JP2022117761A - Sensor system, image sensor, server device, sensing method, and program - Google Patents

Abstract

To further increase the availability of a sensor system.SOLUTION: A sensor system includes a plurality of image sensors and a server communicable with the image sensors. The image sensors are installed in respective assigned areas in a building. The image sensor includes a human detection portion, an imaging portion, and a transmission portion. The human detection portion detects the presence/absence of persons in the area. The imaging portion images an area to generate image data. The transmission portion transmits image data generated when the absence of a person is detected to the server. The server includes a receiving portion, a storage portion, and an image connection portion. The receiving portion receives the image data respectively transmitted from the image sensors. The storage portion stores the received image data. The image connection portion creates a connected image by connecting images of adjacent areas on the basis of the image data in the storage portion.SELECTED DRAWING: Figure 6

Description

The embodiments of the present invention relate to sensor systems, image sensors, server devices, sensing methods, and programs.

The digitalization of society has progressed against the background of the progress and spread of semiconductor technology. With the spread of the Internet and other advances in wired and wireless communication technology, and the spread of computer-equipped products and the use of cloud servers, the rise of low-cost, high-performance CMOS image sensors has made digital cameras more popular. let me Not only smartphones and notebook PCs are equipped with cameras, but also surveillance cameras are installed in stores, ATMs, airports, etc., and visitors are monitored by cameras in public facilities, buildings, and buildings. .

WO2018-193813 JP 2016-150849 A JP-A-2002-208493 JP 2009-284230 A

Sensor systems have focused on obtaining information about humans. In addition, in recent years, applications such as grasping the flow line of vehicles such as forklifts operating in warehouses and confirming that there are no obstacles on the flow line of robots are being considered. Alternatively, there are requests such as checking the layout of fixtures on the office floor and checking for forgotten items. Due to such diverse needs, expectations are high for image sensors and sensor systems using image sensors. On the other hand, taking a picture of a person indiscriminately poses a problem in terms of personal information protection such as portrait rights.
Accordingly, it is an object of the present invention to avoid the problem and provide a sensor system, an image sensor, a server device, a sensing method, and a program with further improved availability.

According to embodiments, a sensor system includes a plurality of image sensors and a server in communication with the image sensors. The image sensors are installed in their assigned areas in the building. The image sensor includes a human detection section, an imaging section, and a transmission section. The human detector detects the presence/absence of people in the area. The imaging unit images an area to generate image data. The transmission unit transmits image data generated when the absence of a person is detected to the server. The server includes a receiver, a storage, and an image linker. The receiving unit receives the image data respectively transmitted from the image sensors. The storage unit stores the received image data. The image connecting unit creates a connected image by connecting images of adjacent areas based on the image data in the storage unit.

FIG. 1 is a diagram showing an example of the inside of an office building assumed in an embodiment. FIG. 2 is a diagram illustrating an example of a sensor system according to the embodiment; FIG. 3 is a diagram showing an example of a form of communication between the absence detection unit 10, the image sensor 11, the repeater 13, and the cloud 400. As shown in FIG. FIG. 4 is a diagram showing an example layout of a site. FIG. 5 is a functional block diagram showing an example of the image sensor 11. As shown in FIG. FIG. 6 is a functional block diagram showing an example of the server 2. As shown in FIG. FIG. 7 is a flowchart illustrating an example of a processing procedure of a sensing method according to the embodiment; FIG. 8 is a diagram for explaining a procedure when imaging is performed by the image sensor 11 in response to a request from the server 2. As shown in FIG. FIG. 9 shows an example in which a person 40 and a misplaced item 50 are detected in the same image. FIG. 10 is a diagram showing an example of a corrected image created by masking a person. FIG. 11 is a diagram showing an installation example of an image sensor.

Image sensors can acquire a wider variety of information than physical sensors or infrared sensors. Some have communication functions, and have a high affinity with IoT (Internet of Things) technology. Furthermore, it is also expected to be an edge device for big data analysis. A recent image sensor is equipped with a CPU (Central Processing Unit) and memory, and can be said to be a so-called built-in computer with a lens. It also has advanced image processing functions, and can analyze captured image data to calculate the presence/absence of people or the number of people, for example.

By using a fisheye lens, a wide-angle camera, or the like, the area that can be captured by a single image sensor can be expanded, and image distortion can be corrected by calculation. An image sensor having a function of separately setting a sensing area and a non-sensing area within a field of view and a learning function is also known. The image sensor according to the embodiment can obtain human information and environment information, for example, by processing image data generated by capturing an image captured within the field of view.

Human information is information about humans existing in the target space, such as the number of people in the area, the behavior of people, the amount of activity of people, presence/absence indicating the presence or absence of people, or whether people are walking or not. Walk/Stay, etc., indicating whether to stay in one place. The presence or absence of an object (goods) associated with a person, that is, a package, is also an example of human information. The environment information is information about the environment of the space to be controlled (target space), and examples thereof include the illuminance distribution or temperature distribution of the store.

Human information and environmental information can be calculated for each target space. Alternatively, human information and environmental information can be calculated for each small area (area) obtained by dividing the target space. This embodiment envisages an application in an office building in particular.

[Constitution]
FIG. 1 is a diagram showing an example of the inside of an office building assumed in an embodiment. As shown in FIG. 1, the lighting equipment 1, the outlets of the air conditioners 3, and the image sensor 11 are arranged on, for example, the ceiling of each floor. Area a1 is assigned to one image sensor 11 as a sensing target, and area a2 is assigned to another image sensor 11 as a sensing target. As indicated by hatching in the figure, the areas assigned to different image sensors 11 may partially overlap.

The image sensor 11 looks down on an area and catches it within a field of view at an angle of view, and captures an image within the field of view to generate image data. This image data is processed by the image sensor 11 to calculate human information or environmental information. That is, the image sensor 11 senses an object in the object space and calculates sensor data related to this object.

FIG. 2 is a diagram illustrating an example of a sensor system according to the embodiment; The sensor system includes server 2 of cloud 400 and image sensor 11 installed in building 100 .
A user's smartphone or tablet 200 can access the cloud 400 via a wireless access line. The cloud 400 also includes an office database 44, a mail server 500, and the like. The office database 44 is a database in which data relating to offices located in the building 100 are registered, and can be accessed from the server 2 .

A building 100 includes an office 101 in which tenants reside, and a management room 102 in which a manager of the building resides. A plurality of image sensors 11 are arranged, for example, on the ceiling of the office 101 so as to look down on the floor.

The image sensor 11 takes an image of what is caught in the field of view and generates image data. The field of view of the image sensor 11 includes not only office workers (persons) but also articles such as desks, seats (chairs), and fixtures.

In the embodiment, the absence detection unit 10 is installed, for example, on the ceiling of the office 101 . The absence detection unit 10 is, for example, an infrared sensor, and detects the movement and presence/absence of a person separately from the image sensor 11 .

The image sensor 11 is connected via a signal line 4 to a repeater 13 arranged in, for example, a control room. Similarly, the absence detection unit 10 is also connected to the repeater 13 via the signal line 4 . EtherCAT (registered trademark), BACnet (registered trademark), TCP/IP (Transmission Control Protocol/Internet Protocol), UDP/IP, etc. can be applied to the protocol of the signal line 4 .

The repeater 13 is connected to the intra-building network 5 . As a communication protocol for the intra-building network 5, a Building Automation and Control Networking protocol (BACnet (registered trademark)), DALI (registered trademark), ZigBee (registered trademark), ECHONET Lite (registered trademark), etc. can be applied. be.

Furthermore, a lighting controller 7 connected to the lighting installation 1 is connected to the intra-building network 5 . The lighting controller 7 controls the amount of light of the lighting equipment 1 and on/off based on the control from the management server 8 .

A management server 8 and a database 9 are also connected to the intra-building network 5 . The management server 8 manages lighting, air conditioning, safety, etc. of the office building 100 based on various sensor data acquired from the absence detection unit 10, the image sensor 11, and the like. The database 9 stores a sensor database 9a. The sensor database 9a stores sensor data generated by the image sensor 11 . Although the absence detection unit 10 and the image sensor 11 are shown as separate sensors in FIG. 2 , the image sensor 11 may also serve as the presence/absence detection unit 10 . This also applies to subsequent figures.
The intra-building network 5 is connected to the cloud 400 via a firewall 6 and via a leased line network 300 formed on the Internet, for example.

FIG. 3 is a diagram showing an example of a form of communication between the absence detection unit 10, the image sensor 11, the repeater 13, and the cloud 400. As shown in FIG. In FIG. 3, absence detection units 10 (10a1 to 10xn), image sensors 11 (11a1 to 11xn), transmission units 12 (12a1 to 12xn), and repeaters 13 (13a1 to 13xn) are all referred to as nodes. be. Here, the transmission unit 12 transmits to the server 2 the image data generated in the area where the absence of people has been detected.

In FIG. 3, when the absence detection unit 10a1 detects the absence of a person in the area a1, the image sensor 11a1 generates image data of the area a1. The generated image data is transmitted to the cloud 400 via the repeater 13a2 by the transmitter 12a1. The absence information detected by the absence detection unit 10a1 is transmitted to the cloud 400 via the repeater 13a1. That is, the image data generated by the image sensors 11a1 to 11an are transmitted to the cloud 400 via the repeater 13a2 by the transmitters 12a1 to 12an. The absence information detected by the absence detection units 10a1 to 10an is transmitted to the cloud 400 via the repeater 13a1. That is, the repeater 13 a 1 relays information from n absence detection units 10 , and the repeater 13 a 2 relays image data from n image sensors 11 . In the embodiment, for example, a unit grouped by the suffix a is one group.

Similarly, in the x-th group, the image data generated by the image sensors 11x1 to 11xn are transmitted to the cloud 400 via the repeater 13x2 by the transmitters 12x1 to 12xn. The absence information detected by the absence detection units 10x1 to 10xn is transmitted to the cloud 400 via the repeater 13x1.

FIG. 4 is a diagram showing an example layout of a site. An exemplary site for office 101 (FIG. 3) includes four rooms and a corridor. People can enter and leave the room, which is hereinafter referred to as absence detection areas (areas) a1 to a4. A passage is also an area, and is called a passage area e.

An absence detection unit 10 and an image sensor 11 are installed, for example, on the ceiling of each area. That is, each image sensor 11 is assigned a plurality of areas obtained by dividing the space. FIG. 4 shows an implementation example for n=5 in FIG. The image sensor 11 analyzes the image data to generate sensor data such as human motion information and presence/absence. Sensor data is generated for each area.

In FIG. 4, the absence detection unit 10a1 detects the absence of people in the area a1. When the absence is detected, the information is transmitted to server 2 of cloud 400 via repeater 13a1. A response instruction signal from the server 2 is transmitted to the image sensor 11a1 via the transmitter 12a1 via the repeater 13a2. Alternatively, the response instruction signal may be transmitted to the image sensor 11a1 via the repeater 13a1 and the absence detection section 10a1.

The image sensor 11a1 that has received the response instruction signal from the server 2 takes an image of the area a1 and generates image data. This image data is passed to the transmission unit 12a1. The transmission unit 12a1 compresses the image data in a predetermined format and transmits the compressed image data to the server 2 via the repeater 13a2. Similarly, image data are similarly generated for areas a2 to area a5 and transmitted to the server 2. FIG.

FIG. 5 is a functional block diagram showing an example of the image sensor 11. As shown in FIG. The image sensor 11 includes a camera section 31 , a memory 32 , a processor 33 and a communication section 34 . These are connected to each other via an internal bus 35 .

A camera section 31 as an imaging section includes a fisheye lens 31 a , an aperture mechanism 31 b , an imaging element (image sensor) 31 c and a register 30 . The fisheye lens 31a captures its own assigned area in its field of view, and forms an image within the field of view on the imaging device 31c. The imaging element 31c is an image sensor represented by a CMOS (Complementary Metal Oxide Semiconductor), and generates a video signal with a frame rate of 30 frames per second, for example. This video signal is digitally encoded to generate image data. The amount of light incident on the imaging device 31c is adjusted by the aperture mechanism 31b.

The register 30 stores camera information 30a. The camera information 30a is information about the camera unit 31, such as the state of the auto gain control function, gain value, and exposure time, or information about the image sensor 11 itself.

The memory 32 is a semiconductor memory such as SDRAM (Synchronous Dynamic RAM) or EPROM (Erasable Programmable ROM). The memory 32 stores a program 32a for causing the processor 33 to execute various functions related to the embodiment, image data 32b generated by the camera unit 31, a sensor ID (IDentification) 32c for uniquely distinguishing the image sensor, and , store the dictionary data 32d.

The dictionary data 32d is, so to speak, template data created for detecting a person in image data. For example, a person is detected from the image data by performing template matching processing using the dictionary data 32d prepared for "a person looking down from the ceiling". Dictionary data can be created using a machine-learning framework such as a support vector machine or a Boltzmann machine.

The processor 33 executes a program 32a stored in the memory 32 to implement various functions described in the embodiments. The processor 33 is, for example, an LSI (Large Scale Integration) that includes a multi-core CPU and is tuned to execute image processing at high speed. The processor 15 can also be configured with an FPGA (Field Programmable Gate Array) or the like. An MPU (Micro Processing Unit) is also one of the processors.
The communication unit 34 is connectable to the signal line 4 and mediates transmission and reception of data with the repeater 13 , the management server 8 , the cloud 400 and the server 2 .

By the way, the processor 33 includes a human detection unit 33a, a transmission unit 33b, and a mask processing unit 33c as processing functions according to the embodiment. The human detection unit 33a, the transmission unit 33b, and the mask processing unit 33c are processes generated in the course of the processor 33 executing arithmetic processing according to the program 32a loaded into the register of the processor 33, for example.

The human detection unit 33a analyzes the image data 32b and generates sensor data including a person's position, attribute information, stay time, and the like. That is, the human detection unit 33a detects human information (position of a person, presence/absence of a person, number of people, behavior of a person, amount of activity of a person, presence/absence of luggage, etc.) based on a feature amount obtained by image processing the image data 32b. etc.) and environmental information (illuminance distribution, temperature distribution, etc.). There are also sensing items such as human cell position, staying time, and walking/staying. The human detection unit 33a can also sense more detailed attribute information such as male, female, young, middle-aged, and old.
Then, the human detection unit 33a detects presence/absence of a person in the area. In other words, assuming that a person is to be detected, "absence" is sensed if no person is detected within the field of view.
The transmission unit 33b transmits to the server 2 the image data generated when the "absence" is detected.
The mask processing unit 33c creates corrected image data by masking a person included in image data generated in a state in which a person is detected, that is, in a state in which "presence" is detected. The corrected image data is also sent to the server 2 as needed.

FIG. 6 is a functional block diagram showing an example of the server 2. As shown in FIG. The server 2 is a computer including a processor 21 such as a CPU or MPU, a ROM (Read Only Memory) 22 and a RAM (Random Access Memory) 23 . The server 2 further includes a storage unit 24 such as a hard disk drive (HDD), an optical media drive 25 and a communication unit 26 .

The ROM 22 stores basic programs such as BIOS (Basic Input Output System) and UEFI (Unified Extensible Firmware Interface), various setting data, and the like. The RAM 23 temporarily stores programs and data loaded from the storage unit 24 .

The optical media drive 25 reads digital data recorded on a recording medium such as a CD-ROM 27 . Various programs executed by the server 2 are recorded on, for example, a CD-ROM 27 and distributed. The program stored in this CD-ROM 27 is read by the optical media drive 25 and installed in the storage section 24 .
The communication unit 26 controls communication with the site (building 100) via the cloud 400. FIG. The communication unit 26 also functions as a receiving unit that receives image data transmitted from the image sensor 11 .

In addition to the program 24a executed by the processor 21, the storage unit 24 stores the image data 24b received from the image sensor 11, the connected image 24c, the absence map 24d, and the route information 24e. The connected image 24c, absence map 24d, and route information 24e will be described later.

Incidentally, in FIG. 6, the processor 21 has, as its functions, an image linking section 21a, a lighting control section 21b, a transmission request section 21c, an article detection section 21d, a map creation section 21e, a notification section 21f, and a route creation section 21g.

The image linking unit 21a reads out from the storage unit 24 the image data obtained from the plurality of image sensors 11 covering adjacent areas, and creates a linked image by linking the images of the respective areas. The created connected image is stored in the storage unit (connected image 24c).

The lighting control unit 21b controls the lighting equipment 1 (FIG. 1) in the area where the absence is detected to provide the image sensor 11 with the amount of light necessary for the image sensor 11 in the area to generate image data. . Specifically, the lighting control unit 21b gives a control signal to the lighting controller 7 directly or via the management server to control the amount of light of the lighting equipment 1 in the target area or the illuminance of the area.

The transmission request unit 21c requests each image sensor 11 to transmit image data, for example, at the timing of a schedule created in advance or periodically. The image sensor 11 generates and transmits image data according to a request from the server 2 . By aligning the timings of generation/transmission/reception of image data in this way, it is possible to align the photographing times of the individual images that make up the connected image. Also, the latest connected image can always be created.
Further, the transmission request unit 21c requests the image sensor that transmitted the corrected image data generated by masking the image including the person to retransmit the image data generated when the absence of the person was detected. demand.

The article detection unit 21d detects the presence/absence of an article based on the difference between the time-series images or the difference between the time-series connected images.
The map creation unit 21e performs image processing on the connected images to create an absence map indicating areas where people are absent. The created absence map is notified to a predetermined user by the notification unit 21f.

The route creation unit 21g performs image processing on the connected image to create route information indicating the movement route of patrol devices such as mobile robots, cleaning robots, guidance robots, and parcel-carrying robots. The notification unit 21f transmits this route information to the patrolling device and notifies it. Next, the operation of the above configuration will be described.

[Action]
FIG. 7 is a flowchart illustrating an example of a processing procedure of a sensing method according to the embodiment; In FIG. 7, in the initial setting (including the default setting of determination processing by administrator input), an initial setting operation is performed by the administrator (step S10). In the initial setting, the default setting in the judgment processing block in the flow chart can also be input.

When the initial settings are completed and the system starts operating, the image sensor 11 determines whether or not it is in its own target area (step S11). If absent, the result is Yes, and the image sensor 11 determines whether or not to perform illuminance control based on the imaging result (step S12). For the judgment here, it is possible to set a default value according to the time or the target area.

If the illuminance is not controlled (No in step S12), the image sensor 11 takes an image of the target area to create image data (step S17), and transmits this image data to the repeater 13 (step S20). On the other hand, if the illuminance is to be controlled (Yes) in step S12, the image sensor 11 captures an image of the target area and creates image data (step S16), analyzes the illuminance of the image, and recaptures the image. It is determined whether or not (step S18).

In step S18, for example, it is possible to determine whether re-imaging is necessary based on whether or not the illuminance of the entire image satisfies a predetermined value. Alternatively, it may be determined whether or not the difference value of the image from the past imaging result of the same area exceeds a predetermined cumulative value. Alternatively, object recognition may be performed on the image, and it may be determined whether or not the object can be recognized with a predetermined resolution.

If No in step S18, the image sensor 11 performs illumination control on the target area (step S19), and then the processing procedure returns to step S11. If Yes in step S18, re-imaging is unnecessary, and the image sensor 11 transmits the image data to the repeater 13 (step S20).

Next, the server 2 determines whether or not to image the next image sensor (step S21), and if Yes, returns to step S11 to image the next area. If No in step S21, the processing ends assuming that the imaging of all the areas to be imaged has been completed.

On the other hand, if the person is staying in step S11, that is, if it is in the state of presence, the judgment is No, and the processing procedure moves to step S13. In this step, the server 2 determines whether or not to perform imaging even if there is a person in the target area (group). In other words, the process when there is a person is determined for each individual target area or for each group of repeaters 13, for example. The behavior (shooting/not shooting) setting here can be defaulted.

If No (not to shoot) in step S13, the server 2 waits for a predetermined time (T=T+ΔT), then returns to step S11 and starts shooting at the next timing. If Yes (to shoot) in step S13, the server 2 determines whether or not to perform illuminance control based on the imaging result (step S14). For the determination here, it is possible to set default values according to the imaging area and the imaging time.

If the illuminance is not to be controlled (No in step S14), the server 2 controls the image sensor 11 to capture an image of the target area (step S26), and performs mask processing (step S24). By masking, the human portion included in the image data is masked to generate corrected image data. After the mask processing is completed, the processing procedure moves to step S20.

On the other hand, if the illuminance is to be controlled in step S14 (Yes), the image sensor 11 captures an image of the target area to create image data (step S22), analyzes the illuminance of the image, and determines whether recapture is necessary. It is determined whether or not (step S23).

If No in step S23, the server 2 performs lighting control on the target area (step S25), and then the processing procedure returns to step S11. If Yes in step S23, the image sensor 11 performs mask processing (step S24), and transmits the corrected image data in which the person is not captured to the intermediary device 13 of the affiliation (step S20). It should be noted that the execution of mask processing by a person (step S24) can also be executed on the server 2 side.

FIG. 8 is a diagram for explaining a procedure when imaging is performed by the image sensor 11 in response to a request from the server 2. As shown in FIG. At the building 100 (site) in which the image sensor group and the repeater are installed, the absence information detected by the image sensors 11a1 to 11a5 is notified to the repeater 13a2. In response to this, the repeater 13a2 instructs the image sensors 11a1 to 11a5 to acquire image data.

The acquired image data is sent to the cloud 400 via the repeater 13a2 and received by the server 2. FIG. If the server 2 detects that the image data acquired by the image sensor 11a3 with ID: 3 has a defect or that the mask processing has been performed, the server 2 issues a re-imaging instruction (imaging request). It is transmitted to the image sensor 11a3 with ID:3. The image sensor 11 a 3 that receives this image again takes an image and transmits the image data to the server 2 .

In FIG. 8, it is assumed that the image sensor 11 also functions as the absence detection unit 10 . On the cloud side, the server 2 provides functions such as image processing, furniture detection, and layout detection, and image sensor services such as floor map creation service, furniture layout management service, robot movement support map service, and the like are provided.

FIG. 9 shows an example of an image containing an article and a person. FIG. 9 shows an example where a person 40 (before being masked) and a misplaced item 50 are detected in the same image. The server 2 detects the presence/absence of an article based on the difference between the time-series connected images 24c stored in the storage unit 24 (FIG. 6). For example, the past connected image 24c and the latest connected image 24c are compared, and from the time stamp of the image, it can be found that the item was left behind by the previous user.

FIG. 10 is a diagram showing an example of a corrected image created by masking a person. In the image, the person 40 is made invisible by mask processing 41 . As described above, image data containing a person as a result of imaging is masked and transmitted to the server 2 as corrected image data.

FIG. 11 is a diagram showing an installation example of an image sensor. For example, multiple image sensors are installed on the ceiling of office areas and corridors. Each image sensor is assumed to be integrated with the absence detection section, and the arrangement of only the image sensor is shown. As shown in FIG. 11, in an actual installation, the area covered by an image sensor overlaps the area covered by an adjacent image sensor. Depending on the installation plan, it may become a blind spot for large fixtures such as lockers and may not be imaged. When installing the image sensor, it is preferable to ensure that there are no blind spots in the target area. Also, the resolution may be poor and obscured at locations that are much further away from the image sensor than elsewhere. Therefore, it is preferable to design the layout of the image sensor so that misplacement, loss, and the like of articles can be detected satisfactorily.

[effect]
As described above, in the embodiment, each area is imaged by a plurality of image sensors 11 to which predetermined areas are assigned. At that time, the absence detection unit 10 for detecting the absence of a person in a predetermined area takes an image when it detects that the person is absent, and transmits the image data to the server 2 . Since information without people is sent to the server via the network, it is possible to avoid the risk of personal information protection. The server 2 stores the collected image data from the plurality of image sensors 11 in the storage unit 24 . By reading images of adjacent areas from the storage unit 24 and outputting them in a concatenated manner, it is possible to obtain image information obtained by a plurality of image sensors in which people are not captured.

With existing technology, image data is blindly sent to the network regardless of whether or not a person is in the image. Because of this risk, there was a risk that it would be disadvantageous in recruiting tenants.

In addition, human information is not the only useful information captured and collected by image sensors installed in buildings and facilities. Up-to-date information on fixtures, fixtures, and items in the facility is also useful. For example, information such as misplacement of items by users, detection of suspicious items, loss of equipment, information such as the usage status of free offices and shared offices, advance information on whether objects are placed in patrol passages and cleaning robots can pass confirmation information, etc. On the other hand, in buildings and facilities where many people come and go, it is difficult to save image data without worrying about personal information protection. There is
On the other hand, in the embodiment, since the obtained image data is evaluated and lighting control is performed, clear image data can be obtained. In addition, since data including a person is not transmitted to the network, image data can be collected without infringing on personal information protection concerns.

For these reasons, according to the embodiments, it is possible to provide a sensor system, an image sensor, a server device, a sensing method, and a program with further improved availability.

It should be noted that the present invention is not limited to the above embodiments.

For example, the system may be provided with a display device that displays the connected images generated by the server 2 over time. In this way, for example, in a shared office or the like, it is possible to know changes over time in facility usage conditions.

Also, in an area where the absence of a person is detected, sterilization equipment such as ultraviolet light and ozone sterilization may be operated. As a result, sterilization and sterilization can be performed without making people feel uncomfortable. It is also effective against infectious diseases.

Also, even if a person is staying in a part of the area, the image may be taken periodically, the person's part may be masked, and the image may be transmitted to the server 2 . In this way, even if people are not completely absent from the area covered by one group, the image data can be uploaded to the server 2 anyway while avoiding the risk of personal information protection. If necessary, the masked image may be captured at a later time and transmitted to the server 2 to replace the image.

Further, when the absence is detected, the lighting control of the target absence detection area may be performed, and if necessary, the lighting may be turned on before the image is captured. It is better to have a certain amount of illuminance for object detection. You can control the lighting.

Also, when the lighting equipment 1 automatically turns off in an unoccupied area, the camera unit 31 of the image sensor 11 captures an image of the area and saves image data during the period from when the absence is detected until when the lighting equipment 1 turns off. may be generated. By doing so, a sufficient amount of light can be secured.

In addition, in FIG. 2, the management server 8 is provided with input/output terminals, but all the control may be performed on the server 2 side. In that case, the management room 102 may be an article storage space without a work space for the manager.
Also, in FIG. 3, it is not essential that the transmitter 12 is connected only to the image sensor 11 . For example, when the image data generated by the image sensor 11 is compressed by the transmission unit 12 and transmitted to the cloud 400, it is reasonable to use the transmission unit 12 having a data compression function. Alternatively, if the processor of the image sensor 11 has sufficient capability, it is of course possible to implement the function of the transmission unit 12 together with the compression function in the image sensor 11 .

Also, the absence detection unit 10 may be connected to the transmission unit 12 to transmit the absence information to the cloud 400 . Also, it is not essential that one group has two repeaters, and it is possible to combine them into one repeater.

Furthermore, the absence detection unit 10 and the image sensor 11 may be functions included in the same device. In other words, the presence/absence of a person may be detected by the image processing function of the image sensor 11 . Image sensors of this kind have already been provided in recent years.

Also, in the explanation of FIG. 4, the image sensor 11 has explained an example in which the image is captured according to the instruction signal from the server 2 . Not limited to this, the image sensor 11 may capture an image of the area according to an instruction from the absence detection unit 10 that has detected absence. Alternatively, the repeater 13 may control the imaging timing. That is, at the timing when absence is detected by all of the absence detection units 10a1 to 10a5, the repeater 13a1 may issue an imaging instruction to the connected image sensors 11a1 to 11a5. By doing so, it is possible to match the imaging times within one group to the same time.

All or part of each function of the sensor system in the embodiment may be realized using hardware such as ASIC (Application Specific Integrated Circuit), PLD (Programmable Logic Device), FPGA (Field Programmable Gate Array), or the like. The program may be recorded on a computer-readable recording medium. A computer-readable recording medium is, for example, a portable medium such as a magnetic disk, a magneto-optical disk, a CD-ROM, or a DVD-ROM, or a storage device such as a hard disk built into a computer. The program may be transmitted over telecommunications lines.

While embodiments of the invention have been described, the embodiments are provided by way of example and are not intended to limit the scope of the invention. This novel embodiment can be embodied in various other forms, and various omissions, replacements, and modifications can be made without departing from the scope of the invention. This embodiment and its modifications are included in the scope and gist of the invention, and are included in the scope of the invention described in the claims and its equivalents.

REFERENCE SIGNS LIST 1 Lighting equipment 2 Server 3 Air conditioner 4 Signal line 5 Building network 6 Firewall 7 Lighting controller 8 Management server 9 Database 9a Sensor database 10 Absence detection unit 11 Image sensor 12 Transmission unit 13 Repeater 15 Processor 21 Processor 21a Image connection unit 21b Illumination control unit 21c Transmission request unit 21d Article detection Part 21e... Map creation part 21f... Notification part 21g... Route creation part 22... ROM 23... RAM 24... Storage part 24a... Program 24b... Image data 24c... Connected image 24d... Absence map , 24e... route information, 25... optical media drive, 26... communication section, 30... register, 30a... camera information, 31... camera section, 31a... fisheye lens, 31b... aperture mechanism, 31c... imaging element, 32... memory, 32a Program 32b Image data 32d Dictionary data 33 Processor 33a Person detection unit 33b Transmission unit 33c Mask processing unit 34 Communication unit 35 Internal bus 40 Person 41 Mask processing 44 Office database 50 Goods 100 Office building 101 Office 102 Control room 200 Tablet 300 Private line network 400 Cloud 500 Mail server.

Claims (18)

a plurality of image sensors installed in respective assigned areas of a building;
a server capable of communicating with the image sensor;
The image sensor is
a human detection unit that detects presence/absence of a person in the area;
an imaging unit that captures an image of the area and generates image data;
a transmitting unit configured to transmit image data generated when the person's absence is detected to the server;
The server is
a receiving unit that receives image data transmitted from each of the image sensors;
a storage unit that stores the received image data;
and an image connecting unit that creates a connected image by connecting the images of the adjacent areas based on the image data of the storage unit. When the building is equipped with lighting equipment,
The server is
2. The sensor system of claim 1, further comprising a lighting controller that controls the lighting fixture to provide the image sensor with the amount of light necessary to generate the image data when the absence is detected. When the building is equipped with lighting equipment that automatically turns off in the absence area,
2. The sensor system according to claim 1, wherein said imaging unit images said area after said absence is detected until said lighting equipment is turned off. The server further comprises a transmission request unit that requests transmission of image data from the image sensor,
2. The sensor system according to claim 1, wherein said transmission unit transmits said image data in response to a request from said server. 5. The sensor system according to claim 4, wherein said transmission request unit periodically requests said image sensor to transmit said image data. 2. The sensor system according to claim 1, wherein said server further comprises an article detection unit that detects presence/absence of an article based on a difference between time-series images or a difference between time-series connected images. The server is
an image processing unit that processes the connected image to create an absence map;
2. The sensor system according to claim 1, further comprising a notification unit that notifies a predetermined user of said absence map. 2. The sensor system according to claim 1, further comprising a display device for displaying said connected images over time. If the building is equipped with sterilization equipment,
2. The sensor system of claim 1, wherein the server activates the sterilization equipment in the area where the absence is detected. 10. The sensor system of claim 9, wherein the sterilization facility is ultraviolet lighting. The server is
an image processing unit that performs image processing on the connected image to create route information indicating a movement route of the patrol device;
2. The sensor system according to claim 1, further comprising a notification unit that notifies said patrol device of said route information. The image sensor is
further comprising a mask processing unit that creates corrected image data by masking the person included in the image data generated while the person is detected,
2. The sensor system according to claim 1, wherein said transmission unit transmits said corrected image data to said server. The server further comprises a transmission request unit that requests the image sensor that transmitted the corrected image data to retransmit the image data generated when the absence of the person was detected,
13. The sensor system according to claim 12, wherein said transmission unit retransmits said image data in response to a request from said server. further comprising a repeater that buffers the image data transmitted from the plurality of image sensors;
14. The sensor system of claim 13, wherein the repeater retransmits the buffered image data upon request from the server. In the image sensor of a sensor system comprising a plurality of image sensors installed in respective assigned areas in a building and a server capable of communicating with the image sensors,
a human detection unit that detects presence/absence of a person in the area;
an imaging unit that captures an image of the area and generates image data;
and a transmitting unit configured to transmit image data generated when the person's absence is detected to the server. In the server of a sensor system comprising a plurality of image sensors installed in respective assigned areas of a building and a server capable of communicating with the image sensors,
a receiving unit that receives image data transmitted from each of the image sensors;
a storage unit that stores the received image data;
and an image connecting unit that creates a connected image by connecting the images of the adjacent areas based on the image data of the storage unit. A sensing method for a sensor system comprising a plurality of image sensors installed in respective assigned areas in a building and a server capable of communicating with the image sensors, comprising:
the image sensor detects presence/absence of a person in the area;
the image sensor imaging the area to generate image data;
The image sensor transmits image data generated with the absence of the person detected to the server,
the server receiving image data transmitted from each of the image sensors;
the server stores the received image data in a storage unit;
The sensing method, wherein the server creates a connected image by connecting the images of the adjacent areas based on the image data of the storage unit. The server of a sensor system comprising a plurality of image sensors installed in each assigned area of a building, and a server capable of communicating with the image sensors,
a command to function as a receiving unit that receives image data transmitted from each of the image sensors;
a command to function as a storage unit that stores the received image data;
and a command functioning as an image linking unit that creates a linked image by linking the images of the adjacent areas based on the image data in the storage unit.

Images