JP2017204825A - Camera system and camera device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To allow for highly accurate detection of an object by performing appropriate area setting, even if there is a change in a captured image.SOLUTION: The camera device 10 of a camera system images an object area, performs area setting including the setting of a detection area for executing detection of an object, in a captured image of the object area, and when a predetermined detection event occurs in the detection area of the captured image, determines occurrence of event and transmits event detection information to a server device 20, determines existence of a change in the area setting at a predetermined determination timing, and transmits area change detection information to the server device 20 when a change of area setting occurred. The server device 20 acquires the event detection information or area change detection information transmitted from the camera device 10, and displays a notification screen for notifying a monitor 42 of the occurrence of a detection event or the change of area setting.SELECTED DRAWING: Figure 3

Description

  The present invention relates to a camera system and a camera apparatus that capture an image of a desired subject and detect an object in a predetermined area in a captured image.

  Camera systems are used in various applications and locations, such as monitoring applications that monitor the situation in a specific location. In a camera system, a camera device that captures an image of a subject sets an imaging area by adjusting an angle of view of an imaging lens in order to capture a desired area, or uses a PTZ (pan / zoom / tilt) mechanism. It has a function of allowing the imaging region to be arbitrarily adjusted by displacing the imaging lens.

  In this type of camera device, when a specific subject is continuously imaged, the orientation of the imaging lens and the zoom amount are determined so that an appropriate imaging region including the subject to be imaged is obtained, and the imaging region is constant. In this state, the position of the imaging lens is fixed. However, the image position of the captured image captured by the camera device may change due to secular change, etc., and the target subject cannot be captured properly due to the positional deviation of the captured image, and the monitoring of the target is normal Issues such as inability to occur.

  For example, Patent Document 1 discloses an image misregistration detection device that can detect the occurrence of misregistration of a captured image. In this conventional image misregistration detection apparatus, a corrected image obtained by performing gradation correction processing on the time-accumulated image of the input image is created, a correlation value between the corrected image and the reference image is calculated, and the correlation value is obtained. Based on the position deviation. This makes it possible to detect misalignment even when a large change occurs in the subject to be photographed by the camera and the surrounding environment due to aging.

JP 2007-208513 A

  In the camera system, when detecting an object in a specific area within the imaging area, for example, the detection area is set in the captured image, and the object appearing in the set detection area is detected. In this case, if the position of the captured image is shifted due to secular change or the like and the position of the set detection area is changed, there is a possibility that a detection failure or an erroneous detection may occur for an assumed event. In addition, if an environmental change such as a layout change, movement, or increase / decrease of an object occurs in the imaging area, the positional relationship between the initially set detection area and the object may be shifted, resulting in detection failure or false detection. There is. It is difficult to detect an object by adapting to such various changes in the captured image, and an appropriate detection area cannot be easily set.

  In order to solve the above-described conventional problems, the present invention provides a camera system and a camera apparatus that can detect an object with high accuracy by performing appropriate area setting even when a change occurs in a captured image. The purpose is to provide.

  The present invention is a camera system in which a camera device and a server device are connected to each other, and the camera device images a target region and detects a target in a captured image of the target region. When a predetermined detection event occurs in the detection region in the captured image, the event occurrence is determined and event detection information is transmitted to the server device, and at a predetermined determination timing, It is determined whether or not there is a change in the area setting, and when the change in the area setting occurs, area change detection information is transmitted to the server apparatus, and the server apparatus transmits the event detection information transmitted from the camera apparatus. Or, the area change detection information is acquired, and a notification screen for notifying the occurrence of the detection event or the change of the area setting is displayed on a monitor connected to the server device. To provide a camera system.

  In addition, the present invention is a camera device that captures a target area, and in the captured image of the target area, performs area setting including setting of a detection area for performing detection of the target object, and detects the detection area in the captured image When a predetermined detection event occurs, event occurrence is determined and event detection information is generated, and whether there is a change in the region setting at a predetermined determination timing, and a change in the region setting occurs A notification screen for generating the area change detection information and notifying the monitor connected to the camera device of the occurrence of the detection event or the change of the area setting based on the event detection information or the area change detection information Provided is a camera device.

  According to the present invention, even when a change occurs in a captured image, an appropriate region can be set and an object can be detected with high accuracy.

Block diagram showing the system configuration of the camera system of the present embodiment (A), (B) The figure which shows an example of the setting screen which performs the area | region setting in a captured image The block diagram which shows the functional internal structure of the camera apparatus and server apparatus of 1st Embodiment. The flowchart which shows the 1st example of the shift | offset | difference detection process of the area setting in the camera apparatus of 1st Embodiment. The flowchart which shows the 2nd example of the shift | offset | difference detection process of the area setting in the camera apparatus of 1st Embodiment. (A), (B) The figure which shows an example of the notification screen at the time of detecting a region setting shift | offset | difference The block diagram which shows the functional internal structure of the camera apparatus and server apparatus of 2nd Embodiment. The flowchart which shows the 1st example of the shift | offset | difference detection process of the area setting in the camera apparatus of 2nd Embodiment. The flowchart which shows the 2nd example of the shift | offset | difference detection process of the area | region setting in the camera apparatus of 2nd Embodiment.

  Hereinafter, an embodiment (hereinafter referred to as “the present embodiment”) that specifically discloses a camera system and a camera apparatus according to the present invention will be described in detail with reference to the drawings as appropriate. However, more detailed description than necessary may be omitted. For example, detailed descriptions of already well-known matters and repeated descriptions for substantially the same configuration may be omitted. This is to avoid the following description from becoming unnecessarily redundant and to facilitate understanding by those skilled in the art. The accompanying drawings and the following description are provided to enable those skilled in the art to fully understand the present disclosure, and are not intended to limit the subject matter described in the claims.

  In the following embodiment, as shown in FIG. 1, for example, a plurality of sites (site A (100A), site B (100B),...) And a management headquarter 200 that manages the camera system are connected via a network 300. Description will be made assuming a connected system form. However, the embodiment of the camera system and the camera device according to the present invention is not limited to the contents of the embodiment described later.

(System configuration)
FIG. 1 is a block diagram showing the system configuration of the camera system of this embodiment. In the camera system, a plurality of sites 100A, 100B,... And the operation headquarters 200 that manages the camera system are connected to each other via a network 300, and image data captured at each site is transmitted and received. Is called. The site A (100A) is provided with a plurality of camera devices 10A, 10B,... 10N, a server device 20, a recorder 30, an input device 41, and a monitor 42. These devices are connected via a network 70. Are connected to each other. The networks 300 and 70 are wireless networks or wired networks. The wireless network is, for example, a wireless LAN (Local Area Network), a wireless WAN (Wide Area Network), 3G, LTE (Long Term Evolution), or WiGig (Wireless Gigabit). The wired network is, for example, an intranet or the Internet. Moreover, although not shown in figure, the camera apparatus, a server apparatus, a recorder, an input device, and a monitor are provided in the site B (100B) similarly to the site A (100A).

  Camera devices 10 (hereinafter, representative of camera devices 10A, 10B,... 10N) are respectively installed at desired positions on site 100 (hereinafter, representative of site A (100A), site B (100B),...). Then, the subject in the imaging area set at each installation position is imaged. The detailed configuration of the camera device 10 will be described later. The server device 20 is configured using, for example, a PC (Personal Computer), and performs various settings, controls, and the like of the camera device 10 in accordance with a user input operation using the input device 41. At this time, the server device 20 displays a menu screen, a setting screen, a control screen, and the like related to the management of the camera device 10 on the monitor 42. Further, the server device 20 acquires image data of an image obtained by imaging of each camera device 10 (hereinafter, an image obtained by imaging of the camera device is referred to as “captured image”), and the captured image is displayed on the monitor 42. Display. Further, the server device 20 displays a detection notification screen on the monitor 42 and transmits a detection notification to the operation headquarters 200 in accordance with the detection result of the object by the camera device 10.

  The recorder 30 is configured using, for example, a semiconductor memory or a hard disk device, and stores image data of a captured image captured by each camera device 10 installed in the site 100. The image data of the captured image stored in the recorder 30 is used for monitoring work such as crime prevention, security, and material management.

  The input device 41 is configured using, for example, a mouse, a keyboard, a touch panel, or a touch pad, and outputs a signal corresponding to a user input operation to the camera device 10 or the server device 20. Although FIG. 1 shows a configuration in which the input device 41 is connected to the server device 20, the input device 41 may be connected to the camera device 10.

  The monitor 42 is configured by using, for example, an LCD (Liquid Crystal Display) or an organic EL (Electroluminescence), and displays a captured image captured by the camera device 10 and various screens generated by the server device 20. The monitor 42 is provided as an external device different from the server device 20, but may be configured to be included in the server device 20.

  The operation headquarter 200 is provided with a server device 210, an input device 221, and a monitor 222, and performs browsing processing of various information related to the captured image, such as browsing of the captured image captured at each site 100 and confirmation of the detection result of the target object. Done. The server apparatus 210 causes the monitor 222 to display a display screen for various information such as a captured image and a detection result in accordance with a user input operation using the input device 221. Further, the server device 210 may have the same function as the server device 20 at each site 100, and may be capable of processing such as various settings and control of the camera device 10.

(Region setting)
When detecting an object in a specific area in the camera system, the user sets a detection area for executing detection of the object and a mask area for excluding detection determination in the captured image captured by the camera device 10. The setting of the area including the detection area and the mask area is referred to as “area setting”, and the area including the detection area and the mask area set by the area setting is referred to as “setting area”. The camera device 10 determines that a predetermined detection event has occurred when the presence, movement, or other event of a specific object occurs in the detection region in the captured image, and records the event occurrence, the server device 20. Execute actions when an event occurs, such as sending event detection information to Further, the camera device 10 determines that even if any event occurs in the mask area, it is not a predetermined detection event, and does not execute the operation when the event occurs. When the server device 20 receives the event detection information from the camera device 10, the server device 20 displays a notification screen informing the occurrence of the detection event on the monitor 42 to notify the user that a predetermined event has been detected.

  FIG. 2 is a diagram illustrating an example of a setting screen for setting a region in a captured image. 2 is displayed on the monitor 42 provided in the site 100 or the monitor 222 provided in the operation headquarters 200, and the region setting process is executed by the operation input of the input devices 41 and 221. . Below, the case where the area | region setting process is performed with the server apparatus 20, the monitor 42, and the input device 41 in the spot 100 is demonstrated.

  FIG. 2A shows a first example of a region setting method for setting a detection region and a mask region by designating a region. The camera device 10 transmits the captured image to the server device 20. The server device 20 displays the captured image 50 acquired by the camera device 10 on the monitor 42 as in the setting screen on the left side in the drawing. The camera device 10 recognizes boundaries, contours, specific objects, and the like based on values and changes in color, brightness, etc. in the captured image 50, and divides the captured image into regions. Then, the server device 20 displays an area frame by outlines indicating the areas 51a, 51b, 51c, and 51d divided on the captured image, an area surface by a solid or shaded plane, and the like. In this setting screen, first, the user designates “detection region” or “mask region” at the lower left of the setting screen by the input device 41, and selects the region type to be set. Then, from the divided areas 51a, 51b,..., The user designates an area to be set as a detection area or a mask area by the input device 41, selects the target area, and instructs the setting button 52 at the lower right of the setting screen. Then, a detection area or a mask area is set. This setting instruction is sent to the camera device 10, and the detection region and the mask region are set in the camera device 10. As a result, the set detection area 55 and mask area 56 are displayed as in the setting screen after setting the area on the right side of the drawing. By instructing the OK button 57 at the lower right of the setting screen after setting the area, the area setting process is completed, and the area setting information by the user operation is stored in the camera device 10.

  FIG. 2B shows a second example of an area setting method for setting a detection area and a mask area by selecting a feature point. The server device 20 displays the captured image 50 acquired by the camera device 10 on the monitor 42 as in the setting screen on the left side in the drawing. The camera device 10 recognizes boundaries, contours, specific objects, and the like based on values and changes in color, brightness, and the like in the captured image 50, and extracts feature points from the captured image. And the server apparatus 20 displays each feature point 53a, 53b, 53c, ... 53k, ... 53n extracted on the captured image. In this setting screen, first, the user designates “detection region” or “mask region” at the lower left of the setting screen by the input device 41, and selects the region type to be set. Then, from the extracted feature points 53a to 53n, the target region is determined by specifying a plurality of feature points corresponding to the region that the user wants to set as the detection region or the mask region by the input device 41, and is set in the lower right portion of the setting screen. The button 52 is instructed to set a detection area or a mask area. This setting instruction is sent to the camera device 10, and the detection region and the mask region are set in the camera device 10. As a result, the set detection area 55 and mask area 56 are displayed as in the setting screen after setting the area on the right side of the drawing. By instructing the OK button 57 at the lower right of the setting screen after setting the area, the area setting process is completed, and the area setting information by the user operation is stored in the camera device 10.

(First embodiment)
<Configuration of camera device>
FIG. 3 is a block diagram illustrating a functional internal configuration of the camera device and the server device according to the first embodiment. The camera apparatus 10 includes an imaging unit 101, an image input unit 102, a feature extraction unit 103, a region setting unit 104, a region setting information storage unit 105, a deviation / change detection unit 106, a transmission unit 107, and a reception unit 108. . The feature extraction unit 103 includes a region division unit 131 and a feature point extraction unit 132. The deviation / change detection unit 106 includes a deviation determination unit 161 and a change extraction unit 162.

  The imaging unit 101 includes at least a lens and an image sensor. The lens collects light (light rays) incident from the outside of the camera device 10 and forms an image on a predetermined imaging surface of the image sensor. As the lens, a fish-eye lens or a wide-angle lens capable of obtaining an angle of view of, for example, 140 degrees or more is used. The image sensor is, for example, a solid-state imaging device such as a charge-coupled device (CCD) or a complementary metal oxide semiconductor (CMOS), and converts an optical image formed on the imaging surface into an electrical signal. The imaging unit 101 may be any imaging optical system such as an omnidirectional camera device, a fixed camera device with a fixed angle of view, or a PTZ camera device having a PTZ mechanism having a pan direction, a tilt direction, and a zoom function. It may have.

  The image input unit 102 is configured using, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or a DSP (Digital Signal Processor), and performs predetermined signal processing using an electrical signal from the imaging unit 101. Thus, data (frame) of a captured image having a predetermined frame rate (for example, 30 fps (frame per second)) defined by RGB (Red Green Blue) or YUV (luminance / color difference) recognizable by humans is generated. The image input unit 102 outputs the generated captured image data to the feature extraction unit 103.

  The feature extraction unit 103 is configured using, for example, a CPU, MPU, or DSP, and uses predetermined captured image data (for example, region segmentation) for each predetermined time interval using captured image data output from the image input unit 102. By performing processing and feature point extraction processing, feature information based on regions, feature points, and the like in the captured image is extracted. The region dividing unit 131 recognizes features such as boundaries, contours, specific objects, and the like based on values and change amounts of color, brightness, and the like in the captured image, and performs region division processing that divides the captured image into a plurality of regions. As a result of the area division process, divided area information including information such as the number, position (coordinates such as boundaries), area, and the like of each divided area is acquired. The feature point extraction unit 132 recognizes boundaries, contours, specific objects, and the like based on values and change amounts of color, brightness, and the like in the captured image, and performs feature point extraction processing to extract a plurality of feature points in the captured image. As a processing result of the feature point extraction process, feature point information including information such as the number, position (feature point coordinates), and feature vector of each extracted feature point is acquired.

  The region setting unit 104 uses the divided region information or feature point information extracted by the feature extraction unit 103 to exclude the detection region for detecting the object and the detection determination by the procedure using FIG. 2 described above. Set the area to be masked. The region setting unit 104 outputs region setting information regarding the detection region and the mask region to the region setting information storage unit 105. The area setting information storage unit 105 is configured using, for example, a semiconductor memory or a hard disk device, and stores area setting information of the detection area and the mask area set by the area setting unit 104.

  The shift / change detection unit 106 is configured by using, for example, a CPU, MPU, or DSP, and divided region information or feature point information generated by the feature extraction unit 103 and a region setting stored in the region setting information storage unit 105. Information is used to detect the occurrence of displacement or change in the area setting of the detection area and the mask area. As a method for detecting the shift of the setting area, a known motion detection method in an image may be used. For example, a pixel that does not move in a predetermined period (long term or short term) is regarded as a non-moving region that does not change (does not move), and features such as edge, color, and brightness of the non-moving region are extracted and extracted. A method of calculating a deviation by obtaining a change amount of a feature portion by pattern matching or point matching of the feature is used. As the shift of the set area, the area of each area is enlarged or reduced, the movement of each area (increase in the position error of the feature point), or the like is detected. Here, the following detection method is used.

  The shift determination unit 161 compares the area setting information with the divided area information or feature point information, and the difference between the previously set position of the setting area and the area division result or the feature point position in the current captured image is determined. It is determined whether or not the difference is greater than or equal to a predetermined value. If the difference in position is equal to or greater than the predetermined value, it is determined that a positional deviation has occurred. The change extraction unit 162 compares the region setting information with the divided region information or the feature point information, and positions between the previously set setting region and the region divided result or the feature point extracted region in the current captured image. Alternatively, it is determined whether or not the difference in area is greater than or equal to a predetermined value. If the difference in position or area is greater than or equal to the predetermined value, it is determined that there is a region change. The deviation / change detection unit 106 outputs area change detection information when a displacement or change relating to area setting is detected as a result of the deviation detection process.

  The transmission unit 107 includes a communication circuit that performs wired communication or wireless communication. The transmission unit 107 includes divided region information or feature point information generated by the feature extraction unit 103, region setting information generated by the region setting unit 104, The area change detection information generated by the shift / change detection unit 106 is transmitted to the server device 20. The receiving unit 108 includes a communication circuit that performs wired communication or wireless communication, and receives input information transmitted from the server device 20. In the illustrated example, the transmission unit 107 and the reception unit 108 are separately illustrated, but a configuration including a communication unit including the transmission unit 107 and the reception unit 108 may be used.

  The region setting unit 104 designates a region or a feature point related to the detection region and the mask region with respect to the divided region information or the feature point information generated by the feature extraction unit 103 according to the input information from the server device 20 based on the user operation. Input and execute the area setting of the detection area and the mask area.

  The server device 20 includes an input information receiving unit 201, a display image generating unit 202, a receiving unit 203, and a transmitting unit 204. The input information receiving unit 201 is configured to include an interface circuit such as a USB (Universal Serial Bus), for example, and receives input information related to a region setting instruction output from the input device 41 based on a user operation, and generates a display image Output to the unit 202 and the transmission unit 204. The display image generating unit 202 includes an interface circuit such as HDMI (High-Definition Multimedia Interface) (registered trademark), and receives information received from the camera device 10 received by the receiving unit 203 and an input information receiving unit. Using the input information from 201, a display image signal is generated and output to the monitor 42. The display image generation unit 202 notifies that the setting image regarding the captured image and the region setting and the region setting shift are detected based on the captured image data, the divided region information or feature point information, the region setting information, and the region change detection information. A display image such as a notification screen is generated and displayed on the monitor 42.

<Area setting deviation detection processing>
In the first embodiment, a configuration example will be described in which a displacement of a setting area accompanying a change in a captured image due to a lens position shift or a field angle change of a camera device is detected.

  FIG. 4 is a flowchart illustrating a first example of region setting shift detection processing in the camera device of the first embodiment. The first example shows a region setting shift detection process when region setting is performed by region specification shown in FIG.

  The camera apparatus 10 determines whether or not it is time to determine the occurrence of a shift in area setting in the shift / change detection unit 106 (S11). The determination timing of the region setting deviation is, for example, a deviation determination at every predetermined time or a change in the position of the picked-up image by using a timing such as when a predetermined time such as one hour elapses or when the imaging angle of view is changed by the PTZ mechanism. Time shift determination is possible. At this time, in the camera device 10, it is assumed that the detection area and the mask area are already set by area division.

  When the determination timing for the region setting shift is reached, the camera device 10 acquires a captured image captured by the imaging unit 101 in the image input unit 102 (S12). Subsequently, the camera device 10 performs region division processing in the region dividing unit 131 of the feature extracting unit 103, and performs region division of the currently acquired captured image (S13). Then, the camera device 10 executes a change determination process for determining whether or not there is a change in the region setting in the shift determination unit 161 and the change extraction unit 162 of the shift / change detection unit 106 (S14).

  The shift determination unit 161 and the change extraction unit 162 first acquire region setting information stored in the region setting information storage unit 105 as a change determination process (S141). Then, the divided region information generated by the region dividing unit 131 is acquired, and the position and area of each divided region are compared by comparing the previously set region setting information with the current divided region information. (S142). Next, the deviation determination unit 161 and the change extraction unit 162 determine whether there is a difference of a predetermined value or more in the position and area of each divided region (S143). Here, when there is a difference greater than or equal to a predetermined value, the deviation determination unit 161 and the change extraction unit 162 determine that there is a change in each region divided (S144). On the other hand, when there is no difference greater than or equal to the predetermined value, the deviation determination unit 161 and the change extraction unit 162 determine that there is no change in each region divided (S145). With this change determination process, the presence or absence of a region change is determined regarding the region setting of the detection region and the mask region by region division.

  The camera apparatus 10 determines whether the shift / change detection unit 106 has detected a shift or change in the detection area and the mask area based on the processing result of the change determination process (S15). When a shift or change in the setting area is detected, the camera apparatus 10 updates the area setting information in accordance with the change in the area in the captured image in the area setting unit 104 and stores the new area setting information in the area setting information storage unit 105. (S16). Then, the camera device 10 transmits the region change detection information and the region setting information from the transmission unit 107 to the server device 20, and displays the updated setting region information on the monitor 42 to prompt confirmation of the setting region update ( S17).

  FIG. 5 is a flowchart illustrating a second example of the region setting shift detection process in the camera device of the first embodiment. The second example shows a region setting shift detection process when region setting is performed by feature point selection shown in FIG.

  Similarly to the first example of FIG. 4, the camera apparatus 10 determines whether or not it is time to determine the occurrence of a shift in area setting in the shift / change detection unit 106 (S <b> 21). At this time, in the camera device 10, it is assumed that the detection area and the mask area are already set by feature point selection. When it is time to determine the region setting deviation, the camera apparatus 10 acquires a captured image captured by the imaging unit 101 in the image input unit 102 (S22). Subsequently, the camera device 10 performs feature point extraction processing in the feature point extraction unit 132 of the feature extraction unit 103, and extracts feature points from the currently acquired captured image (S23). Then, the camera device 10 executes a change determination process for determining whether or not there is a change in the region setting in the shift determination unit 161 and the change extraction unit 162 of the shift / change detection unit 106 (S24).

  The shift determination unit 161 and the change extraction unit 162 first acquire the region setting information stored in the region setting information storage unit 105 and the feature point information extracted by the feature point extraction unit 132 as a change determination process. The selected feature point of the region set in (2) is matched with the currently extracted feature point (S241). Then, an error in the position between the corresponding selection point and the feature point corresponding to both features is calculated (S242). Next, the deviation determination unit 161 and the change extraction unit 162 determine whether the error between the corresponding selection point and the feature point is equal to or larger than a predetermined threshold (S243). Here, the deviation determination unit 161 and the change extraction unit 162 determine that there is a change in each feature point related to the region setting when the error is greater than or equal to the threshold (S244). On the other hand, when the error is less than the threshold value, the deviation determination unit 161 and the change extraction unit 162 determine that there is no change in each feature point related to the region setting (S245). With this change determination process, the presence / absence of a region change is determined regarding the region setting of the detection region and the mask region by the feature point selection.

  The camera apparatus 10 determines whether the shift / change detection unit 106 has detected a shift or change in the detection area and the mask area based on the processing result of the change determination process (S25). When detecting the shift or change of the set area, the camera apparatus 10 updates the area setting information in accordance with the change of the area in the captured image in the area setting unit 104, and stores the new area setting information in the area setting information. The information is stored in the unit 105 (S26). Then, the camera device 10 transmits the region change detection information and the region setting information from the transmission unit 107 to the server device 20, and displays the updated setting region information on the monitor 42 to prompt confirmation of the setting region update ( S27).

  In the procedure of the flowcharts of FIGS. 4 and 5, when a shift or change in the set area is detected, the area setting information is updated to notify the user of a new detection area and mask area. Alternatively, the user may be notified that a deviation or change in the set area has been detected, and the user may be prompted to change the area setting.

  FIG. 6 is a diagram illustrating an example of a notification screen when an area setting shift is detected. FIG. 6A shows a notification screen 61 of the first example in which the user is notified of the detection of the deviation of the setting area, and the area setting change operation by the user is accepted. In this case, on the notification screen 61, the server device 20 displays the captured image and setting area 65 at the previous area setting, and the captured image and setting area 66 in a state where the current area change has occurred on the monitor 42. . When the area change button 68 at the lower left of the notification screen is instructed, an instruction input is transmitted to the camera apparatus 10, and the camera apparatus 10 executes the area setting process again to update the area setting information.

  FIG. 6B notifies the user of the detection of the shift of the setting area, presents the changed setting area plan to the user, and accepts the permission operation for changing the area setting from the user. The screen 62 is shown. In this case, the camera apparatus 10 performs processing such as feature point extraction and region division on the current captured image, and changes the position and area of the setting region so that the target region where the region has changed is in an appropriate state. Thus, a setting area plan is generated. On the notification screen 61, the server device 20 displays on the monitor 42 a captured image and a setting area 66 in a state where the current area change has occurred, and a setting area plan 67 in which the target area where the area has changed is appropriately changed. To do. When the area change button 69 in the setting plan at the lower right of the notification screen is instructed, an instruction input is transmitted to the camera apparatus 10 and the camera apparatus 10 executes the area setting process so as to adopt the setting area plan. The area setting information is updated. When the area change button 68 at the lower left of the notification screen is instructed, the server apparatus 20 transmits an instruction input to the camera apparatus 10 and the camera apparatus 10 executes the area setting process again, as in the first example. To update the area setting information.

  For example, in the example shown in FIG. 6A, in the current captured image on the right side, the angle of view of the camera device 10 moves downward as compared to before, and the captured image is shifted upward. In this case, the same feature point as the previous captured image moves upward, and the detection area and the mask area are shifted downward with respect to the captured image. For this reason, a part of the part which should be a detection area becomes a mask area, and there is a possibility that detection omission may occur. In the present embodiment, it is possible to detect an area setting shift by determining a change in a setting area or a feature point, and it is possible to change settings of an appropriate detection area and mask area according to the current captured image.

  As described above, in the present embodiment, in the state where the detection operation is performed by performing region setting using region division of the captured image or region setting using feature point detection in the captured image, When a setting area shift occurs due to a change in the captured image due to a lens position shift or a change in the angle of view, a change in the area setting of the detection area and the mask area is detected to notify the user of the area setting shift and the shift The area setting can be changed according to the amount. Further, by extracting and using feature points in area setting and area setting change, it is possible to easily set a new detection area and mask area even if a positional deviation of the captured image occurs. At this time, each of the detection region and the mask region can cope with various positional changes such as rotation and enlargement / reduction as well as the displacement of the parallel movement. Therefore, even when a change occurs in the captured image due to a change in the angle of view of the imaging lens of the camera device, a change in the imaging region, etc., it is possible to detect an object with high accuracy by setting an appropriate region.

(Second Embodiment)
<Configuration of camera device>
FIG. 7 is a block diagram illustrating a functional internal configuration of the camera device and the server device according to the second embodiment. The second embodiment is an example in which the configuration of the camera device is partially changed. The camera device 10-1 includes an imaging unit 101, an image input unit 102, a feature extraction unit 103-1, an area setting unit 104, an area setting information storage unit 105, a deviation / change detection unit 106, a transmission unit 107, a reception unit 108, The configuration includes a detection history information storage unit 109. That is, the camera apparatus 10-1 includes a detection history information storage unit 109 in addition to the configuration of the first embodiment illustrated in FIG. The feature extraction unit 103-1 includes a region dividing unit 131, a feature point extraction unit 132, and a detection history feature extraction unit 133. In the description of each part of the camera device 10-1 shown in FIG. 7, the same components and operations as those of the camera device 10 shown in FIG.

  The detection history information storage unit 109 is configured by using, for example, a semiconductor memory or a hard disk device, and stores statistical information of the history detected in the captured image in the past predetermined time as detection history information. As statistical information of the detection history, for example, flow line information (for example, “target position information”, “flow line information”, “passing situation or The flow line analysis process that extracts the information on the stay status ”) is extracted, and the flow line analysis information such as the number of moving objects detected, the residence time, and the heat map (flow line analysis image) obtained by this flow line analysis process. Use it.

<Area setting deviation detection processing>
In the second embodiment, a configuration example will be described in which a shift of a setting area due to a change in a captured image due to a change in an imaging target is detected. In this case, processing suitable for each case is performed depending on the number of detected events in the captured image.

  FIG. 8 is a flowchart illustrating a first example of region setting shift detection processing in the camera device of the second embodiment. The first example shows an area setting shift detection process when there are relatively many detection events in a captured image. In a camera system that counts the number of people and stays detected at a site where a person constantly appears such as a store, a relatively large number of detection events occur when the person detection is a detection event. The first example is a processing example suitable for such a case.

  The camera apparatus 10-1 determines whether or not it is the timing for determining the occurrence of a shift in area setting in the shift / change detection unit 106 (S31). The determination timing of the region setting deviation is, for example, a deviation determination at every predetermined time or a change in the position of the picked-up image by using a timing such as when a predetermined time such as one hour elapses or when the imaging angle of view is changed by the PTZ mechanism. Time shift determination is possible. At this time, it is assumed that the detection area and the mask area have already been set in the camera device 10-1.

  When the determination timing of the region setting deviation is reached, the camera device 10-1 detects the past predetermined period accumulated in the detection history information accumulation unit 109 in the detection history feature extraction unit 133 of the feature extraction unit 103-1. History information is acquired (S32). Subsequently, the detection history feature extraction unit 133 acquires current detection history information (S33). Next, the camera device 10-1 compares the past and present detection history information in the change extraction unit 162 of the deviation / change detection unit 106 (S34).

  The camera apparatus 10-1 determines whether the deviation / change detection unit 106 has a change in the detection history (S35), and determines that there is a change in the region setting when a change of a predetermined amount or more is detected in the detection history. To do. In this case, the region setting unit 104 performs region setting processing using the current captured image, and stores new region setting information in the region setting information storage unit 105 (S36). Then, the camera apparatus 10-1 transmits the area change detection information and the area setting information from the transmission unit 107 to the server apparatus 20, displays the changed setting area information on the monitor 42, and presents the area setting plan to the user. (S37). The camera apparatus 10-1 receives an instruction input from the server apparatus 20, and performs a region setting change or maintenance process (S38).

  FIG. 9 is a flowchart illustrating a second example of region setting shift detection processing in the camera device of the second embodiment. The second example shows a region setting shift detection process when the number of detection events in a captured image is relatively small. In a camera system that monitors an intruder or a suspicious person, the occurrence frequency of person detection or the like is usually low in a detection area where no person is present, and the occurrence of detection events is relatively low. The second example is a suitable processing example in such a case.

  Similarly to the first example of FIG. 8, the camera apparatus 10-1 determines whether or not it is time to determine the occurrence of a shift in area setting in the shift / change detection unit 106 (S <b> 41). At this time, it is assumed that the detection area and the mask area have already been set in the camera device 10-1. When the determination timing of the region setting shift is reached, the camera device 10-1 causes the feature point extraction unit 132 of the feature extraction unit 103-1 to use a short-term average image or a long-term image as an average image for a predetermined period related to the captured image. A mean image is acquired (S42). The time interval for generating the average image may be set as appropriate. For example, an average image every 10 minutes for the short term and an average image every two hours for the long term are created and used. Subsequently, the feature point extraction unit 132 extracts features such as edges, colors, and luminance from the short-term average image or the long-term average image (S43).

  Next, in the feature point extraction unit 132, the camera device 10-1 acquires the current captured image (S44), and extracts features such as edges, colors, and luminance from the current captured image (S45). Then, in the change extraction unit 162 of the shift / change detection unit 106, the camera device 10-1 compares the image characteristics of the short-term average image or long-term average image with the current captured image (S46).

  The camera apparatus 10-1 determines whether or not there is a change in the image feature in the deviation / change detection unit 106 (S47), and if the change in the image feature is detected by a predetermined amount or more, the region setting is changed. Is determined. In this case, the region setting unit 104 performs region setting processing using the current captured image, and stores new region setting information in the region setting information storage unit 105 (S48). Then, the camera apparatus 10-1 transmits the area change detection information and the area setting information from the transmission unit 107 to the server apparatus 20, displays the changed setting area information on the monitor 42, and presents the area setting plan to the user. (S49). The camera apparatus 10-1 receives an instruction input from the server apparatus 20, and performs processing for changing or maintaining the area setting (S50).

  When an environmental change in the imaging area occurs, such as increase / decrease of structures in the imaging area, movement of installation objects, etc., there is a risk of detection omission and false detection in the initially set detection area and mask area. For example, if there is no structure in the mask area, and there is a possibility that a person may exist or pass through, the mask area is reduced and the detection area is enlarged to prevent detection omission. There is a need. When a relatively large number of detection events occur as in the first example described above, the detection trend such as the number of detections, residence time, heat map, etc. has changed significantly from the previous one by comparing the detection history information. Thus, it is possible to detect a region setting shift, and it is possible to change the setting of the appropriate detection region and mask region according to the current captured image. Further, as in the second example described above, when the occurrence of the detection event is relatively small, the feature point and the position of the region division can be determined by comparing the short-term or long-term average image with the current captured image. When changed, it is possible to detect an area setting shift, and it is possible to change settings of an appropriate detection area and mask area according to the current captured image.

  As described above, in this embodiment, when a setting area shift occurs due to a change in the captured image due to a change in the imaging target, the area setting of the detection area and the mask area is performed by comparison with the detection history information or the average image. It is possible to detect a change, notify the user of the area setting deviation, and change the area setting according to the deviation amount. Therefore, even when the captured image changes due to environmental changes such as layout change, movement, increase / decrease of the target object, the target object can be detected with high accuracy by setting an appropriate region.

  As a site using the camera system of the present embodiment, a store, a factory, a construction site, a nursing site, and the like are assumed. For example, in a system that monitors an accident such as a subject falling from a bed at a nursing care site, a change in the set area is detected and the area setting is detected in response to a bed misalignment or a change in arrangement at the imaging target location. What is necessary is just to notify generation | occurrence | production of deviation | shift. Thereby, it is possible to determine a change in the area where the event should be detected in the monitoring target area in the care site, and it is possible to take measures such as resetting an appropriate detection area according to the current situation.

  In the camera system of the present embodiment, the camera device 10 captures a target region, performs region setting including setting of a detection region for performing detection of the target object in the captured image of the target region, and detects the detection region in the captured image. When a predetermined detection event occurs, the event occurrence is determined and event detection information is transmitted to the server device 20. In addition, the camera device 10 determines whether or not there is a change in region setting at a predetermined determination timing, and transmits region change detection information to the server device 20 when a change in the region setting occurs. The server apparatus 20 acquires the event detection information or the area change detection information transmitted from the camera apparatus 10, and notifies the monitor 42 connected to the server apparatus 20 of the occurrence of the detected event or the change of the area setting. Is displayed.

  As a result, when a region setting change such as a detection region and a mask region occurs in a state where a detection operation for detecting occurrence of a predetermined detection event is activated based on a captured image of the camera device, this region setting is performed. By detecting and notifying this change, it is possible to take measures such as notifying the user of the area setting deviation and changing the area setting according to the deviation amount. The user recognizes the change in the area setting, and manually resets the area such as the detection area according to the shift amount so as to match the current captured image, or the area setting plan generated in the camera device It is possible to update the area setting.

  Further, in the camera system of the present embodiment, the camera device 10 divides the region of the current captured image, and compares the position or area of each region with each region of the captured image divided in the previous region setting. When the difference is greater than or equal to a predetermined value, it is determined that there is a change in the region setting, and the region change detection information is transmitted to the server device 20.

  As a result, in the state where the detection operation is performed by performing region setting using the region division of the captured image, the displacement of the setting region due to the change in the captured image due to the lens position displacement or the angle of view change of the camera device is detected. When this occurs, it is possible to detect a change in the area setting such as the detection area and the mask area and notify the user of the area setting deviation.

  Further, in the camera system of the present embodiment, the camera device 10 extracts feature points in the current captured image, and positions of corresponding feature points compared with the feature points of the captured image extracted in the previous region setting. Is equal to or greater than the threshold value, it is determined that there is a change in the region setting, and the region change detection information is transmitted to the server device 20.

  As a result, in the state in which the detection operation is performed by performing the region setting using the feature point detection in the captured image, the setting region accompanying the change in the captured image due to the lens position shift or the angle of view change of the camera device When a deviation occurs, it is possible to detect a change in the area setting such as the detection area and the mask area and notify the user of the area setting deviation.

  In the camera system of the present embodiment, the camera device 10 acquires detection history information including statistical information of the history detected in the captured image, and compares the previous detection history information with the current detection history information. When there is a change of a predetermined amount or more in the detection history, it is determined that there is a change in the area setting, and the area change detection information is transmitted to the server device 20.

  As a result, the detection history information when the detection trend of the target object such as the number of detections, dwell time, heat map, etc. has changed greatly from the previous with the change of the captured image due to the change of the imaging target, and the setting area has shifted. It is possible to detect a change in the area setting by comparing the two and notify the user of the area setting deviation.

  Further, in the camera system of the present embodiment, the camera device 10 acquires an average image of a captured image for a predetermined period, compares the average image with the current captured image, and changes in the image feature by a predetermined amount or more. If there is a change in the area setting, the area change detection information is transmitted to the server device 20.

  Thereby, when the position of the feature point or the region division changes with the change of the captured image due to the change of the imaging target and the setting region shifts, the change of the region setting is detected by comparison with the average image, The user can be notified of a region setting shift.

  Further, in the camera system of the present embodiment, the camera device 10 performs region setting based on the current captured image to update the region setting information when the region setting changes, and the updated region setting information. Is transmitted to the server device 20, and the server device 20 acquires the region change detection information and the region setting information transmitted from the camera device 10, and notifies the monitor 42 of the occurrence of the region setting change and the updated region. A notification screen including an area setting plan based on the setting information is displayed.

  As a result, the user can recognize the occurrence of a change in the area setting, and can change the area setting to match the current captured image using the area setting plan updated in the camera device.

  In the camera device 10 according to the present embodiment, a target area is imaged, and in the captured image of the target area, area setting including setting of a detection area for performing detection of an object is performed, and predetermined detection is performed in the detection area in the captured image. When an event occurs, the event occurrence is determined and event detection information is generated. At a predetermined determination timing, whether or not there is a change in the region setting is determined. Based on the event detection information or the area change detection information, the notification screen for notifying the occurrence of the detection event or the change of the area setting is displayed on the monitor 42 connected to the camera device 10. As a result, the user is notified of the occurrence of a detection event, and when there is a change in the area setting, the occurrence of an area setting deviation can be notified, and it is possible to deal with changes in the area setting according to the amount of deviation. Become.

  Further, in the camera device 10 of the present embodiment, when a change in area setting occurs, the area setting information is updated based on the current captured image, and the area setting detection information and the updated area setting are updated. Based on the information, the monitor 42 displays a notification screen including a notification of the occurrence of a change in area setting and an area setting plan based on the updated area setting information. As a result, the user can recognize the occurrence of a change in the area setting, and can change the area setting to match the current captured image using the area setting plan updated in the camera device.

  The present invention is defined as a detection region setting method including any one of the region setting for detecting the object by the camera system or the camera device according to the present embodiment and the operation (step) for detecting the shift of the region setting. May be.

  While various embodiments have been described above with reference to the drawings, it goes without saying that the present invention is not limited to such examples. It will be apparent to those skilled in the art that various changes and modifications can be made within the scope of the claims, and these are naturally within the technical scope of the present invention. Understood.

  INDUSTRIAL APPLICABILITY The present invention is useful as a camera system and a camera device that can detect an object with high accuracy by setting an appropriate region even when a captured image changes.

10, 10A, 10B, 10N, 10-1 Camera device 20, 210 Server device 30 Recorder 41, 221 Input device 42, 222 Monitor 70, 300 Network 100, 100A, 100B On-site 101 Imaging unit 102 Image input unit 103, 103- DESCRIPTION OF SYMBOLS 1 Feature extraction part 104 Area | region setting part 105 Area | region setting information storage part 106 Deviation / change detection part 107 Transmission part 108 Reception part 131 Area division part 132 Feature point extraction part 133 Detection history feature extraction part 161 Deviation determination part 162 Change extraction part 200 Administration headquarters

Claims (8)

A camera system in which a camera device and a server device are connected to each other,
The camera device is
Image the target area,
In the captured image of the target area, perform area setting including setting of the detection area for executing detection of the object,
When a predetermined detection event occurs in the detection area in the captured image, the event occurrence is determined and event detection information is transmitted to the server device,
At a predetermined determination timing, the presence / absence of a change in the region setting is determined, and when the change in the region setting occurs, the region change detection information is transmitted to the server device,
The server device
Obtain the event detection information or the area change detection information transmitted from the camera device,
On the monitor connected to the server device, a notification screen for notifying the occurrence of the detection event or the change in the area setting is displayed.
Camera system. The camera system according to claim 1,
The camera device is
When the region of the current captured image is divided and the difference in position or area of each region is equal to or greater than a predetermined value compared to each region of the captured image divided in the previous region setting, the region setting It is determined that there is a change, and the area change detection information is transmitted to the server device.
Camera system. The camera system according to claim 1,
The camera device is
When the feature point in the current captured image is extracted, and the error of the position of the corresponding feature point is greater than or equal to the threshold value compared to the feature point of the captured image extracted in the previous region setting, the change in the region setting Determining that there is, and transmitting the region change detection information to the server device,
Camera system. The camera system according to claim 1,
The camera device is
When the detection history information including statistical information of the history detected in the captured image is acquired, and the previous detection history information is compared with the current detection history information, and the detection history has a predetermined amount or more, It is determined that there is a change in area setting, and the area change detection information is transmitted to the server device.
Camera system. The camera system according to claim 1,
The camera device is
An average image for a predetermined period related to the captured image is acquired, and when the average image and the current captured image are compared and there is a change of a predetermined amount or more in image characteristics, it is determined that there is a change in the region setting, Transmitting the region change detection information to the server device;
Camera system. The camera system according to any one of claims 1 to 5,
The camera device is
When a change in the region setting occurs, the region setting is performed based on the current captured image to update the region setting information, and the updated region setting information is transmitted to the server device,
The server device
The region change detection information and the region setting information transmitted from the camera device are acquired, and the monitor includes a notification of the occurrence of the region setting change and a region setting plan based on the updated region setting information. Display a notification screen,
Camera system. A camera device for imaging a target area,
In the captured image of the target area, perform area setting including setting of the detection area for executing detection of the object,
When a predetermined detection event occurs in the detection region in the captured image, event occurrence is determined and event detection information is generated,
At a predetermined determination timing, it is determined whether or not there is a change in the region setting, and when a change in the region setting occurs, region change detection information is generated,
Based on the event detection information or the area change detection information, a notification screen for notifying the occurrence of the detection event or the change in the area setting is displayed on a monitor connected to the camera device.
Camera device. The camera device according to claim 7,
When the change in the area setting occurs, update the area setting information by performing the area setting based on the current captured image,
Based on the region change detection information and the updated region setting information, a notification screen including a notification of the occurrence of the region setting change and a region setting plan based on the updated region setting information is displayed on the monitor. ,
Camera device.

Images