Surveillance system and method

Abstract

To provide a monitoring system with which it is possible to automatically correct a camera's angle deviation and thereby shorten the time for preset reregistration.SOLUTION: Provided is a monitoring system (100) that includes a camera unit (101), a monitoring unit (102), and a position correction unit (104-1). The monitoring unit includes a database (305) for storing first preset information that defines the bearing and field angle of the camera unit. The position correction unit includes a deviation amount recognition unit (406) for determining, with respect to the first preset information, a field angle deviation amount that indicates, as the number of pixels, how much the field angle of the camera unit is shifted from a prescribed reference, a correction unit (407-1) for moving the camera unit to a correction position to resolve the field angle deviation, using a movement angle calculated from the determined field angle deviation, and a preset reregistration unit (410) for updating the first preset information on the basis of the correction position and registering it as second prescribed information.SELECTED DRAWING: Figure 4

Description

[Technical field]

[0001] The present disclosure relates to a monitoring system and a monitoring method. [Background technology]

[0002] Conventionally, as part of crime prevention measures, surveillance systems using surveillance cameras capable of capturing images of suspicious objects and people have been provided in various locations such as stores, roads, parking lots, etc. Among these systems, a means for controlling the direction and angle of view of the surveillance camera using preset information that has been set in advance is known.

[0003] An example of a surveillance camera using preset information is disclosed in Japanese Patent No. 6016295 (Patent Document 1). Patent Document 1 discloses a monitoring system including: a plurality of cameras capturing images within a monitoring area; an image processing device that processes image signals input from the plurality of cameras to detect an intruding object that has invaded the monitoring area; and a control unit that instructs the plurality of cameras to change their orientations and angles of view based on preset information registered in advance from the coordinate position of the intruding object detected by the image processing device; the image processing device that detects an intruding object from image signals captured by each camera and calculates the coordinate position and detection frame area information of the intruding object is connected to each of the plurality of cameras; each image processing device is provided with a plurality of encoders that add the coordinate position and the detection frame area information of the intruding object to a header portion of image data from the image processing device and transmit the image data to the control unit; the control unit predicts the movement of the intruding object based on the coordinate position of the intruding object input from the encoder, and ranks the importance of images transmitted from the plurality of cameras based on the detection frame area information of the intruding object input from the encoder, and causes a monitoring monitor to display the images in accordance with the ranking. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 6016295 Summary of the Invention [Problem to be solved by the invention]

[0005] Patent Document 1 describes a surveillance system that predicts the next action of an intruder based on the size of the detection frame when the intruder is detected by an image processing device, the intruder's trajectory information detected by a laser sensor, etc., and provides important images to a surveillance person in real time by ranking the importance from multiple camera images. Also, in the means described in Patent Document 1, changes in the direction and angle of view of the surveillance camera are controlled based on preset information registered in advance so that this "important image" can be captured.

[0006] However, the angle of view of a surveillance camera may deviate from the angle of view specified by the preset information due to deterioration of the motor over time, etc. This deviation in the angle of view can make it impossible to capture the subject, limiting the accuracy of detecting intruders and suspicious objects, so when the deviation in the angle of view occurs, measures must be taken to correct it.

[0007] Conventionally, when the deviation in the angle of view of a surveillance camera exceeds the allowable range, it is necessary to re-register the preset information of the surveillance camera. When re-registering the presets, the worker must manually update and register all the presets to the appropriate angles, which is time-consuming and may lead to mistakes in preset registration due to user error. In view of the above problem, there is a need for a means for reducing the burden of re-registering presets due to deviations in the angle of view of a surveillance camera.

[0008] Therefore, an object of the present disclosure is to provide a surveillance system that can shorten the time required for preset re-registration by automatically correcting the deviation in the angle of view of the camera. [Means for solving the problem]

[0009] In order to solve the above-mentioned problems, one representative monitoring system of the present invention is a monitoring system including a camera unit, a monitoring unit, and a position correction unit, the monitoring unit including a database storing first preset information defining an orientation and an angle of view of the camera unit, the position correction unit including a deviation amount recognition unit that determines, for the first preset information, an angle of view deviation amount that indicates, as a number of pixels, how much the angle of view of the camera unit deviates from a predetermined reference, a correction unit that moves the camera unit to a correction position that eliminates the angle of view deviation amount by using a movement angle calculated from the determined angle of view deviation amount, and a preset re-registration unit that updates the first preset information based on the correction position and registers the first preset information as second preset information. the deviation amount recognition unit acquires an input image acquired by the camera unit and a reference image captured in a correct direction and angle of view of the camera unit, compares the input image with the reference image, and determines whether or not a predetermined reference pattern in the reference image is recognizable in the input image. If it is determined that the reference pattern is recognizable in the input image, the unit determines the number of pixels of the input image that are deviated from the reference image as the amount of deviation of angle of view based on the input image and the reference image. If it is determined that the reference pattern is not recognizable in the input image, the unit determines whether the input image is normal or abnormal from a video state of the input image. If the input image is normal, the amount of deviation of angle of view is set to 0 and the reference pattern is re-registered. If the input image is abnormal, the unit sets the amount of deviation of angle of view to 0 and does not perform processing by the correction unit. . Effect of the Invention

[0010] According to the present disclosure, it is possible to provide a surveillance system that can shorten the time required for preset re-registration by automatically correcting deviation in the angle of view of a camera. Other objects, configurations and effects will become apparent from the following description of the preferred embodiment of the invention. [Brief description of the drawings]

[0011] [Figure 1] FIG. 1 is a diagram illustrating an example of a configuration of a monitoring system according to a first embodiment of the present disclosure. [Diagram 2] FIG. 2 is a diagram illustrating an example of a configuration of a monitoring system according to a second embodiment of the present disclosure. [Diagram 3] FIG. 3 is a diagram illustrating an example of an internal configuration of a monitoring unit according to an embodiment of the present disclosure. [Figure 4] FIG. 4 is a diagram illustrating an example of an internal configuration of a correction unit according to the first embodiment of the present disclosure. [Diagram 5] FIG. 5 is a diagram illustrating an example of an internal configuration of a correction unit according to the second embodiment of the present disclosure. [Figure 6] FIG. 6 is a diagram illustrating an example of a configuration of a preset information table according to an embodiment of the present disclosure. [Figure 7]FIG. 7 is a flowchart of a misalignment amount recognition process performed by the misalignment amount recognition unit according to an embodiment of the present disclosure. [Figure 8] FIG. 8 is a flowchart of a position correction process performed by the position corrector according to the first embodiment of the present disclosure. [Figure 9] FIG. 9 is a flowchart of a position correction process performed by a position corrector according to the second embodiment of the present disclosure. [Figure 10] FIG. 10 is a flowchart of a preset re-registration process (1) performed by a preset re-registration unit according to an embodiment of the present disclosure. [Figure 11] FIG. 11 is a flowchart of a preset re-registration process (2) performed by the preset re-registration unit according to an embodiment of the present disclosure. [Figure 12] FIG. 12 is a flowchart of a preset re-registration process (3) performed by the preset re-registration unit according to an embodiment of the present disclosure. [Figure 13] FIG. 13 is a diagram illustrating an example of an image display during manual alignment according to an embodiment of the present disclosure. [Figure 14] FIG. 14 is a diagram illustrating an example of an operation screen displayed on a user interface of a display unit according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. Note that the present invention is not limited to the embodiment. In addition, in the description of the drawings, the same parts are denoted by the same reference numerals. In the following, aspects of the present disclosure may be described by specifying an example such as Example 1 or Example 2, or may be described without specifying an example. An aspect of the present disclosure described by specifying an example is not limited to that example and may be applied to other examples. Also, an aspect of the present disclosure described without specifying an example is a common element that can be applied to any example such as Example 1 or Example 2.

[0013] As described above, an object of the present disclosure is to provide a surveillance system that can shorten the time required for preset re-registration by automatically correcting deviation in the angle of view of a camera. More specifically, in the present disclosure, when the preset re-registration is performed, if all the presets included in the preset information are not outside the allowable range, the information of the presets that can be corrected is automatically collected and the amount of deviation in the angle of view is calculated. If all the presets are outside the allowable range or if the user wants to manually re-register the presets, one preset is manually set and the amount of deviation in the angle of view that occurred in that preset is calculated.

[0014] The correction position of the camera unit is determined based on this calculated amount of angle of view deviation, the camera unit is moved to that correction position, and that correction position is registered as a new preset, thereby eliminating the angle of view deviation and automatically re-registering the preset. In addition to displaying the current camera image, a reference image captured with a correct preset and the current camera image are superimposed on each other to facilitate fine adjustments when re-registering a preset.

[0015] First, with reference to FIG. 1, a configuration of a monitoring system according to a first embodiment of the present disclosure will be described.

[0016] Fig. 1 is a diagram illustrating an example of a configuration of a monitoring system 100 according to the first embodiment of the present disclosure. As illustrated in Fig. 1, the monitoring system 100 according to the first embodiment of the present disclosure includes a camera unit 101, a monitoring unit 102, a display unit 103, and a position correction unit 104-1. It should be noted that the camera unit 101, the monitoring unit 102, the display unit 103, and the position correction unit 104-1 may be software applications executed by a single device (e.g., a computing device), or may be independent dedicated hardware.

[0017] The camera unit 101 is a functional unit installed to capture a predetermined environment. The camera unit 101 is, for example, a camera equipped with a camera platform having adjustment functions such as pan, tilt, and zoom, and may be a rotating camera that can rotate 360 ​​degrees. The installation locations and number of the camera units 101 are not particularly limited in this disclosure, and may be appropriately determined depending on the purpose of surveillance, etc.

[0018] The monitoring unit 102 is a functional unit having functions for recording, managing, and viewing images and videos. The monitoring unit 102 may output images captured by the camera unit 101 to the display unit 103, and may transfer instructions from the display unit 103 (e.g., a preset re-registration operation) to the camera unit 101. As an example, the monitoring unit 102 may be a functional unit equipped with a so-called VMS (Video Management System).

[0019] The display unit 103 is a device that provides a user interface to a user of the monitoring system 100, and manages the display of images captured by the camera unit 101, control of the camera platform, input of instructions to the camera unit 101, etc. The display unit 103 may include, for example, a computer (a notebook computer, a desktop computer) or a mobile terminal (a smartphone, a tablet) connected to the monitoring unit 102.

[0020] The position correction unit 104-1 is a functional unit for adjusting the position of the camera unit 101. As will be described later, the position correction unit 104-1 may include, for example, a deviation amount recognition unit for recognizing deviation in the angle of view of the camera unit 101, a correction unit for correcting the position of the camera unit 101, a camera head control unit for controlling the camera head of the camera unit 101, reference position data that is a reference for determining the position of the camera unit 101, and a preset re-registration unit for re-registering the preset of the camera unit 101. The configuration of position correction unit 104-1 will be described with reference to FIG. 4, and therefore description thereof will be omitted here.

[0021] Next, a configuration of a monitoring system according to a second embodiment of the present disclosure will be described with reference to FIG.

[0022] 2 is a diagram illustrating an example of a configuration of a monitoring system 200 according to a second embodiment of the present disclosure. The monitoring system 200 according to the second embodiment of the present disclosure is different from the monitoring system 100 according to the first embodiment in that the monitoring system 200 includes a position correction unit 104-2 having a video output function for outputting a video for supporting a preset re-registration process, instead of the position correction unit 104-1. The other configurations are the same.

[0023] Position correction unit 104-2 creates an image to be displayed on the user interface of display unit 103, and then outputs the created image to display unit 103. By displaying the image of position correction unit 104-2 on the user interface of display unit 103, the user can view the image after the angle of view deviation has been corrected. It should be noted that the details of the processing by position correction section 104-2 will be described with reference to FIG. 8, and therefore will not be described here.

[0024] According to the above-described monitoring systems 100 and 200, it is possible to automatically correct the angle of view deviation and shorten the time required for re-registering the presets. Note that which of the monitoring systems 100 and 200 is to be used may be freely selected based on, for example, whether or not it is necessary to check the video after the angle of view deviation has been corrected.

[0025] Next, an internal configuration of a monitoring unit according to an embodiment of the present disclosure will be described with reference to FIG.

[0026] 3 is a diagram illustrating an example of an internal configuration of the monitoring unit 102 according to an embodiment of the present disclosure. As illustrated in FIG. 3, the monitoring unit 102 is mainly composed of a program memory 301, a database 305, a data bus 312, a CPU 313, and a LAN I / F 314.

[0027] The program memory 301 is a random access semiconductor memory, storage device, or storage medium (either volatile or non-volatile) for storing data and programs. More specifically, the program memory 301 may store a software program that manages a screen to be displayed on the interface of the display unit 103 described above. For example, as shown in FIG. 3, the program memory 301 may include a screen creation unit 302, a screen display unit 303, and a communication confirmation unit 304.

[0028] When the screen creation unit 302 receives startup information indicating that the display unit 103 has started up, it uses various information stored in the database 305 to create an operation screen 1400 to be displayed on the user interface of the display unit 103. Details of the created operation screen 1400 will be described with reference to Fig. 14, and therefore description thereof will be omitted here.

[0029] The screen display unit 303 outputs the operation screen 1400 created by the screen creation unit 302 to the display unit 103 .

[0030] The communication confirmation unit 304 performs a communication confirmation to verify whether or not data can be transmitted and received with respect to the camera unit 101. If communication is not possible, the communication confirmation unit 304 changes the color of the "error" portion of the user interface screen of the display unit 103 to red, and if communication is possible or the error is resolved, the communication confirmation unit 304 displays the "error" portion of the user interface screen of the display unit 103 in white.

[0031] CPU 313 is one or more general-purpose programmable central processing units configured to execute programs stored in program memory 301 .

[0032] The LAN I / F 314 is a local area network interface for transmitting and receiving data between the monitoring unit 102, the camera unit 101, and the display unit 103.

[0033] Database 305 is a storage unit for storing various information used by monitoring unit 102. For example, as shown in Fig. 3, database 305 may store camera name 306 indicating the name of camera unit 101 connected to monitoring unit 102, video source address 307 indicating the source address (e.g., IP address, etc.) of the video captured by camera unit 101, preset information 308 defining changes in the orientation and angle of view of camera unit 101, model information 309 indicating the models of camera unit 101 and display unit, preset image 310 captured by camera unit 101 set based on preset information 308, and terminal information 311 regarding display unit 103 on which video and an operation screen are displayed.

[0034] The data bus 312 is a bus interface that performs data communication between the program memory 301 , the database 305 , the CPU 313 , and the LAN I / F 314 .

[0035] Next, an internal configuration of the position correction unit according to the first embodiment of the present disclosure will be described with reference to FIG.

[0036] 4 is a diagram illustrating an example of an internal configuration of the position correction unit 104-1 according to the first embodiment of the present disclosure. As described above, the position correction unit 104-1 is a functional unit for adjusting the position of the camera unit 101 so as to correct the view angle shift. As shown in FIG. 4, the position correction unit 104-1 is mainly composed of an image input I / F 401, a processing memory 402, a program memory 415, a CPU 413, and a LAN I / F 414.

[0037] The image input I / F 401 is a communication interface for video data. The image input I / F 401 takes in an image from the camera unit 101 via the LAN I / F 414, and stores the image in an image memory 403 in the processing memory 402.

[0038] The processing memory 402 is a random access semiconductor memory, storage device, or storage medium (either volatile or non-volatile) for storing data and programs. More specifically, the processing memory 402 may store image data captured by the camera unit 101. As shown in FIG. 3, the processing memory 402 may include an image memory 403 , a reference image memory 404 , and a work memory 405 .

[0039] The image memory 403 is an image storage memory that temporarily stores various image data used in the position correction process of the camera unit 101 . The reference image memory 404 is a memory for storing a reference image for determining the angle of view shift of the camera unit 101. This reference image may be set, for example, when setting the position correction unit 104-1. Also, the reference image stored in the reference image memory 404 may be updated when a preset is re-registered. The work memory 405 is a memory for storing data other than images used in the position correction process of the camera unit 101, such as the calculated amount of deviation in the angle of view and the viewing angle.

[0040] The CPU 413 is one or more general-purpose programmable central processing units, and is configured to execute programs stored in the program memory 415 and perform position correction processing.

[0041] The program memory 415 is a random access semiconductor memory, storage device, or storage medium (either volatile or non-volatile) for storing data and programs. More specifically, the program memory 415 may include a displacement amount recognition unit 406, a correction unit 407-1, a camera head control unit 408, reference position data 409, and a preset re-registration unit 410. The deviation amount recognition unit 406 is a functional unit for recognizing the deviation in the angle of view of the camera unit 101 . The correction unit 407-1 is a functional unit for correcting the position of the camera unit 101. The camera head control unit 408 is a functional unit for controlling the camera head of the camera unit 101. The camera head control unit 408 may, for example, interpret the acquisition of focal length and camera head movement instructions executed by the deviation amount recognition unit 406, the correction unit 407-1, and the preset re-registration unit 410, generate a command for moving the camera head, and output the command to the camera unit 101 via the LAN I / F 414. The reference position data 409 is reference position data that serves as a reference for determining the position of the camera unit 101 . The preset re-registration unit 410 is a functional unit for re-registering the presets of the camera unit 101 . The details of the deviation amount recognition unit 406, the correction unit 407-1, the camera head control unit 408, the reference position data 409, and the preset re-registration unit 410 will be described later, and therefore will not be described here.

[0042] The LAN I / F 414 is a local area network interface for transmitting and receiving data between the position correction unit 104-1, the monitoring unit 102, the camera unit 101, and the display unit 103.

[0043] Next, an internal configuration of a position correction unit according to the second embodiment of the present disclosure will be described with reference to FIG.

[0044] 5 is a diagram illustrating an example of an internal configuration of a position correction unit 104-2 according to a second embodiment of the present disclosure. In addition to the configuration of the position correction unit 104-1 according to the first embodiment, the internal configuration of the position correction unit 104-2 according to the second embodiment of the present disclosure includes an output image memory 501 for storing the corrected image in the processing memory 402 in order to output the corrected image in which the view angle shift has been corrected, and an image output I / F 502 for transmitting the corrected image to the display unit 103 via the LAN I / F 414. Moreover, the position correction unit 104-2 according to the second embodiment includes a correction unit 407-2 that further performs processing to output the corrected image instead of the correction unit 407-1. Other than these points, the configuration of the position correction unit 104-2 is the same as that of the position correction unit 104-1 according to the first embodiment, so repeated explanations will be omitted.

[0045] Next, a configuration of a preset information table according to an embodiment of the present disclosure will be described with reference to FIG.

[0046] 6 is a diagram showing an example of a configuration of a preset information table 600 according to an embodiment of the present disclosure. The preset information table 600 shown in Fig. 6 is a table for storing preset information (for example, the preset information 308 shown in Fig. 3) that specifies changes in the direction and angle of view of the camera unit 101.

[0047] As shown in FIG. 6, the preset information table 600 includes, for each preset number 602 as an identifier for identifying a particular preset, pan 604 indicating the pan angle, tilt 606 indicating the tilt angle, zoom 608 indicating the degree of zoom of the camera, focus 610 indicating the degree of focus of the camera, and focal length 612 indicating the focal length of the camera. The camera unit 101 controls pan, tilt, zoom, focus, and focal length in accordance with the preset information defined in the preset information table 600 to capture images. However, as described above, the position and angle of view of the camera unit 101 may deviate from those defined by the preset information due to deterioration of the motor caused by aging, etc. Therefore, according to the present disclosure, the time required for re-registering the preset can be shortened by automatically correcting the deviation in the angle of view. Note that the presets stored in the preset information table 600 are not limited to those shown in FIG. 6, and may actually be set appropriately depending on the model and settings of the camera unit 101, the purpose of shooting, etc.

[0048] Next, a deviation amount recognition process performed by a deviation amount recognition unit according to an embodiment of the present disclosure will be described with reference to FIG.

[0049] Fig. 7 is a flowchart of a shift amount recognition process 700 by the shift amount recognition unit 406 according to an embodiment of the present disclosure. The shift amount recognition process 700 shown in Fig. 7 is a process for determining the amount of shift of the angle of view of the camera unit 101 with respect to preset information (for example, preset information stored in the preset information table 600 shown in Fig. 6, also referred to as "first preset information"). The amount of shift of the angle of view here is information indicating how much the angle of view of the camera unit 101 is shifted with respect to the preset information, and may be expressed, for example, by the number of pixels.

[0050] First, in step 701, the deviation amount recognition unit 406 sets the initial value of the pattern re-registration flag to "0." The pattern here means a specific subject (e.g., a stationary object such as a signboard, building, or sign) in an image used as a reference for determining the amount of deviation in the angle of view of the camera unit 101 in so-called pattern recognition. Setting the initial value of the pattern re-registration flag to "0" indicates that pattern re-registration is not to be performed.

[0051] Next, in step 702, the deviation amount recognition unit 406 monitors the operation state of the camera unit 101 and judges whether or not the camera unit 101 is stopped. Since the judgment of the angle of view deviation amount is executed only when the camera unit 101 is stopped, when the user moves, that is, when a preset movement is performed by operating the operation screen 1400 of the display unit 103, the deviation amount recognition unit 406 judges whether or not the operation state of the camera unit 101 has changed from a moving state to a stopped state. If it is determined in step 702 that the camera unit 101 is stationary, the process proceeds to step 703. On the other hand, if it is determined that the camera unit 101 is moving, the process returns to step 701 and the subsequent steps are repeated.

[0052] Next, in step 703, the deviation amount recognition unit 406 selects either QR code recognition or pattern recognition as a method for determining the amount of deviation in the angle of view. Here, the deviation amount recognition unit 406 may select the method for determining the amount of deviation in the angle of view based on a user's input, or may select a determination method that is preset at the time of setting. By using the QR code recognition or pattern recognition, the deviation in the angle of view from the reference image of the camera unit 101 can be easily determined. If QR code recognition is used, the process proceeds to step 704; if pattern recognition is used, the process proceeds to step 705.

[0053] In step 704, deviation amount recognition unit 406 extracts, as a QR code, an image of the reference position registered in reference position data 409 from the reference images stored in reference image memory 404 of position correction unit 104-1 or position correction unit 104-2. Thereafter, deviation amount recognition unit 406 determines whether or not a QR code corresponding to the extracted QR code can be recognized in the input image captured by camera unit 101.

[0054] In step 705, the deviation amount recognition unit 406 extracts, as a reference pattern, an image of the reference position registered in the reference position data 409 from the reference images stored in the reference image memory 404 of the position correction unit 104-1 or the position correction unit 104-2. Thereafter, the deviation amount recognition unit 406 determines whether or not a reference pattern corresponding to the extracted reference pattern can be recognized in the input image captured by the camera unit 101.

[0055] In step 706, the deviation amount recognition unit 406 determines whether or not the QR code was recognized in step 704, and whether or not the reference pattern was recognized in step 705. If either the QR code or the reference pattern was recognized, the process proceeds to step 707. On the other hand, if neither the QR code nor the reference pattern can be recognized, the process proceeds to step 708 .

[0056] In step 707, the deviation amount recognizing unit 406 uses the recognized QR code or reference pattern to determine the amount of deviation of the angle of view of the input image captured by the camera unit 101 from the reference position indicated by the QR code or reference pattern. Here, the deviation amount recognizing unit 406 may determine the amount of vertical deviation and the amount of horizontal deviation. Thereafter, the deviation amount recognizing unit 406 stores the determined amount of deviation of the angle of view (the amount of vertical deviation and the amount of horizontal deviation) in the work memory 405 of the position correcting unit 104-1 or the position correcting unit 104-2. Thereafter, the process returns to step 701 and repeats the subsequent steps.

[0057] In step 708, the deviation amount recognition unit 406 judges the image state of the input image captured by the camera unit 101. The image state is judged here because, for example, if the input image is dark, if there is fog, or if water droplets are attached to the camera unit 101, the QR code or reference pattern may not be recognized even if it is present in the input image. Therefore, by judging the image state of the input image, it is possible to judge whether the QR code or reference pattern was not recognized due to the state of the input image despite being present in the input image, or whether the QR code or reference pattern was not actually present in the input image.

[0058] The judgment of the image condition here may include judging whether the input image is normal or not by comparing the input image with a reference image based on a predetermined image condition judgment criterion. The image condition judgment criterion here may include, for example, an edge amount, a contrast difference, an image level, etc. of the image. More specifically, the deviation amount recognition unit 406 may compare the reference image acquired from the reference image memory 404 with the input image captured by the camera unit 101, and determine whether the values ​​of the edge amount, contrast difference, and image level of these two images satisfy a predetermined similarity standard. If any of the values ​​of the edge amount, contrast difference, and image level of these two images satisfy the predetermined similarity standard, the input image is determined to be normal. On the other hand, if none of the values ​​of the edge amount, contrast difference, and image level of these two images satisfy the predetermined similarity standard, the input image is determined to be abnormal.

[0059] When water droplets are attached to the camera unit 101, the screen tends to blur and the amount of edges tends to decrease. Therefore, by using the amount of edges as a criterion for judging the image condition, it is possible to judge whether the input image is normal or not. Furthermore, when the image is dark, the image level drops drastically and a lot of noise occurs, so by comparing the edge amount and image level, it is possible to determine whether the input image is normal or not. Furthermore, when there is fog, the contrast difference is extremely reduced, so that by using the contrast difference as a criterion for judging the image condition, it is possible to judge whether the input image is normal or not.

[0060] If the input image is determined to be normal in step 708, the process proceeds to step 709. On the other hand, if the input image is determined to be abnormal in step 708, the process proceeds to step 710.

[0061] In step 709, the deviation amount recognition unit 406 sets the amount of deviation in the angle of view of the camera unit to "0." After that, in step 710, the deviation amount recognition unit 406 sets the pattern re-registration flag to "1." Setting this pattern re-registration flag to "1" indicates that the reference pattern or QR code is to be re-registered. By re-registering the reference pattern or QR code and performing step 704 or step 705 again, it is possible to improve the accuracy of pattern recognition for images that were determined to be normal but in which the reference pattern or QR code could not be recognized. Thereafter, the process returns to step 701 and repeats the subsequent steps.

[0062] In step 710, the deviation amount recognition unit 406 sets the amount of deviation in the angle of view of the camera unit to "0" and outputs the input image to the display unit 103 without performing the position correction process described below. After that, the process returns to step 701 and the subsequent steps are repeated.

[0063] According to the deviation amount recognition process 700 described above, the amount of deviation in the angle of view with respect to the preset information of the angle of view of the camera unit 101 can be determined.

[0064] Next, a position correction process performed by the correction unit according to the first embodiment of the present disclosure will be described with reference to FIG.

[0065] Fig. 8 is a flowchart of a position correction process 800 by the correction unit 407-1 according to the first embodiment of the present disclosure. The position correction process 800 shown in Fig. 8 is a process for correcting the position of the camera unit 101 and eliminating the deviation in the angle of view based on the deviation amount of the angle of view of the camera unit 101 with respect to the preset information of the angle of view determined by the deviation amount recognition process 700 described above.

[0066] First, in step 801, the correction unit 407-1 acquires focal length information and the size of the image sensor of the camera unit 101. Here, the correction unit 407-1 may acquire the focal length information of the camera unit 101 from, for example, the preset information table 600 described with reference to FIG.

[0067] Next, in step 802, correction unit 407-1 calculates the viewing angle of camera unit 101 from the focal length and image sensor size of camera unit 101 acquired in step 801. The viewing angle here is the range of the scene captured in the video captured by camera unit 101 expressed in degrees, and may include a horizontal viewing angle and a vertical viewing angle. The correction unit 407-1 may calculate the horizontal viewing angle and the vertical viewing angle of the camera unit 101 using, for example, the following formulas. [Number 1] Horizontal field of view = 2 x atan(horizontal image sensor size / (2 x focal length)) [Number 2] Vertical field of view = 2 x atan(vertical image sensor size / (2 x focal length))

[0068] Next, in step 803, correction unit 407-1 calculates the movement angle of camera unit 101 from the amount of view angle deviation stored in work memory 405 in step 707 of deviation amount recognition process 700 described above and the viewing angle calculated in step 802. The movement angle here is the deviation of the view angle of camera unit 101 from preset information (for example, preset information stored in preset information table 600 shown in FIG. 6) expressed as an angle. In other words, the movement angle is information indicating how many degrees the view angle of camera unit 101 deviates from the angle specified in the preset information. This movement angle may also include a horizontal movement angle and a vertical movement angle. The correction unit 407-1 may calculate the horizontal movement angle and the vertical movement angle of the camera unit 101 using, for example, the following formulas. [Number 3] Horizontal movement angle = horizontal viewing angle / horizontal image size (640 for VGA) x horizontal shift amount [Number 4] Vertical movement angle = vertical viewing angle / vertical image size (480 for VGA) x vertical shift amount

[0069] Next, in step 804, it is determined whether the movement angle calculated in step 803 is equal to or greater than a predetermined specified value (movement angle threshold) that has been specified in advance. This is because the pan head that controls the movement of the camera unit 101 has a stopping error, so there is no need to move the pan head for a small movement angle. If at least one of the horizontal movement angle and the vertical movement angle calculated in step 803 is equal to or greater than the specified value, the process proceeds to step 805, and if both the horizontal movement angle and the vertical movement angle calculated in step 803 are less than the specified value, the pan head is not moved and the process returns to step 801, and the subsequent processes are repeated.

[0070] In step 805, the correction unit 407-1 uses the camera head control unit 408 to move the camera unit 101 from the position specified in the preset information according to the horizontal movement angle and vertical movement angle calculated in step 803. This makes it possible to correct the camera's angle of view deviation. In this specification, the position where the camera's angle of view deviation has been corrected is referred to as the "corrected position." For example, assume that the "pan" angle of a certain preset is set as "30 degrees" in the preset information. However, as a result of performing the deviation amount recognition process described with reference to FIG. 7, a deviation occurs in the origin of the camera due to loosening of the screws for installing the camera unit 101, and the camera stops at "20 degrees", resulting in a deviation of 10 degrees for the preset. In this case, the correction position of the camera unit 101 is set to "40 degrees", which is the sum of the deviation amount "10 degrees" and the "30 degrees" specified in the preset. As a result, when the camera unit 101 is moved to the correction position of "40 degrees" according to the preset, a deviation of 10 degrees occurs, and the camera unit 101 is placed at the position of "30 degrees" originally specified in the preset, so that the deviation in the angle of view can be eliminated. Moreover, by correcting the deviation in the angle of view of the camera, it is possible to provide the display unit 103 with an image in which the deviation in the angle of view has been corrected.

[0071] Next, a position correction process performed by a correction unit according to the second embodiment of the present disclosure will be described with reference to FIG.

[0072] Fig. 9 is a flowchart of a position correction process 900 by the correction unit 407-2 according to the second embodiment of the present disclosure. The position correction process 900 shown in Fig. 9 is a process for outputting a corrected image in which the view angle shift of the camera is corrected, and is performed following the position correction process 800 shown in Fig. 8. For example, the position correction process 900 may be performed after the end of step 805 of the position correction process 800.

[0073] First, in step 901, the correction unit 407-2 creates and initializes the output video memory 501 in the image memory 403 of the position correction unit 104-2. For example, the correction unit 407-2 may set the initial value to 0 and display a black screen.

[0074] Next, in step 902, correction unit 407-2 acquires from work memory 405 the horizontal and vertical field of view displacement amounts stored in work memory 405 in step 707 of the above-mentioned displacement amount recognition process 700, and creates a corrected image by copying the input image stored in image memory 403 to a position moved by the horizontal and vertical displacement amounts. Then, correction unit 407-2 saves the created corrected image in output image memory 501.

[0075] Next, in step 903, correction unit 407-2 acquires the corrected image created in step 902 from output image memory 501, and outputs it to display unit 103. This makes it possible to output a corrected image in which the angle of view deviation has been corrected, and the user can view a camera image without the angle of view deviation. The above-mentioned position correction process 900 is executed continuously, but while the camera unit 101 is stopped, a corrected image moved by the amount of deviation is output to the display unit 103, and when the camera unit 101 moves, the camera image is output directly to the display unit 103.

[0076] Next, a preset re-registration process (1) performed by the preset re-registration unit according to the embodiment of the present disclosure will be described with reference to FIG.

[0077] 10 is a flowchart of preset re-registration process (1) 1000 by the preset re-registration unit 410 according to an embodiment of the present disclosure. The preset re-registration process (1) 1000 is a first part of a process for re-registering the presets of the camera unit 101, and is a process for determining the amount of deviation of the angle of view for each preset included in the preset information.

[0078] First, in step 1001, the preset re-registration unit 410 displays a confirmation box asking "Do you want to register a preset?" on the screen of the user interface of the display unit 103. If "NO" is selected, the process proceeds to step 1002, and if "YES" is selected, the process proceeds to step 1003.

[0079] In step 1002, the time when "No" was pressed in step 1001 is recorded, and after a certain time has elapsed, a process for re-notifying the user to register the preset is started, and the preset re-registration unit 410 is registered. In the process for re-notifying the user to register the preset, the process returns to step 1001 in the preset re-registration unit 410 after a certain time has elapsed.

[0080] In step 1003, the preset re-registration unit 410 displays a confirmation box asking "Register preset automatically? Register preset manually?" on the screen of the user interface of the display unit 103. If "Register preset automatically" is selected, the process proceeds to step 1006, where a process of calculating the amount of deviation of the angle of view is performed for all preset numbers included in the preset information. On the other hand, if "Register preset manually" is selected, the process proceeds to step 1004, where the user performs manual alignment processing.

[0081] In step 1004, the preset re-registration unit 410 determines the current position of the camera unit 101, and stores the determined current position of the camera unit 101 in the work memory 405, and then displays a notification on the operation screen 1400 of the user interface of the display unit 103 to prompt the user to perform manual alignment processing. Thereafter, the user uses the operation screen 1400 of the display unit 103 to move the camera unit 101 to a correction position where the angle of view deviation has been eliminated. Thereafter, the user presses a preset registration button on the operation screen 1400 of the display unit 103 to end the manual alignment processing.

[0082] Next, in step 1005, after the manual alignment process by the user is completed, the preset re-registration unit 410 determines current position information (i.e., the corrected position to which the camera unit 101 has been moved by the user's operation) from the camera unit 101. Thereafter, the preset re-registration unit 410 calculates the difference between the position information before the manual alignment process stored in the work memory 405 in step 1004 and the position information after the manual alignment process (i.e., the corrected position information) to calculate the movement angle of the camera unit 101 and store it in the work memory 405.

[0083] In step 1006, the preset re-registration unit 410 determines whether the amount of deviation in the angle of view has been calculated for all preset numbers included in the preset information. If the amount of deviation in the angle of view has been calculated for all preset numbers included in the preset information, the process proceeds to preset re-registration process (2) 1100 shown in Fig. 11. If the amount of deviation in the angle of view has not been calculated for all preset numbers included in the preset information, the preset re-registration unit 410 executes steps 1007 to 1010 until the amount of deviation in the angle of view has been calculated for all preset numbers included in the preset information.

[0084] In step 1007, the preset re-registration unit 410 uses the camera head control unit 408 to move the camera unit 101 to a position designated in the preset for which it is desired to recognize the amount of deviation in the angle of view.

[0085] Next, in step 1008, the preset re-registration unit 410 waits until the camera unit 101 stops, and after the camera unit 101 stops, acquires focal length information from the camera unit 101. Thereafter, the preset re-registration unit 410 stores the acquired focal length information in the work memory 405 in association with the target preset number.

[0086] Next, in step 1009, the preset re-registration unit 410 executes the deviation amount recognition process 700 described with reference to FIG. 7, for example, to calculate the amount of deviation in the angle of view of the target preset.

[0087] Next, in step 1010, the preset re-registration unit 410 stores the amount of view angle shift calculated in step 1009 in association with the target preset in the work memory 405. When the calculation of the amount of view angle shift for all presets is completed, the process proceeds to preset re-registration process (2) 1100 shown in FIG.

[0088] Next, a preset re-registration process (2) performed by the preset re-registration unit according to the embodiment of the present disclosure will be described with reference to FIG.

[0089] 11 is a flowchart of a preset re-registration process (2) 1100 by a preset re-registration unit according to an embodiment of the present disclosure. The preset re-registration process (2) 1100 is a second part of the process for re-registering the presets of the camera unit 101, and is a process for calculating a movement angle indicating the amount of deviation in the angle of view in degrees. The preset re-registration process (2) 1100 may be performed after the calculation of the amount of deviation in the angle of view for all presets is completed in the preset re-registration process (1) 1000 shown in FIG.

[0090] First, in step 1110, the preset re-registration unit 410 sets the initial value of the accumulated movement angle to "0." This accumulated movement angle is the sum of the amount of view angle deviation calculated for each preset.

[0091] Next, in step 1111, the preset re-registration unit 410 sets the initial value of the number of times the cumulative movement angle has been calculated to "0." In the following description, the number of times the cumulative movement angle is calculated will be referred to as a "count."

[0092] Next, in step 1112, the preset re-registration unit 410 determines whether or not the process of calculating the accumulated movement angle for all calculated amounts of view angle shift has been completed. If the process of calculating the accumulated movement angle for all amounts of view angle shift has been completed, the process proceeds to step 1120. On the other hand, if the process of calculating the accumulated movement angle for all amounts of view angle shift has not been completed, steps 1113 to 1119 are repeated until the movement angle is calculated for all amounts of view angle shift.

[0093] In step 1113 , the preset re-registration unit 410 acquires from the work memory 405 the amount of view angle deviation to be processed, from among the amounts of view angle deviation calculated in the preset re-registration process ( 1 ) 1000 .

[0094] Next, in step 1114 , the preset re-registration unit 410 acquires from the work memory 405 the focal length associated with the amount of deviation of the angle of view to be processed acquired in step 1113 .

[0095] Next, in step 1115, the preset re-registration unit 410 calculates the viewing angle of the camera unit 101 from the focal length acquired in step 1114 and the image sensor size of the camera unit 101. Here, the preset re-registration unit 410 may calculate the viewing angle using, for example, the above-mentioned formulas 1 and 2.

[0096] Next, in step 1116, the preset re-registration unit 410 calculates a movement angle using the viewing angle calculated in step 1115 and the amount of view angle deviation of the processing target acquired in step 1113. Here, the preset re-registration unit 410 may calculate the movement angle using, for example, the above-mentioned formulas 3 and 4.

[0097] Next, in step 1117, the preset re-registration unit 410 sets a weight for the movement angle calculated in step 1116. This weight is decided based on the focal length acquired in step 114 and the amount of view angle deviation acquired in step 1113. Here, the weight is set for the movement angle because the influence of the stopping accuracy of the camera unit 101 on the movement angle differs depending on the focal length, and in order to obtain an accurate movement angle, it is desirable to mitigate the difference in the influence of the stopping accuracy of the camera unit 101 on the movement angle.

[0098] More specifically, when the focal length is short, that is, in the wide direction, the movement angle is not affected by the stopping accuracy of the camera unit 101, but the amount of deviation (number of pixels) on the image tends to be small. On the other hand, when the focal length is long, that is, in the telephoto direction, the movement angle is affected by the stopping accuracy of the camera unit 101, but the amount of deviation (number of pixels) on the image may be large. Therefore, in order to estimate a more accurate movement angle, it is desirable to set a weight for the accumulated movement angle for each focal length between 0 and 1.0. Also, when the amount of deviation of the angle of view is 0, it is possible that the amount of deviation of the angle of view could not be measured, so it is desirable to set the weight to 0 so that it is not reflected in the accumulated movement angle. In this way, the weight for counting is set to 0 or 1, and the weight is set to 0 when the amount of deviation of the angle of view is 0, and the weight is set to 1 in other cases.

[0099] Next, in step 1118, the preset re-registration unit 410 calculates the cumulative movement angle. Here, the preset re-registration unit 410 calculates the cumulative movement angle c may be calculated according to the following formula: [Number 5] Cumulative travel angle c = cumulative travel angle p +(weight c × travel angle c ) Here, the cumulative movement angle p is the sum of the preset movement angles processed up to now, and the movement angle c is the movement angle of the preset to be processed (i.e., the movement angle calculated in step 1116), and the weight cis the preset movement angle (movement angle c ) are the weights set for

[0100] Next, in step 1119, the preset re-registration unit 410 calculates the latest count, count, according to the following formula: c Calculate. [Number 6] count c =Count p +(1×weight c ) Here, count p is the number of times the cumulative movement angle has been calculated up to now (i.e., the number of presets processed), and weight c is the preset movement angle (movement angle c ) are the weights set for

[0101] Next, in step 1120, when the process of calculating the accumulated movement angle for all the calculated view angle shift amounts is completed, the preset re-registration unit 410 calculates a weighted average movement angle according to the following formula. [Number 7] Weighted average moving angle = cumulative moving angle c / count c Here, in order to calculate a more accurate movement angle, a method of calculating a weighted average of the movement angles is adopted, but the present disclosure is not limited to this, and for example, a method of using only the initially calculated movement angle, or a method of using the minimum, median, or maximum value of the movement angles calculated for each preset may also be considered. After calculating the weighted average movement angle, the process proceeds to preset re-registration process (3) 1200 shown in FIG.

[0102] Next, the preset re-registration process (3) performed by the preset re-registration unit according to the embodiment of the present disclosure will be described with reference to FIG.

[0103] 12 is a flowchart of preset re-registration process (3) 1200 by the preset re-registration unit according to an embodiment of the present disclosure. The preset re-registration process (3) 1200 is a third part of the process for re-registering the presets of the camera unit 101, and may be performed after the weighted average movement angle is calculated in the preset re-registration process (2) 1100 shown in FIG.

[0104] First, in step 1201, the preset re-registration unit 410 determines whether the preset re-registration process has been completed for all presets included in the preset information. If it is determined that the preset re-registration process has been completed for all presets, the process returns to step 1001 and performs the subsequent steps. If it is determined that the preset re-registration process has not been completed for all presets, the preset re-registration unit 410 repeats steps 1202 to 1206 until the preset re-registration process has been completed for all presets.

[0105] In step 1202, the preset re-registration unit 410 moves the camera unit 101 to a position specified in the preset to be re-registered, using the camera head control unit 408. For example, if the position specified in the preset to be re-registered is "140 degrees", the preset re-registration unit 410 moves the camera unit 101 to the "140 degrees" position, using the camera head control unit 408.

[0106] Next, in step 1203, the preset re-registration unit 410 uses the camera head control unit 408 to move the camera unit 101 by the weighted average movement angle calculated in step 1120 or step 1005. As a result, the camera unit 101 is moved to a position estimated to be the preset re-registration position (i.e., the corrected position). Also, since the camera unit 101 can be moved using the movement angle stored by the user's manual positioning in step 1005, it is possible to update all presets based on the movement angle determined for one preset by manual operation. This reduces the workload on the user and shortens the time required to re-register presets.

[0107] Next, in step 1204, the preset re-registration unit 410 checks whether or not a user adjustment is required before re-registering the correction position to which the camera unit 101 was moved in step 105 as a new preset. For example, here, the preset re-registration unit 410 may display a confirmation box on the screen of the user interface of the display unit 103 asking "Do you want to re-register the preset or perform manual adjustment?" If user adjustment is required, the process proceeds to step 1205. On the other hand, if user adjustment is not required, the process proceeds to step 1206.

[0108] In step 1205, the user adjusts the position of the camera unit 101 using the operation screen of the display unit 103. Thereafter, the user presses the preset registration button on the operation screen of the display unit 103 to end the manual positioning process.

[0109] Next, in step 1206, the preset re-registration unit 410 re-registers the correction position to which the camera was moved in step 1203 or step 1205 as a new preset (for example, a second preset). Here, "re-registering the correction position as a new preset" means updating the angle of the target preset to the angle of the correction position in the preset information shown in Fig. 6, for example. In this way, by updating each preset included in the preset information to the angle of the correction position, it is possible to generate new preset information (for example, second preset information) in which the view angle deviation of the camera unit 101 is corrected. Furthermore, when the preset is re-registered, the preset re-registration unit 410 updates the reference image memory 404 and the reference position data 409. When the reference position data 409 is updated, a QR code or pattern recognition process may be performed.

[0110] As an example, in the preset information, the "pan" angle of the first preset is set to "140 degrees." However, as a result of calculating the weighted average movement angle in step 1120, the camera unit 101 determines that there is a deviation of 20 degrees from the first preset. In this case, the preset re-registration unit 410 moves the camera unit 101 to the "140 degrees" position in step 1202, and then moves the camera unit 101 further by "20 degrees" equivalent to the weighted average movement angle to the "160 degrees" position in step 1203. Then, in step 1206, the preset re-registration unit 410 updates the first preset of "140 degrees" to "160 degrees" and re-registers it as a new second preset. As a result, when the camera unit 101 is moved to the corrected position of "160 degrees" according to the second preset, a deviation of 20 degrees occurs, and the camera unit 101 returns to the position of "140 degrees" originally specified in the first preset, thereby eliminating the angle of view deviation.

[0111] According to the preset re-registration described above with reference to Fig. 10 to Fig. 12, it is possible to automatically correct the deviation of the camera's angle of view caused by aging, etc., for various presets that specify changes in the direction and angle of view of a surveillance camera such as a rotating camera. This makes it possible to shorten the time required for manual re-registration work and significantly reduce the burden on the user.

[0112] Next, with reference to FIG. 13, an image display during manual alignment according to an embodiment of the present disclosure will be described.

[0113] Fig. 13 is a diagram showing an example of an image display during manual alignment according to an embodiment of the present disclosure. As described above, for example, in the preset re-registration process (1) 1000 described with reference to Fig. 10 and the preset re-registration process (3) 1200 described with reference to Fig. 12, the user may manually move the camera unit 101 to eliminate a deviation in the angle of view of the camera unit 101. However, when performing this manual alignment, it may be difficult to align the camera unit 101 using only the camera image. Therefore, the present disclosure provides a configuration that can display an input image acquired by the camera unit 101 and a reference image without any misalignment in the angle of view in a superimposed manner, thereby facilitating position adjustment during manual positioning.

[0114] 13, for example, the overlaid display image 1303-1 shows a case where the reference image 1301 is displayed by a dotted line and the input image 1302-1 acquired by the camera unit 101 is displayed by a solid line. While referring to the overlaid display image 1303-1, the user can manually correct the angle of view deviation by moving the camera unit 101 so that the input image 1302-1 is superimposed on the reference image 1301.

[0115] Furthermore, as shown in the overlaid display image 1303-2, in addition to displaying the reference image 1301 with a dotted line and the input image 1302-2 acquired by the camera unit 101 with a solid line, it is possible to calculate the vertical and horizontal differences between the images and display the calculated differences as a bar graph. In this case, the user can manually correct the angle of view deviation by moving the camera unit 101 so as to minimize the difference between the images shown by the bar graph.

[0116] In addition, although two types of superimposed display are described in Fig. 13, the present disclosure is not limited to this, and other superimposed display methods are also possible. As an example, by taking the difference between the reference image and the input image and displaying a binarized image (black and white image), it is possible to provide an image in which white is displayed when there is a positional deviation and black is displayed when there is no deviation. Furthermore, it is also possible to display the difference amount on the vertical axis and horizontal axis as a line graph instead of a bar graph.

[0117] Next, an operation screen displayed on the user interface of the display unit according to the embodiment of the present disclosure will be described with reference to FIG.

[0118] 14 is a diagram showing an example of an operation screen 1400 displayed on the user interface of the display unit 103 according to an embodiment of the present disclosure. The operation screen 1400 shown in FIG. 14 is a screen for performing manual positioning of the camera unit 101.

[0119] As shown in FIG. 14, operation screen 1400 is composed of an input image 1401 acquired from camera unit 101, a camera selection list 1402, control buttons 1403 for adjusting the movement of the camera head, zoom, and focus, a button with an image 1404 for performing preset operations, an error display 1405, and a preset re-registration button 1406. An input image 1401 is acquired from a video distribution source address 307 registered in a database 305. A camera selection list 1402 is created based on a camera name 306 registered in a database 305. A control button 1403 is created based on a model information 309 registered in a database 305. A button 1404 with a screen for performing a preset operation is created based on preset information 308 and a preset image 310 in a database 305. A preset re-registration button 1406 is a button for re-registering, as a new preset, a position to which the camera unit 101 has been moved by operating the operation screen 1400 (i.e., a correction value that has eliminated the deviation in the angle of view).

[0120] Although the embodiment of the present invention has been described above, the present invention is not limited to the above-described embodiment, and various modifications are possible without departing from the gist of the present invention. [Explanation of symbols]

[0121] 100-200: monitoring system, 101: camera unit, 102: monitoring unit, 103: display unit, 104-1-104-2: position correction unit, 301-415: program memory, 302: screen creation unit, 303: screen display unit, 304: communication confirmation unit, 305: database, 306: camera name, 307: video distribution source address, 308: preset information, 309: model information, 310: preset image, 311: terminal information, 312: data bus, 313: CPU, 314: LAN I / F, 401: image input I / F, 402: processing memory, 403: image memory, 404: reference image memory, 405: work memory, 406: deviation amount recognition section, 407-1, 407-2: correction section, 408: head control section, 409: reference position data, 410: preset re-registration section, 501: output image memory, 600: preset information table, 700: deviation amount recognition processing, 800, 900: position correction processing, 1000: preset re-registration processing (1), 1100: preset re-registration processing (2), 1200: preset re-registration processing (3), 1301: reference image, 1302-1, 1302-2: input image, 1303-1, 1303-2: overlaid display image, 1400: operation screen

Claims

1. A surveillance system including a camera unit, a surveillance unit, and a position correction unit, the monitoring unit includes a database that stores first preset information that defines a direction and an angle of view of the camera unit; The position correction unit is a deviation amount recognition unit that determines a deviation amount of an angle of view that indicates, for the first preset information, how much the angle of view of the camera unit deviates from a predetermined reference as a number of pixels; a correction unit that uses a movement angle calculated from the determined amount of deviation in the angle of view to move the camera unit to a correction position that eliminates the amount of deviation in the angle of view; a preset re-registration unit that updates the first preset information based on the corrected position and registers the updated first preset information as second preset information, The deviation amount recognition unit Acquire an input image acquired by the camera unit and a reference image captured in a correct direction and with a correct angle of view of the camera unit; comparing the input image with the reference image and determining whether a reference pattern preregistered in the reference image is recognizable in the input image; If it is determined that the reference pattern is recognizable in the input image, determining, based on the input image and the reference image, the number of pixels of the input image that are shifted with respect to the reference image as the amount of deviation of the angle of view; If it is determined that the reference pattern is not recognizable in the input image, determining whether the input image is normal or abnormal based on a video state of the input image; If the input image is normal, the amount of deviation of the angle of view is set to 0 and the reference pattern is re-registered. If the input image is abnormal, the amount of deviation of the angle of view is set to 0 and processing by the correction unit is not performed. A monitoring system comprising:

2. The reference pattern is The QR code is embedded in the reference image or is a previously designated subject.

2. The monitoring system according to claim 1 .

3. The deviation amount recognition unit Determining whether an input image is normal or abnormal based on whether any of the values ​​of the edge amount, contrast difference, and image level of the two images, the input image and the reference image, satisfies a predetermined similarity criterion; 2. The monitoring system according to claim 1 .

4. The correction unit is acquiring focal length information and image sensor size information of the camera unit from the camera unit; Calculating a viewing angle of the camera unit based on the focal length information and the image sensor size information; Calculating the movement angle based on the determined amount of view angle deviation and the calculated viewing angle; If the calculated movement angle satisfies a predetermined movement angle threshold, the camera unit is moved from a position designated in the first preset information to the correction position based on the movement angle.

2. The monitoring system according to claim 1 .

5. The monitoring system includes: Further comprising a display unit, the correction unit outputs an output image generated by superimposing the input image and the reference image to the display unit.

5. The monitoring system according to claim 4.

6. When the deviation amount recognition unit determines that the input image is normal, The preset re-registration unit Calculating the movement angle for each preset included in the first preset information from the view angle deviation amount, the focal length information, and the view angle; Calculating a weighted average movement angle, which is a weighted average of the movement angles, based on the movement angles calculated for each preset and a weight set based on the focal length information; registering the corrected position determined from the weighted average movement angle for each preset included in the first preset information as the second preset information; 6. A monitoring system according to claim 4 or 5.

7. A monitoring method using a monitoring system including a camera unit, a monitoring unit, and a position correction unit, acquiring an input image acquired by the camera unit and a reference image captured in a correct orientation and with a correct angle of view of the camera unit; comparing the input image with the reference image and determining whether a predetermined reference pattern in the reference image is recognizable in the input image; determining, when it is determined that the reference pattern is recognizable in the input image, a number of pixels of the input image that are shifted with respect to the reference image as an amount of deviation of an angle of view based on the input image and the reference image; a step of determining whether the input image is normal or abnormal based on a video state of the input image when it is determined that the reference pattern is unrecognizable in the input image, and if the input image is normal, re-registering the reference pattern with the amount of deviation of the angle of view set to 0, and if the input image is abnormal, not performing a process of moving the camera unit to a correction position with the amount of deviation of the angle of view set to 0; acquiring focal length information and image sensor size information of the camera unit from the camera unit; calculating a viewing angle of the camera unit based on the focal length information and the image sensor size information; calculating a movement angle that indicates the amount of deviation of the angle of view of the camera unit in degrees based on the determined amount of deviation of the angle of view and the calculated viewing angle; a step of moving the camera unit from a position designated in first preset information to a correction position that eliminates the amount of deviation of the angle of view based on the movement angle when the calculated movement angle satisfies a predetermined movement angle threshold value; creating second preset information by updating the first preset information based on the corrected position; controlling movement of the camera unit using the second preset information; A monitoring method comprising:

Images