1 of individual A with θ2 of individual B); randomly adjust the angles of some individuals slightly (such as increasing or decreasing a certain θ i by 5°) to increase diversity; repeat the above steps until a satisfactory solution is found (for example, the blind area 3 is less than the preset threshold) or the maximum number of iterations is reached. Using the genetic algorithm has strong global search ability and can avoid falling into local optima.

[0057] The embodiment of the present application also provides a camera 1 component, which includes: multiple cameras 1, an acquisition module, and a processing module. Each camera 1 is arranged in the area to be monitored. For example, as shown in the figure, there are four cameras 1 in the present application, and the four cameras 1 are dispersedly arranged around the building 4. It should be noted that the number of cameras 1 can be 2 - 6, such as 3 or 5.

[0058] The acquisition module acquires the current orientation of each camera 1, and the processing module obtains the coverage area 2 of the camera 1 based on the current orientation of each camera 1. The processing module stores the area to be monitored. For example, in this embodiment, the area to be monitored is the area around the building 4, and each camera 1 is dispersedly arranged around the house. The processing module obtains the coverage area 2 of the camera 1 based on the current orientation of the camera 1, combines the coverage areas 2 of each camera 1 to form a regional union, and subtracts the regional union from the area to be monitored to obtain the blind area 3.

[0059] The processing module controls and adjusts the orientation of one or more of each camera 1, and obtains the blind area 3 again. When the blind area 3 is less than the preset threshold or the number of repetitions is exhausted, the adjustment of the orientation of each camera 1 is terminated. Finally, the orientation where each camera 1 is located is the orientation when the blind area 3 is the smallest.

[0060] In order to obtain the current positions of each camera 1, each camera 1 is also respectively equipped with a UWB module, and each UWB module is used to measure the relative distance between each pair of cameras 1. The UWB module (Ultra-Wideband Module) is a wireless communication and positioning hardware component based on ultra-wideband technology (Ultra-Wideband), and usually exists in the form of a chip or an integrated module. It transmits extremely short pulses (nanosecond level) and signals in an extremely wide frequency band (usually exceeding 500 MHz) to achieve high-precision ranging, positioning, and data communication functions.

[0061] Preferably, each camera 1 can be a rotating camera 1, so that each camera 1 can select more facing orientations. The preferred embodiments of the present invention have been described in detail above, but it should be understood that if necessary, aspects of the embodiments can be modified to adopt aspects, features, and concepts of various patents, applications, and publications to provide additional embodiments.

[0062] Considering the above detailed description, these and other changes can be made to the embodiments. Generally speaking, in the claims, the terms used should not be considered as limited to the specific embodiments disclosed in the specification and the claims, but should be understood to include all possible embodiments together with the full equivalent scope enjoyed by these claims.

[0063] Those skilled in the art can understand that all or part of the steps in the methods of the above embodiments can be completed by instructing relevant hardware through a program. This program is stored in a storage medium, including several instructions to enable a device (which can be a single-chip microcomputer, a chip, etc.) or a processor (processor) to execute all or part of the steps of the methods described in various embodiments of the present application. The aforementioned storage medium includes: various media that can store program codes such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs.

[0064] Those of ordinary skill in the art can understand that the above embodiments are specific embodiments for implementing the present invention, and in practical applications, various changes can be made in form and details without departing from the spirit and scope of the present invention.

Claims

1. A method for adjusting a video surveillance area, characterized in that, Including: Obtain the coordinate positions of each camera; Obtain the current orientation of each of the cameras, and based on the current orientation of the camera, obtain the coverage area of the camera; Merge the coverage areas of the cameras to form a union of areas; Subtract the union of areas from the area to be monitored to obtain the blind area; Adjust the orientation of the cameras, and repeat the above steps to obtain a smaller blind area. When the blind area is less than a preset threshold or the number of repetitions is exhausted, terminate the adjustment of the orientation of each camera, and the orientation of each camera is the orientation when the blind area is the smallest.

2. The adjustment method of the video monitoring area according to claim 1, characterized in that, After one or more of the cameras rotate a preset angle, obtain a new blind area; Among them, when the new blind area is less than the previous blind area, retain the orientation of each camera corresponding to the new blind area; when the new blind area is greater than the previous blind area, abolish the orientation of each camera corresponding to the new blind area.

3. The method for adjusting a video surveillance area according to claim 1, wherein After one or more of the cameras rotate a preset angle, obtain a new blind area; After the number of repetitions is exhausted, select the orientation of each camera when the blind area is the smallest as the current orientation of each camera.

4. The method for adjusting a video surveillance area according to claim 2 or 3, characterized in that, When one of the cameras rotates, if the blind area expands, synchronously rotate one or more other cameras to reduce the blind area.

5. The method for adjusting a video surveillance area according to claim 1, wherein Use the UWB module to measure the relative distance between each pair of cameras to obtain the coordinates of each camera.

6. The method for adjusting a video surveillance area according to claim 5, wherein After obtaining the distance between each pair of cameras, use trilateration to obtain the relative positions of each camera.

7. The method for adjusting a video surveillance area according to claim 1, wherein Adopt gradient descent or genetic algorithm to adjust the orientation of each camera to obtain a smaller blind area.

8. A camera module, characterized in that, Including: A plurality of cameras, each of the cameras is arranged in the area to be monitored; An acquisition module that acquires the current orientation of each of the cameras; A processing module that, based on the current orientation of the camera, obtains the coverage area of the camera, merges the coverage areas of the cameras to form a union of areas, subtracts the union of areas from the area to be monitored to obtain the blind area; Adjust the orientation of the cameras, and obtain the blind area again. When the blind area is less than a preset threshold or the number of repetitions is exhausted, terminate the adjustment of the orientation of each camera, and the orientation of each camera is the orientation when the blind area is the smallest.

9. The camera assembly according to claim 8, wherein, The area to be monitored is the area around the house, and a plurality of the cameras are dispersedly arranged around the house.

10. The camera module according to claim 8, wherein The camera is a rotating camera.

11. The camera component according to claim 8, wherein The camera has a UWB module, and the UWB module is used to measure the relative distance between each pair of the cameras.

Images