JP6495696B2 - Image collecting apparatus, image collecting method, and computer program - Google Patents

Description

  Embodiments described herein relate generally to an image collection apparatus, an image collection method, and a computer program.

One common method for detecting a moving object from an image is an inter-frame difference method for detecting a moving object based on a change in luminance of the image. The inter-frame difference method is a method of acquiring a difference between images acquired continuously and detecting a subject in a region where the change has occurred as a moving object. A technique for detecting a person based on the result of such moving object detection has been proposed.
However, when a camera is installed in an office or the like, the luminance of an image may change due to changes in the brightness of the space caused by external light or illumination as well as human movement. Therefore, there is a possibility that a person is erroneously detected even though no person actually exists. In order to solve this problem, a technique has been proposed in which a background image of a space to be detected is stored in advance, and whether or not an area having a luminance change is a background by comparing the acquired image with the background image. . However, when such a conventional technique is applied to a space such as an office where the brightness changes, it is necessary to update the reference background image as needed according to the change in the brightness.

  However, it is technically difficult to update to an appropriate background image as needed according to changes in brightness. Therefore, a method for identifying whether or not a moving object is a background based on dictionary information indicating characteristics of a background image has been studied. Using dictionary information generated based on background images captured in different brightness situations, it is possible to identify whether or not the change in brightness is due to a change in brightness.

  The accuracy of background identification using dictionary information depends on the quality of the dictionary information. The quality of the dictionary information depends on how many patterns of dictionary information are generated based on the background image of the pattern. Therefore, in order to generate high quality dictionary information, a very large number of background images are required, and a lot of labor may be required to collect the background images.

Japanese Patent No. 4619082 Japanese Patent No. 4852159 Japanese Patent No. 5349622

  The problem to be solved by the present invention is to provide an image collection apparatus, an image collection method, and a computer program that can efficiently collect background images necessary for generating dictionary information.

  The image collection device according to the embodiment includes an image storage unit, an imaging control unit, and an attribute assigning unit. The image storage unit stores an image in which a space for detecting a person is captured. The imaging control unit controls the timing at which the imaging unit that images the space and acquires the image of the space images the space. The attribute assigning unit acquires the image of the space from the imaging unit, and stores the acquired image in the image storage unit in association with attribute information regarding acquisition of the image.

The figure which shows the usage example of the image sensor 1. FIG. The system block diagram which shows the structure of an apparatus control system provided with the terminal 7 for adjustment of 1st Embodiment. 2 is a functional block diagram showing a functional configuration of the image sensor 1. FIG. The flowchart which shows the flow of the process in which the image sensor 1 detects a person from an image. The functional block diagram which shows the function structure of the terminal 7 for adjustment of 1st Embodiment. The functional block diagram which shows the function structure of the terminal 7a for adjustment of 2nd Embodiment. The functional block diagram which shows the function structure of the terminal 7b for adjustment of 3rd Embodiment. The figure which shows the specific example of task lighting and ambient lighting. The figure which shows the specific example of task ambient control. The functional block diagram which shows the function structure of the terminal 7c for adjustment of 4th Embodiment. The functional block diagram which shows the detail of a function structure of the imaging control part 75c. The figure which shows the example which acquires a background image for every area where a person was absent.

  Hereinafter, an image collection device, an image collection method, and a computer program according to embodiments will be described with reference to the drawings.

(First embodiment)
FIG. 1 is a diagram illustrating a usage example of the image sensor 1.
FIG. 1 shows an example in which the image sensor 1 is used to control equipment on an office floor. In the case of the example in FIG. 1, the lighting device 20 and the air conditioning device 30 are devices to be controlled. The image sensor 1 is installed on the ceiling 10 of the office floor and images the office floor. The image sensor 1 acquires environment information and person information from the captured image. The environment information is information regarding the environment of the imaging target space (hereinafter referred to as “target space”). For example, the environmental information is information indicating the illuminance or temperature of the office. The person information is information about a person in the target space. For example, the person information is information indicating the presence or absence of a person, the number of people, the behavior of the person, the amount of activity of the person, and the like. In order to acquire person information, the image sensor 1 analyzes the acquired image and detects a person. The image sensor 1 transmits the acquired environmental information and person information to a control device that controls the lighting device 20 and the air conditioning device 30. The control device generates control information for controlling the lighting device 20 and the air conditioning device 30 based on the environmental information and the person information acquired by the image sensor 1. The control device transmits the generated control information to the lighting device 20 and the air conditioning device 30. The lighting device 20 and the air conditioning device 30 operate the own device based on the control information transmitted from the control device. By such control, device control based on environmental information and personal information is realized.

  For example, when information indicating the presence or absence of a person is acquired as person information, the control device turns on air conditioning and lighting in an area where there is a person, and turns off air conditioning and lighting in an area where there is no person, or Air conditioning and lighting can be controlled to reduce output. In addition, when there is a person, control that turns on task lighting is also conceivable. In addition, control such as changing the dimming rate of the ambient lighting according to a place where a person is detected, such as a desk or a passage, can be considered.

  Also, for example, when information indicating the amount of activity of a person is acquired as personal information, the control device determines that there are many people who are doing desk work when the amount of activity is small, and reduces the output of air conditioning. When the amount is large, it can be determined that the person is actively active and the air conditioning can be controlled to increase the output of the air conditioning. Further, for example, when information indicating a person distribution is acquired as the person information, the lighting can be controlled so as to change the dimming rate of the lighting in the floor according to the person distribution.

  When acquiring person information using an image sensor as described above, it is necessary to detect a person from an image. Conventionally, there has been proposed a technique for detecting a person from an image by comparing an image of a region extracted by an inter-frame difference method with a background image acquired in advance. However, in a space such as an office where the brightness of the detection target changes, the background image changes greatly due to the influence of lighting ON or OFF, the incidence of external light, and the like. Therefore, when it is attempted to apply the conventional technique to such a space, it is necessary to update the background image as needed according to the change in the brightness of the space to be detected, which is technically difficult. Therefore, a method for identifying whether or not a moving object is a background based on dictionary information indicating the characteristics of a background image has been studied. Using dictionary information generated based on background images captured in different brightness situations, it is possible to identify whether or not the change in brightness is due to a change in brightness.

  The accuracy of background identification using dictionary information depends on the quality of the dictionary information. The quality of the dictionary information depends on how many patterns of dictionary information are generated based on the background image of the pattern. Therefore, in order to generate high quality dictionary information, a very large number of background images are required, and a lot of labor may be required to collect the background images. Therefore, the device control system of the embodiment includes an adjustment terminal that controls collection of background images based on a predetermined condition.

FIG. 2 is a system configuration diagram illustrating a configuration of a device control system including the adjustment terminal 7 according to the first embodiment.
The device control system of FIG. 2 includes a plurality of image sensors 1-1 to 1-3. The image sensors 1-1 to 1-3 transmit personal information and environment information (hereinafter referred to as “detection information”) acquired from the images to the gateway server 3 via the network hub 2. The gateway server 3 transmits the person information and environment information transmitted from each image sensor 1 to a BEMS (Building Energy Management System) 4, a device control device 5, a visualization device 6, an adjustment terminal 7, and the like.

  The BEMS 4 acquires information indicating the energy used in the building and the indoor environment from a sensor or the like, and performs analysis and diagnosis to make use of this information for energy saving.

  The device control device 5 generates control information for optimally controlling the device to be controlled based on the detection information. The device control apparatus 5 controls the device to be controlled by transmitting the generated control information. A device to be controlled by the device control device 5 is a device such as an air conditioner, a lighting device, and an elevator, for example.

  The visualization device 6 is a device that visualizes information of the device control system. For example, the visualization device 6 obtains the results of analysis and diagnosis by the BEMS 4 and visualizes the energy used in the building, the indoor environment, and the like.

  The adjustment terminal 7 (image collection device) is a terminal that communicates with the image sensor 1 and that has an adjustment program installed for performing various settings and adjustments of the image sensor 1. For example, the adjustment terminal 7 is an information terminal such as a PC (Personal Computer), a smartphone, or a tablet. The adjustment program may be installed in a device other than the adjustment terminal 7 as long as it can communicate with the image sensor 1.

  The network hub 2 and the adjustment terminal 7 are connected to the device network 40, and the BEMS 4, the device control device 5, and the visualization device 6 are connected to the control network 50. For example, the control network 50 is a network such as Ethernet (registered trademark), and the control network 50 is a BACnetIP network. Communication between the device connected to the device network 40 and the device connected to the control network 50 is relayed by protocol conversion of the gateway server 3.

  The device network 40 and the control network 50 may be different networks as long as communication between the networks is possible. For example, the device network 40 and the control network 50 may be a network such as industrial Ethernet (registered trademark) standardized for a specific application, or may be a network of a unique protocol. The device network 40 and the control network 50 may be the same network.

FIG. 3 is a functional block diagram showing a functional configuration of the image sensor 1.
The image sensor 1 includes a CPU (Central Processing Unit), a memory, an auxiliary storage device, and the like connected by a bus, and executes an image sensor program. The image sensor 1 functions as a device including the communication unit 11, the imaging unit 12, the image storage unit 13, the dictionary information storage unit 14, the moving object detection unit 15, the moving object determination unit 16, and the person determination unit 17 by executing the image sensor program. . Note that all or part of the functions of the image sensor 1 may be realized using hardware such as an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA). The image sensor program may be recorded on a computer-readable recording medium. The computer-readable recording medium is, for example, a portable medium such as a flexible disk, a magneto-optical disk, a ROM, a CD-ROM, or a storage device such as a hard disk built in the computer system. The image sensor program may be transmitted via a telecommunication line.

  The communication unit 11 is configured using a communication interface for connecting the own device to the network hub 2. The communication unit 11 communicates with various devices connected to the device network 40 and the control network 50 via the network hub 2.

  The imaging unit 12 is configured using an imaging device such as a camera. The imaging unit 12 is installed at a position and orientation at which detection information about the device to be controlled can be acquired. The imaging unit 12 captures a space corresponding to the installation position and orientation, and acquires image data. The imaging unit 12 stores the acquired image data in the image storage unit 13.

  The image storage unit 13 and the dictionary information storage unit 14 are configured using a storage device such as a magnetic hard disk device or a semiconductor storage device. The image storage unit 13 stores the image data acquired by the imaging unit 12. The dictionary information storage unit 14 stores dictionary information used for moving object determination. The dictionary information is information indicating correspondence between the feature amount extracted from the background image and various features of the background. The dictionary information is generated based on a pre-captured image (hereinafter referred to as “pre-image”) and stored in the dictionary information storage unit 14 in advance. Hereinafter, this generation and storage of dictionary information is referred to as learning.

  The moving object detection unit 15 detects a moving object candidate that is estimated to be a moving object based on a plurality of images obtained by imaging the space to be detected. As a method for detecting moving object candidates, inter-frame difference, optical flow, template matching, and the like can be used.

  The moving object determination unit 16 determines whether the moving object candidate detected by the moving object detection unit 15 is a moving object based on the dictionary information. Specifically, the moving object determination unit 16 determines whether the moving object candidate is a background based on the characteristics of the background image indicated by the dictionary information. When it is determined that the moving object candidate is not the background, the moving object determination unit 16 determines that the moving object candidate is a moving object. As a method for determining whether or not a moving object candidate is the background, a neural network, SVM (Support Vector Machine), k neighborhood classifier, Bayesian classification, or the like can be used.

  The person determination unit 17 (person detection unit) determines whether or not the moving object determined by the moving object determination unit is a person.

FIG. 4 is a flowchart showing a flow of processing in which the image sensor 1 detects a person from an image.
First, the imaging unit 12 captures a space to be detected and acquires image data (step S101). The imaging unit 12 stores the acquired image data in the image storage unit 13 in association with information indicating the timing at which the image data was acquired.

  The moving object detection unit 15 acquires image data from the image storage unit 13. At this time, the moving object detection unit 15 acquires image data in the order of the acquired timing. The moving object detection unit 15 detects moving object candidates based on the acquired image data (step S102). For example, the moving object detection unit 15 detects a moving object candidate based on the inter-frame difference of the acquired image. Then, the moving object detection unit 15 outputs information indicating the area where the moving object candidate is detected (hereinafter referred to as “moving object candidate area”) to the moving object determination unit 16 (step S103).

  The moving object determination unit 16 calculates the feature amount of the image of the moving object candidate region output from the moving object detection unit 15. The feature amount extracted here is a feature amount related to a luminance change such as a cumulative difference described in Patent Document 2 or a feature related to a luminance distribution such as CoHOG (Co-occurrence Histograms of Oriented Gradients) described in Patent Document 3. An amount may be used. The moving object determination unit 16 calculates the similarity between the image of the moving object candidate region and the background image based on the calculated feature amount and dictionary information (step S104). The moving object determination unit 16 determines whether the moving object candidate is a moving object based on the calculated similarity. When it is determined that the moving object candidate is a moving object, the moving object determination unit 16 sets the moving object candidate area as an area where the moving object is detected (hereinafter referred to as “moving object area”), and information indicating the moving object area is a human determination unit. 17 (step S105).

  The person determination unit 17 determines whether the moving object is a person based on the moving object region image output from the moving object determination unit 16 (step S106).

  It should be noted that feature amount extraction and background / moving object identification processing may be performed in units of pixels, or may be performed in units of regions extracted from an image. In this case, feature amount extraction and identification processing may be performed in units of regions including the extracted regions, such as circumscribed rectangles.

FIG. 5 is a functional block diagram illustrating a functional configuration of the adjustment terminal 7 according to the first embodiment.
The adjustment terminal 7 includes a CPU, a memory, an auxiliary storage device, and the like connected by a bus and executes an adjustment program. The adjustment terminal functions as a device including the communication unit 71, the storage unit 72, the image data acquisition unit 73, the attribute assignment unit 74, and the imaging control unit 75 by executing the adjustment program. Note that all or part of the functions of the adjustment terminal 7 may be realized using hardware such as an ASIC, PLD, or FPGA. The adjustment program may be recorded on a computer-readable recording medium. The computer-readable recording medium is, for example, a portable medium such as a flexible disk, a magneto-optical disk, a ROM, a CD-ROM, or a storage device such as a hard disk built in the computer system. The adjustment program may be transmitted via a telecommunication line.

  The communication unit 71 is configured using a communication interface for connecting the own apparatus to the device network 40. The communication unit 71 communicates with various devices connected to the device network 40 and the control network 50 via the network hub 2 or the gateway server 3.

  The storage unit 72 is configured using a storage device such as a magnetic hard disk device or a semiconductor storage device, and stores image information. The image information is information in which image data acquired by the imaging unit 12 is associated with attribute information regarding acquisition of the image data. The image information is associated by the attribute adding unit 74 adding the attribute information to the image data.

  The image data acquisition unit 73 receives a notification (hereinafter referred to as “imaging instruction notification”) that a background image capturing instruction has been given to the image sensor 1, and acquires a background image from the image sensor 1. This notification is performed by the imaging control unit 75. The image data acquisition unit 73 stores the acquired image data in the storage unit 72.

  The attribute assigning unit 74 receives an imaging instruction notification from the imaging control unit 75, and acquires attribute information to be added to the acquired image data based on the imaging instruction (that is, in synchronization with the imaging of the imaging unit 12). . Specifically, the attribute information is imaging setting information indicating settings of the imaging unit 12 regarding the imaging operation of the background image, or space state information indicating information regarding the state of the imaging target space at the time of imaging. For example, the imaging setting information is camera parameters such as shutter speed, gain, and white balance. Further, the spatial state information is information such as the above-described person information, environment information, person information, or intermediate data generated in the acquisition of environment information. The attribute assigning unit 74 acquires the attribute information from the image sensor 1. The attribute assigning unit 74 associates the acquired attribute information with the image data of the background image stored in the storage unit 72 to generate image information. The attribute assigning unit 74 stores the generated image information in the storage unit 72.

  The imaging control unit 75 instructs the image sensor 1 to capture a background image. For example, the imaging control unit 75 instructs the image sensor 1 to capture a background image in response to an instruction transmitted from another device or an instruction input from an input device such as a keyboard or a mouse. The imaging control unit 75 notifies the image data acquisition unit 73 and the attribute assignment unit 74 that an imaging instruction has been given to the image sensor 1 by an imaging instruction notification.

  The adjustment terminal 7 according to the first embodiment configured as described above instructs the image sensor 1 to acquire a background image, and acquires a background image captured according to the instruction from the image sensor 1. Then, the adjustment terminal 7 adds attribute information to the acquired background image and accumulates it. By providing such a function, the adjustment terminal 7 can reduce the labor required for collecting a large amount of preliminary images necessary for generating dictionary information used by the image sensor 1. Further, as described above, the background image and the attribute information are acquired in association with each other, so that information necessary for generating dictionary information can be acquired collectively.

(Second Embodiment)
The timing at which the background image is collected is preferably a timing at which there is no person who can cause the background image to change. For this reason, for example, when collecting a background image of a building or the like, it is generally performed at the time of adjustment before a person moves in. However, in the case of a large-scale building, thousands of image sensors may be installed, and if the coordinator instructs each image sensor to acquire an image, the work efficiency decreases. Therefore, the adjustment terminal 7a according to the second embodiment includes a configuration that automatically collects background images based on conditions set in advance regarding acquisition of background images.

FIG. 6 is a functional block diagram illustrating a functional configuration of the adjustment terminal 7a according to the second embodiment.
The adjustment terminal 7a of the second embodiment is provided with a storage unit 72a instead of the storage unit 72, and an adjustment terminal 7 of the first embodiment is provided with an imaging control unit 75a instead of the imaging control unit 75. And different. Other functional units are the same as those of the adjustment terminal 7. Therefore, in FIG. 6, functional units other than the storage unit 72a and the imaging control unit 75a are denoted by the same reference numerals as those in FIG.

The storage unit 72a is different from the storage unit 72 in the first embodiment in that it stores imaging condition information (acquisition condition information) indicating conditions related to imaging of a background image in addition to image information. For example, the imaging condition information is information indicating the start time of image collection, the time required for image collection, the target image sensor 1, and the like.
The imaging control unit 75a controls the timing at which the image sensor 1 captures the background image based on the imaging condition information.

  The adjustment terminal 7a of the second embodiment configured as described above can automatically collect background images by controlling the image sensor 1 based on preset imaging conditions. Therefore, it is possible to improve the efficiency of collecting a large amount of background images.

  Note that the above-described setting of the imaging condition information may be performed in any manner. For example, the imaging control unit 75a may acquire a file including imaging condition information from another device or a storage medium. In addition, the imaging control unit 75a may display a setting screen for inputting imaging conditions on the display unit of its own apparatus, and generate imaging condition information based on a user input. Further, the setting screen may be configured such that the user can directly input an instruction relating to collection of the background image.

  When the adjustment terminal 7 a has such a function, the user can remotely control the background image collection operation using the image sensor 1. For example, the user can issue an instruction to capture a background image while visually confirming the target image sensor 1.

(Third embodiment)
The accuracy of identifying the moving object and the background by the image sensor 1 depends on the quality of dictionary information used for identification. Therefore, high-quality dictionary information is required to accurately identify moving objects and backgrounds. The quality of dictionary information is determined by how many patterns of dictionary information are generated based on background images. For this reason, when considering the influence of brightness on the background image, in order to generate high-quality dictionary information, background images captured in different brightness situations are required. However, much labor is required to acquire a background image under such imaging conditions. For this reason, the adjustment terminal 7b according to the third embodiment includes a configuration that controls a device that affects the brightness of the space, such as a lighting device, and changes the space to be imaged to a state according to the imaging conditions.

FIG. 7 is a functional block diagram illustrating a functional configuration of the adjustment terminal 7b according to the third embodiment.
The adjustment terminal 7b of the third embodiment includes a storage unit 72b instead of the storage unit 72a, a point including an imaging control unit 75b instead of the imaging control unit 75a, a state acquisition unit 76, and a control signal generation unit 77. Is different from the adjustment terminal 7a of the second embodiment in that Other functional units are the same as those of the adjustment terminal 7a. Therefore, in FIG. 7, functional units other than the storage unit 72b, the imaging control unit 75b, the state acquisition unit 76, and the control signal generation unit 77 are denoted by the same reference numerals as those in FIG.

  In addition to the image information and the imaging condition information, the storage unit 72b stores facility state information indicating the state of various facilities related to the detection target space.

  The state acquisition unit 76 (equipment state acquisition unit) periodically acquires the equipment state information and stores it in the storage unit 72b. For example, the state acquisition unit 76 acquires equipment state information from the BEMS 40.

  The imaging control unit 75b controls imaging of the background image by the image sensor 1 based on the imaging condition information. Note that the imaging condition information of the present embodiment includes conditions relating to the state of each facility (hereinafter referred to as “imaging state”) when a background image is acquired. The imaging control unit 75b determines the imaging state of each facility based on the imaging condition information. The imaging control unit 75b notifies the control signal generation unit 77 of the determined imaging state of each facility, thereby changing the imaging target space to a state corresponding to the imaging condition. The imaging control unit 75b determines the current state of each facility based on the facility state information, and instructs the image sensor 1 to capture a background image at the timing when the state of each facility becomes the imaging state.

  The control signal generation unit 77 (device control unit) generates a control signal for controlling the operation of each facility related to the space to be detected. Specifically, the control signal generation unit 77 acquires the imaging state of the equipment to be controlled from the imaging control unit 75b, and generates a control signal for changing the state of each facility to the imaging state. The control signal generation unit 77 transmits the generated control signal to each facility to be controlled.

  Hereinafter, control of various facilities related to the space to be imaged will be described using control of task illumination and ambient illumination as an example.

FIG. 8 is a diagram illustrating specific examples of task lighting and ambient lighting.
Building lighting equipment includes, for example, ambient lighting installed on the ceiling and task lighting installed on a desk by an operator as needed. The task lighting is a lighting device for securing the illuminance for visual work, and the ambient lighting is the lighting device for securing the illuminance of the entire region where the visual work is performed. Control of these ambient lighting and task lighting is called “task / ambient control”. Task / ambient control is a method of controlling different lighting devices under different conditions by dividing a space to be controlled into a task region in which a person exists and an ambient region in other spaces. In the task / ambient control, a necessary illuminance is generally given to the task area and a lower illuminance is given to the other peripheral areas.

  In the case of the example of FIG. 8, task / ambient control of the lighting device is performed according to the detection result of the sensor 100 that detects the presence or absence of a person. The lighting equipment installed on the ceiling indicated by reference numerals 101-1 to 101-4 is ambient lighting, and the lighting equipment installed on each desk indicated by reference numerals 102-1 and 102-2 is task lighting. For example, in this case, the task lighting 102-1 of the desk where the person is working is controlled so as to ensure the illuminance necessary for the work, and the task lighting 102-2 of the desk where there is no person is turned off. In addition, the ambient lights 101-1 to 101-4 are controlled so that the brightness of the surrounding environment is ensured. In general, the ambient lighting is controlled to have an illuminance that is 1/2 to 1/3 of the task lighting.

FIG. 9 is a diagram illustrating a specific example of task / ambient control.
FIG. 9 is a diagram showing an office layout. Ambient lights 200-1 to 200-4 are installed on the office ceiling of FIG. 9, and desks 201-1 to 201-8 are installed on the floor. In this case, for example, when it is determined by the image sensor 1 that there are people on the desks 201-3 and 201-6, the task lighting and the ambient lighting of the desks 201-3 and 201-6 are performed by the task ambient control. 200-2 and 200-3 are lit.

  In an environment in which such task / ambient control is performed, the manner in which the background image is projected varies greatly depending on the location of the lighting to be turned on, the number of lights to be turned on, the dimming rate of each lighting, and the like. Therefore, the adjustment terminal 7b acquires the background image in the image sensor 1 after controlling the lighting device so as to realize the state of the lighting device that may occur in the task / ambient control (hereinafter referred to as “control pattern”). Let For example, the adjustment terminal 7b realizes a state in which some lighting devices are turned on as shown in FIG. 9 or a state in which all lighting devices are turned on, and acquires a background image captured in each state. When a plurality of image sensors 1 are installed in a space to be imaged, the adjustment terminal 7b may realize a control pattern with equipment corresponding to each image sensor 1 or a plurality of adjacent image sensors 1. You may implement | achieve a control pattern with the equipment corresponding to. The state of each device in each control pattern is set in advance in the imaging condition information, and each control pattern is realized by the control signal generation unit 77.

  The adjustment terminal 7b according to the third embodiment configured as described above acquires the background image in the image sensor 1 after controlling the equipment related to the brightness of the space to be imaged to be in the state indicated by the imaging condition information. Instruct. Since the adjustment terminal 7b has such a function, background image collection can be controlled more flexibly, and background image collection work can be performed more efficiently.

  Note that if the brightness intensity of the space to be imaged is too strong, there is a possibility that an imaging failure such as overexposure or blackout may occur in the acquired background image. Therefore, the adjustment terminal 7b may be configured to reacquire a background image as necessary when an imaging failure occurs. In this case, for example, the image data acquisition unit 73 checks whether or not imaging failure has occurred in the acquired image data. When the imaging failure has occurred, the image data acquisition unit 73 notifies the imaging control unit 75b of the image data in which the imaging failure has occurred. The imaging control unit 75b calculates camera parameters that suppress imaging defects based on the imaging setting information of the notified image data. The imaging control unit 75b transmits the calculated camera parameters to the image sensor 1 and instructs to reacquire a background image.

  Hereinafter, modifications of the adjustment terminal 7b according to the third embodiment will be described.

  In order to accurately identify the moving object and the background, it is necessary to consider the effect of brightness due to external light in addition to the effect of brightness due to illumination. Therefore, in order to generate high-quality dictionary information, a background image captured in a state where external light is incident is necessary. Therefore, the adjustment terminal 7b may include a configuration capable of creating a situation in which external light is incident by controlling the blind according to the position of the sun and the weather.

  In this case, the imaging condition information indicates a condition relating to a blind state in the imaging target space. For example, the imaging condition information indicates how much the blind is to be opened according to the position of the sun and the weather. The imaging control unit 75b acquires weather information indicating the weather of the day from an external system or device. In addition, the imaging control unit 75b calculates the position of the sun at an arbitrary date and time observed from the imaging target space, based on position information such as the position and height of the imaging target space and the prediction model of the sun position. . Then, the imaging control unit 75b determines the imaging state of the blind device based on the calculated sun position information and the acquired weather information. The imaging control unit 75b notifies the control signal generation unit 77 of the determined blind imaging state, thereby changing the blind state to the imaging state.

  For example, when the space in the building is a space to be imaged, the imaging control unit 75b estimates the location where sunlight hits the building based on the sun position at that time and the weather of the day, The control signal generation unit 77 is instructed to open the blind in the place where the light hits. The imaging control unit 75b instructs the image sensor 1 to acquire a background image after the blind is opened.

  By providing such a function, the adjustment terminal 7b calculates the sun position based on the position of the sun and the weather of the day, and controls the blind device in a place corresponding to the sun position, so that sunlight enters. Get the background image of the state to be. By providing such a function, the adjustment terminal 7b can efficiently acquire a background image in a situation where sunlight is incident.

  In this case, the imaging control unit 75b may change the blind opening / closing amount and the opening / closing angle according to the incident angle of sunlight. By performing such control, the adjustment terminal 7b can acquire a background image captured in a situation where external light is incident in various patterns.

  Note that such control is to acquire more background images captured in different patterns depending on brightness. Therefore, how to control the blind based on the weather information and the sun position information may be determined by an arbitrary standard. In the above example, the blind opening control is performed to create a situation in which external light is incident on the space. For example, on the contrary, the blind closing control is performed to create a situation in which no external light is incident. It may be broken. Further, control for opening the blinds may be performed even in a situation where there is not much external light.

  In addition, the imaging control unit 75b generates a schedule for acquiring a background image based on imaging conditions, the sun position, the weather of the day or week, and acquires the background image by controlling the blind device based on the generated schedule. It may be configured to. By performing such control, the adjustment terminal 7b can efficiently collect background images in a situation where there is a time constraint such as on-site adjustment of a building.

(Fourth embodiment)
As described above, the generation of high-quality dictionary information requires a background image captured under various conditions. However, there are many restrictions on the time for acquiring such a background image. For example, in the local adjustment performed during the construction of a building, there is a possibility that sufficient time cannot be secured due to the balance with other construction. In addition, after the building is completed, it is more difficult to secure sufficient adjustment time after a person moves in. For this reason, the adjustment terminal 7c according to the fourth embodiment has a configuration that determines the priority for obtaining the background image and collects the background image based on the priority.

FIG. 10 is a functional block diagram illustrating a functional configuration of the adjustment terminal 7c according to the fourth embodiment.
The adjustment terminal 7c according to the fourth embodiment is different from the adjustment terminal 7b according to the third embodiment in that the adjustment terminal 7c includes an imaging control unit 75c instead of the imaging control unit 75b. Other functional units are the same as those of the adjustment terminal 7b. Therefore, in FIG. 10, functional units other than the imaging control unit 75c are denoted by the same reference numerals as those in FIG.

FIG. 11 is a functional block diagram illustrating details of the functional configuration of the imaging control unit 75c.
The imaging control unit 75c includes a required time calculation unit 751 and a priority determination unit 752.
The required time calculation unit 751 calculates the required time required to collect the background image under each imaging condition based on the imaging condition information. For example, the required time calculation unit 751 acquires a predetermined number of background images based on the number of image sensors 1 from which a background image is acquired and the time required to acquire the background image by one image sensor 1. Calculate the time required for. Further, for example, the required time calculation unit 751 controls each facility based on the number of facilities to be controlled by the control signal generation unit 77, the time required for transmission / reception of control signals, the time required for each control, and the like. The required time may be calculated. The required time calculation unit 751 calculates the required time for collecting the background image under each imaging condition by calculating each required time. The required time calculation unit 751 outputs information indicating the calculated required time for each imaging condition to the priority determination unit 752.

  The priority determination unit 752 acquires information indicating the time required for collecting the background image of each imaging condition from the required time calculation unit 751. The priority determination unit 752 determines the priority of each imaging condition based on the acquired time required for each imaging condition. For example, the priority determination unit 752 sets a high priority for imaging conditions that can be acquired within the time limit, and sets a low priority for imaging conditions that exceed the time limit. In addition, for example, the priority determination unit 752 sets a high priority for an imaging condition in which the time required for changing the state of each facility is short, and lowers a priority for an imaging condition in which the required time for changing the state of each facility is long. It may be set. Further, for example, the priority determination unit 752 may set the priority higher in the order from the shortest time required for each imaging condition.

  The adjustment terminal 7c of the fourth embodiment configured as described above determines the priority for acquiring the background image based on various time required for acquiring the background image under each imaging condition, The background images are collected in the order of the determined priority. By providing such a function, the adjustment terminal 7c can efficiently capture a background image under various conditions.

  According to at least one embodiment described above, an image storage unit that stores an image in which a space for detecting a person is captured, and an imaging unit that captures the space and obtains an image of the space are stored in the space. An imaging control unit that controls the timing of imaging, and an attribute adding unit that acquires an image of the space from the imaging unit, and stores the acquired image in the image storage unit in association with attribute information related to the acquisition of the image , It is possible to efficiently collect background images necessary for generating dictionary information.

  Hereinafter, modifications of the adjustment terminal according to the above embodiment will be described.

  Different conditions may be set as the background image capturing condition depending on the location of the space to be imaged. For example, in a building, imaging conditions may be set according to places such as office rooms, hallways, and elevator halls.

  Further, the dictionary information necessary for the image sensor may differ depending on the intended use of the space to be imaged, the layout, the required detection accuracy, and the like. For example, compared to the office room, there are more pedestrians in the hallway and more people are standing and waiting in the elevator hall. In such a case, the area of the moving object region detected from the image and the time interval of movement of the moving object are different. Therefore, the adjustment terminal may adjust the amount of the background image according to the property of the space to be identified.

  Further, the control pattern of the lighting device and the way of taking in external light differ depending on the usage application of the space to be imaged. For example, the brightness of the space changes in accordance with the use of a projector in a conference room, and in the entrance hall in accordance with an image captured on an electric bulletin board or a large television. In such a case, conditions according to the characteristics of the individual spaces may be set as the background image capturing conditions. In this case, the imaging control unit instructs the control signal generation unit to control the projector, the electric bulletin board, and the large television, and acquires a background image for a space having different brightness depending on these devices.

  In addition, it is desirable to obtain the background image in an environment where no person is present. Therefore, the adjustment terminal may be configured to acquire detection information from the image sensor 1 and acquire an image at a timing when no person is present. Also, in a large room where a plurality of image sensors are installed, the adjustment terminal acquires a background image for each area where a person is absent, as shown in FIG. You may control as follows. The collection of background images by such control can be applied not only during on-site adjustment before building delivery, but also during operation after building delivery. If such a background image is acquired, the image sensor 1 can be made to learn the background image during operation of the building as needed.

  Although several embodiments of the present invention have been described, these embodiments are presented by way of example and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the spirit of the invention. These embodiments and their modifications are included in the scope and gist of the invention, and are also included in the invention described in the claims and the equivalents thereof.

DESCRIPTION OF SYMBOLS 1, 1-1, 1-2, 1-3 ... Image sensor, 11 ... Communication part, 12 ... Imaging part, 13 ... Image storage part, 14 ... Dictionary information storage part, 15 ... Moving body detection part, 16 ... Moving body determination , 17... Human determination unit, 2... Network hub, 3. Gateway server, 4... BEMS (Building Energy Management System), 5 .. device control device, 6 .. visualization device, 7, 7a, 7b, 7c. , 71 ... Communication section, 72, 72a, 72b ... Storage section, 73 ... Image data acquisition section, 74 ... Attribute assignment section, 75, 75a, 75b, 75c ... Imaging control section, 751 ... Required time calculation section, 752 ... Priority Degree calculation section, 76 ... status acquisition section, 77 ... control signal generation section, 10 ... ceiling, 20 ... lighting equipment, 30 ... air conditioning equipment, 40 ... equipment network, 50 ... control network, 100 ... sensor, 101-1 to 101 -4 ... Ambi Cement lighting, 102-1, 102-2 ... task lighting, 200-1～200-4 ... ambient lighting, 201-1～201-8 ... desk

Claims (12)

An image collecting device for collecting a background image of the moving object used in a moving object detecting device for detecting a moving object from an image,
An image storage unit for storing the image space Target is captured,
A detection unit for detecting a person existing in the space based on an image of the space;
An imaging control unit that acquires a detection result of the person in the space from the detection unit, and controls the imaging unit to image the space at a timing when a person is absent based on the detection result ;
And attribute assignment unit for storing from the imaging unit acquires an image of the space, the image obtained, in the image storage section in association with the attribute information on the picture image,
An image collecting apparatus comprising: The attribute information includes imaging setting information indicating information set regarding an imaging operation when the imaging unit acquires the image.
The image collecting apparatus according to claim 1. The attribute information includes space state information indicating a state of the space when the image is acquired.
The image collecting apparatus according to claim 1. The attribute assigning unit acquires the imaging setting information from the imaging unit in synchronization with the timing;
The image collecting apparatus according to claim 2 . The imaging control unit controls the timing based on acquisition condition information indicating a condition related to acquisition of the image by the imaging unit;
The image collection device according to claim 1. A device control unit for controlling equipment for changing the brightness of the space;
An equipment state acquisition unit for acquiring equipment state information indicating the current state of the equipment;
Further comprising
The acquisition condition information indicates a condition related to the state of the equipment when the imaging unit acquires the image,
The imaging control unit determines a state of the facility that satisfies a condition indicated by the acquisition condition information as an imaging state of the facility, and determines a current state of the facility based on the facility state information. , Instructing the imaging unit to image the space at the timing when the current state of the equipment becomes the imaging state,
The device control unit controls the facility so that the state of the facility becomes the imaging state.
The image collecting apparatus according to claim 5. The acquisition condition information indicates a condition relating to a blind state of the space when the imaging unit acquires the image,
The equipment status information indicates the current status of the blind,
The imaging control unit determines the imaging state of the blind based on the acquisition condition information and weather information indicating the weather of the day, and at the timing when the current state of the blind becomes the imaging state Instruct the imaging unit to image the space,
The device control unit controls the blind so that the state of the blind is the imaging state;
The image collecting apparatus according to claim 6. The acquisition condition information indicates a condition relating to a blind state of the space when the imaging unit acquires the image,
The equipment status information indicates the current status of the blind,
The imaging control unit determines an imaging state of the blind based on the acquisition condition information and solar position information indicating a sun position, and at a timing when the current state of the blind becomes the imaging state. Instructing the imaging unit to image the space,
The device control unit controls the blind so that the state of the blind is the imaging state;
The image collecting apparatus according to claim 6. The acquisition condition information indicates a plurality of conditions related to acquisition of the image,
A required time calculation unit for calculating a required time required to acquire an image of the space under each condition;
A priority determining unit that determines a priority for acquiring the image of each condition based on the required time;
Further comprising
The image collection device according to claim 5. The acquisition condition information indicates an acquisition condition of the image according to a location,
The imaging control unit instructs the imaging unit to image the space under an acquisition condition according to a location of a space to be imaged based on the acquisition condition information.
The image collection device according to claim 5. An image collecting method for collecting a background image of the moving object used in a moving object detecting device for detecting a moving object from an image,
An image storing step of storing the image space Target is captured in the image storage unit,
A detection step of detecting a person existing in the space based on an image of the space;
An imaging control step of acquiring a detection result of the person in the space by the detection step and controlling the imaging unit so as to image the space at a timing when a person is absent based on the detection result ;
And attribute assignment step of storing from the imaging unit acquires an image of the space, the image obtained, in the image storage section in association with the attribute information on the picture image,
An image collecting method. In a computer functioning as an image collection device that collects a background image of the moving object used in a moving object detection device that detects a moving object from an image,
An image storing step of storing the image space Target is captured in the image storage unit,
A detection step of detecting a person existing in the space based on an image of the space;
An imaging control step of acquiring a detection result of the person in the space by the detection step and controlling the imaging unit so as to image the space at a timing when a person is absent based on the detection result ;
And attribute assignment step of storing from the imaging unit acquires an image of the space, the image obtained, in the image storage section in association with the attribute information on the picture image,
A computer program for causing a computer to execute.

Images