JP2020010204A - Sensing system, maintenance terminal device, data distribution method, and image sensor - Google Patents

Abstract

To further improve usability of a sensing system.SOLUTION: The sensing system includes: an image sensor for detecting an object using a dictionary data set prepared for each detection item. Dictionary data is stored in a data server in advance. The sensing system further includes selection means and distribution means. The selection means selects the dictionary data set corresponding to a requested service for each image sensor. The distribution means distributes the dictionary data corresponding to the selected dictionary data set from the data server to the image sensor.SELECTED DRAWING: Figure 5

Description

An embodiment of the present invention relates to a sensing system, a maintenance terminal device, a data distribution method, and an image sensor.

  Recent image sensors include a CPU (Central Processing Unit) and a memory, and can be called an embedded computer with a lens. It also has an advanced image processing function, and can analyze captured image data to calculate, for example, the presence / absence of a person or the number of people.

JP 2017-138922 A

For example, a lighting control system using an infrared human sensor is known. However, if an image sensor is used, there is a possibility that an unprecedented service can be provided in a modern society having various social infrastructures. In particular, various utilization techniques are expected for an image sensor capable of detecting an object using dictionary data.
Therefore, an object of the present invention is to provide a sensing system, a maintenance terminal device, a data distribution method, and an image sensor that are further improved in usability.

  According to the embodiment, the sensing system includes an image sensor that detects a target using a dictionary data set prepared for each detection item. Dictionary data is stored in the data server in advance. The sensing system further includes a selection unit and a distribution unit. The selecting means selects a dictionary data set corresponding to the requested service for each image sensor. The distribution means distributes dictionary data corresponding to the selected dictionary data set from the data server to the image sensor.

FIG. 1 is a schematic diagram illustrating an example of a sensing system including the image sensor according to the embodiment. FIG. 2 is a diagram showing an example of a building floor. FIG. 3 is a block diagram showing an example of the sensing system shown in FIG. FIG. 4 is a diagram showing an example of an arrangement of tenants occupying the building 10. FIG. 5 is a functional block diagram showing an example of the maintenance terminal 200 shown in FIG. FIG. 6 is a diagram showing an example of dictionary data compiled for each service content. FIG. 7 is a diagram illustrating an example of a GUI window displayed on the monitor 210. FIG. 8 is a diagram illustrating an example of a state in the middle of the operation of specifying the download timing of the dictionary data. FIG. 9 is a diagram illustrating an example of a state in which the specification of the download timing of the dictionary data has been completed. FIG. 10 is a block diagram illustrating an example of the image sensor 3. FIG. 11 is a diagram showing an example of a data flow between the functional blocks shown in FIG. FIG. 12 is a sequence chart illustrating an example of a processing procedure between the maintenance terminal 200 and the image sensor 3 regarding distribution of dictionary data. FIG. 13 is a sequence chart showing another example of the processing procedure between the maintenance terminal 200 and the image sensor 3 concerning distribution of dictionary data. FIG. 14 is a functional block diagram illustrating an example of the maintenance terminal 200 according to the second embodiment. FIG. 15 is a functional block diagram illustrating an example of the image sensor 3 according to the second embodiment. FIG. 16 is a diagram illustrating an example of the dictionary data 32d stored in FIG. FIG. 17 is a diagram for explaining that usable dictionary data is limited according to the service content. FIG. 18 is a diagram for explaining that usable dictionary data is limited according to the service content. FIG. 19 is a block diagram illustrating an example of a sensing system according to the third embodiment of the present invention. FIG. 20 is a functional block diagram illustrating an example of the maintenance terminal 200 according to the third embodiment. FIG. 21 is a functional block diagram illustrating an example of the image sensor 3 according to the third embodiment. FIG. 22 is a diagram illustrating a mode in which some functions are transferred to the cloud 600. FIG. 23 is a diagram illustrating an example in which the functions according to the embodiment are installed in the BEMS server 5 instead of the maintenance terminal 200.

  The image sensor can acquire more information than a human sensor, a light sensor, an infrared sensor, or the like. If a fisheye lens or an ultra-wide-angle lens is used, the area that can be photographed by one image sensor can be enlarged, and image distortion can be corrected by calculation processing. There is also known an image sensor having a function of setting a mask for an area in the field of view not to be sensed and a learning function. Further, by updating the dictionary data for detecting the dictionary data target, the detection performance of the target object can be optimized. Hereinafter, an embodiment of a system including such an image sensor will be described.

  FIG. 1 is a schematic diagram illustrating an example of a sensing system including the image sensor according to the embodiment. In FIG. 1, a lighting device 1, an air conditioner 2, and an image sensor 3 are provided, for example, for each floor of a building 10 and are communicably connected to a controller 4. The controller 4 on each floor is communicably connected to, for example, a BEMS (Building Energy Management System) server 5 of a building management center via a network 500 inside the building. As a communication protocol of the in-building network 500, a Building Automation and Control Networking protocol (BACnet (registered trademark)) is representative. In addition, protocols such as DALI, ZigBee (registered trademark), and ECHONET Lite (registered trademark) are also known.

  The BEMS server 5 can be connected to a cloud computing system (cloud) 600 via a communication network 300 based on, for example, TCP / IP (Transmission Control Protocol / Internet Protocol). The cloud 600 includes a database 70 and a server 80, and provides services related to building management and the like.

  As shown in FIG. 2, the lighting device 1, the outlet of the air conditioner 2, and the image sensor 3 are arranged on, for example, a ceiling of each floor. The image sensor 3 captures an image captured in the field of view and acquires image data. This image data is processed in the image sensor 3 to generate person information and / or environment information.

The environment information is information on the environment of the space (zone) to be imaged, and is, for example, the illuminance and temperature of the floor. The person information is information about a person in the target space. For example, the number of people in the area, the behavior of the person, the amount of activity of the person, the presence / absence indicating the presence or absence of the person, or the walking / retention indicating whether the person is walking or staying in one place, etc. It is an example of information. It is also possible to calculate the environment information and the person information for each small area (area) obtained by dividing the zone into a plurality.
In recent years, it has been studied to secure the comfort and safety of people by controlling the lighting device 1 and the air conditioner 2 based on such information in a living environment of a person.

  FIG. 3 is a block diagram showing an example of the sensing system shown in FIG. In FIG. 3, under the control of the BEMS server 5, an air conditioning controller 41 for controlling the air conditioner 2, an elevator controller 42 for controlling the elevator, a security controller 43 for controlling the security system, a disaster prevention controller 44 for controlling the disaster prevention system, and lighting. The lighting controller 45 that controls the devices 1 (1-1 and 1-2) is connected via the in-building network 500.

  In addition, the maintenance terminal 200 and the gateway 7 are connected to the building network 500 so as to be able to communicate with the BEMS server 5. Further, a plurality of image sensors 3 (3-1 to 3-n) are accommodated under the gateway 7.

  The image sensors 3-1 to 3-n are connected in a one-stroke form by the sensor network 100 (crossover wiring). The sensor network 100 communicatively connects the image sensors 3-1 to 3-n and the gateway 7 by, for example, EtherCAT (registered trademark). The BEMS server 5 and the maintenance terminal 200 can also communicate with the image sensors 3-1 to 3-n via the gateway 7.

  FIG. 4 is a diagram showing an example of an arrangement of tenants occupying the building 10. For example, it is assumed that three tenants A, B, and C are occupying one floor with a wall (dotted line) therebetween. Each tenant has four image sensors 3, which are connected to a gateway 7 via a sensor network 100.

Here, the solution using the image sensor 3 does not need to be the same for all tenants, but rather it is desirable that different services can be flexibly proposed. That is, there is a possibility that the required services are different for each of the tenants A, B, and C. For example, if tenant A is used as a store, tenant B is used as an office, and tenant C is used as a warehouse, the services required will be different. As an example, tenant A may acquire human flow analysis data, tenant B may require fine control of air conditioning / illumination, and tenant C may require security services.
In a store, for example, the service to be obtained may change depending on the time of the day, such as acquisition of human distribution data during the day and crime prevention at night.
It has been difficult for existing technologies to flexibly respond to such various service requests. Hereinafter, a technology that can solve such difficulties will be disclosed.

[First Embodiment] (A form in which minimal dictionary data is installed in an image sensor)
FIG. 5 is a functional block diagram showing an example of the maintenance terminal 200 shown in FIG. The maintenance terminal 200 as an example of the data server is a computer including a processor 250 such as a CPU and an MPU (Micro Processing Unit), a ROM (Read Only Memory) 220, and a RAM (Random Access Memory) 230. The maintenance terminal 200 further includes a storage unit 240 such as a hard disk drive (Hard Disk Drive: HDD), an optical media drive 260, a communication unit 270, and a monitor 210 that displays various information.

  The ROM 220 stores basic programs such as a BIOS (Basic Input Output System) and UEFI (Unified Extensible Firmware Interface), and various setting data. The RAM 230 temporarily stores programs and data loaded from the storage unit 240.

  The optical media drive 260 reads digital data recorded on a recording medium such as a CD-ROM 280. Various programs executed by the maintenance terminal 200 are recorded on, for example, the CD-ROM 280 and distributed. The program stored in the CD-ROM 280 is read by the optical media drive 260 and installed in the storage unit 240.

  The communication unit 270 has a function for communicating with the image sensor 3, the BEMS server 5, and the like via the in-building network 500. Various programs executed by the maintenance terminal 200 may be downloaded from a server via, for example, the communication unit 270 and installed in the storage unit 240. The latest program can be downloaded from the cloud 600 via the communication unit 270, and the installed program can be updated. Further, the maintenance terminal 200 can download and transmit the dictionary data to the image sensor 3 via the building network 500 and the gateway 7.

  Storage unit 240 stores dictionary data 240b and billing data 240c in addition to program 240a executed by processor 250.

  The dictionary data 240b is data similar to template data, which is prepared according to detection items (persons, objects, men, women, etc.) in the image sensor 3. For example, a chair is detected from the image data by performing template matching processing on the image data acquired by the image sensor 3 using the dictionary data 240b prepared for detecting “chair”. Various dictionary data 240b are prepared in advance so that the accuracy, the type of chair (office chair, sofa, sitting chair, etc.) and the color can be distinguished. In addition, it is possible to create dictionary data for detecting a wheelchair, a stroller, a child, a cart, a white cane user, a wandering elderly person, a suspicious person, a lost child, a person who was late to escape, and the like. As an example of the creation method, a machine learning (Machine-Learning) framework such as a support vector machine or a Boltzmann machine can be used.

  As shown in FIG. 6, the dictionary data 240b may include a plurality of sets of dictionary data for each service type (service pack). The basic service detects objects using the dictionary data D written in the storage unit 240 by default, and can use this function using an image sensor immediately after installation. If the function of the service is different or upgraded, the type, number, and combination of dictionary data used also change. For example, for the service pack WWW, the default dictionary data D and the dictionary data m1 and m2 are combined and compiled as a dictionary data set suitable for detecting an object. The dictionary data set mainly targets a data group including a plurality of dictionary data, but is not limited thereto, and includes data composed of one dictionary data (for example, default dictionary data D).

  In general, not only one dictionary data but one dictionary data is often used in combination for one detection item. In addition, one dictionary data is often used not only for one detection item but for a plurality of detection items in common.

  It is also possible to set a price (charging plan) to be provided to a service contractor for each service pack. Further, for example, a charging plan can be set according to the detection accuracy (low accuracy, medium accuracy, high accuracy, etc.), the number of types of detection items, and the like. The charge amount to the entity (for example, a service contractor) who downloaded the dictionary data included in the service pack is stored in a database in the charge data 240c and managed.

  The processor 250 executes an OS (Operating System) and various programs. Further, the processor 250 includes, as processing functions according to the embodiment, a selection unit 250a, a distribution unit 250b, a billing processing unit 250c, a timing specification unit 250d, a period specification unit 250e, and a key information generation unit 250f.

  These functional blocks can be understood as a process in which the program 240a is loaded into the RAM 230 and generated during the execution of the program. That is, the program 240a causes the maintenance terminal 200, which is a computer, to operate as the selection unit 250a, the distribution unit 250b, the accounting unit 250c, the timing designation unit 250d, the period designation unit 250e, and the key information generation unit 250f.

  The selection unit 250a selects a combination (dictionary data set) of dictionary data according to the requested service for each of the image sensors 3-1 to 3-n. Services are often determined for each tenant in a building. For example, when there are three tenants as shown in FIG. 4, the image sensors can be grouped for each tenant as shown in FIG. 7 (groups A, B and C). That is, the service can be associated with the groups A, B, and C. Therefore, the selection unit 250a selects, for example, a dictionary data set for each of the groups A, B, and C associated with the tenant.

  Of course, an optimal dictionary data set may be selected for each of the image sensors 3-1 to 3-n. For example, the required image data may differ between the image sensor near the entrance of tenant A and the image sensor at the back of the store. As described above, by selecting a dictionary data set according to the installation environment of the image sensor 3, more detailed services can be realized.

  The distribution unit 250b reads the dictionary data included in the dictionary data set selected by the selection unit 250a from the storage unit 240, and distributes the dictionary data to the target image sensor. The distribution of the dictionary data is executed at the time designated by the timing designation unit 250d.

The timing specification unit 250d receives a user operation for specifying the distribution timing of the dictionary data by the distribution unit 250b.
FIG. 7 is a diagram illustrating an example of a GUI window displayed on the monitor 210. For example, icons corresponding to the tenant arrangement and the image sensor arrangement in FIG. 4 are displayed. For example, when group A is clicked with a mouse, a calendar as shown in FIG. 8 and a drop-down list of data distribution times are displayed. From here, for example, when 23:00 on 2018/7/4 is designated by the user, the date and time are set in the group A as shown in FIG.

  The timing specification unit 250d stores the download timing of the dictionary data specified in the storage unit 240 for each tenant, each group, or each image sensor. At the designated time, the distribution unit 250b downloads the dictionary data to the target image sensor.

The period designating unit 250e receives the user operation for designating the operation period of the requested service.
The key information generation unit 250f generates key information for validating the dictionary data distributed by the distribution unit 250b during the operation period specified by the period specification unit 250e. This key information is distributed to the target image sensor by the distribution unit 250b.

The billing processing unit 250c manages billing information for billing a subscriber of the service in accordance with the download of the dictionary data. That is, since the dictionary data downloaded to the image sensor 3 changes according to the service, it is necessary to download and update the dictionary data every time. The billing processing unit 250c manages billing information that is generated when a download or service operation starts. The billing information is stored in, for example, the storage unit 240 (billing data 240c).
Note that the selection unit 250a may select a dictionary data set based on a billing plan for the requested service.

  FIG. 10 is a block diagram illustrating an example of the image sensor 3. The image sensor 3 includes an imaging unit 31, a storage unit 32, a processor 33, and a communication unit 34. These are connected to each other via an internal bus 35.

  The imaging unit 31 includes a fisheye lens 31a, an aperture mechanism 31b, an imaging element 31c, and a register 30. The fisheye lens 31a captures an image on the image sensor 31c by capturing the interior of the room as the target space, for example, in a direction looking down from the ceiling. The image sensor 31c is an image sensor represented by a CMOS (complementary metal oxide semiconductor), and generates a video signal having a frame rate of, for example, 30 frames per second. This video signal is digitally encoded and output as image data. The amount of light incident on the image sensor 31c is adjusted by the diaphragm mechanism 31b.

  The register 30 stores camera information 30a. The camera information 30a is information on the imaging unit 31, such as the state of the auto gain control function, the value of the gain, and the exposure time, or information on the image sensor 3 itself.

  The storage unit 32 is a semiconductor memory such as a DRAM (Dynamic Random Access Memory), an SDRAM (Synchronous Dynamic RAM), and an EPROM (Erasable Programmable ROM). A program 32b for causing the processor 33 to execute the function, a sensor ID (IDentification) 32c for uniquely identifying the image sensor, and dictionary data 32d are stored.

  At the time of factory shipment, for example, basic dictionary data that can be used only for human detection may be installed by default. When the installation of the image sensor 3 on the site is completed and a service corresponding to the place is started, the required dictionary data 32d also changes. Therefore, in the embodiment, the function of the image sensor 3 is changed or upgraded by, for example, downloading and updating the dictionary data 32d from the maintenance terminal 200. In other words, the functions of the image sensor 3 can be customized according to needs, from general-purpose functions.

The processor 33 implements various functions described in the embodiment by loading and executing a program stored in the storage unit 32. 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 may be configured by an FPGA (Field Programmable Gate Array) or the like. The MPU is also one of the processors.
The communication unit 34 is connectable to the sensor network 100, and mediates data exchange with a communication partner such as the gateway 7, the maintenance terminal 200, and the BEMS server 5. In particular, the communication unit 34 also functions as an acquisition unit that acquires dictionary data corresponding to a dictionary data set corresponding to a requested service.

  By the way, the processor 33 includes a detection unit 33a, a feature data calculation unit 33b, a learning unit 33c, an identification unit 33d, and a determination unit 33e as processing functions according to the embodiment. The detection unit 33a, the feature data calculation unit 33b, the learning unit 33c, the identification unit 33d, and the determination unit 33e are generated in a process in which the processor 33 performs arithmetic processing according to, for example, a program 32b loaded in a register of the processor 33. Is a process.

  The detection unit 33a detects an object in the visual field using the dictionary data 32d. That is, the detection unit 33a detects a target in the target space from the image data 32a using a dictionary data set prepared for each detection item.

  The feature data calculation unit 33b analyzes the image data 32a stored in the storage unit 32 by a predetermined algorithm, and obtains, for example, histograms of oriented gradients (HOG) feature amount, contrast, resolution, and S / N ratio. , Color tone, luminance gradient direction co-occurrence histogram (Co-OCcurrence HOG: Co-HOG) feature amount, Haar-Like feature amount, and the like.

The identification unit 33d identifies the detected target based on the dictionary data.
The determination unit 33e determines what the identified target is.
The learning unit 33c performs learning based on the result of the determination by the determination unit 33e and the image data 32a so as to improve the correct answer rate of the identification result by the identification unit 33d.

  FIG. 11 is a diagram showing an example of a data flow between the functional blocks in FIG. After the image data from the imaging unit 31 is stored in the storage unit 32, it is passed to the detection unit 33a and the learning unit 33c. The detection unit 33a detects a target from the image data, and passes the result to the identification unit 33d. The identification unit 33d identifies the detected target using the dictionary data 32d, and passes the identification score to the determination unit 33e. The determination unit 33e determines what the detected target is based on the identification score, and passes the result to the communication unit 34. The communication unit 34 notifies the BEMS server 5 and the service contractor of the determination result. In addition, the determination result of the target is also passed to the learning unit 33c, and is fed back to the improvement of the identification processing accuracy by the identification unit 33d. Next, the operation of the above configuration will be described.

  FIG. 12 is a sequence chart illustrating an example of a processing procedure between the maintenance terminal 200 and the image sensor 3 regarding distribution of dictionary data. FIG. 12 shows an example of a push-type procedure in which the maintenance terminal 200 mainly transfers dictionary data to the image sensor 3.

  When the distribution time of the dictionary data is set by the timing designation unit 250d of the maintenance terminal 200 (step S10), the maintenance terminal 200 waits for the arrival of the distribution time (step S11). When the distribution time arrives (Yes in S11), the maintenance terminal 200 reads dictionary data from the storage unit 240 for each target image sensor (Step S13), and transmits one or more dictionary data to the target image sensor (Step S13). Step S14).

  Upon receiving the dictionary data (step S50), the image sensor 3 returns an Ack message and its own sensor ID to the maintenance terminal 200 (step S51), and stores the downloaded dictionary data in the storage unit 32 (step S52).

  The maintenance terminal 200 that has received the Ack message (step S15) writes the billing information for the service contractor using the image sensor to which the dictionary data is downloaded to the billing data 240c. The series of steps S13 to S16 (including steps S50 to S52) is repeated until all the target image sensors are completed (loop of steps S12 and S17). When the dictionary data is downloaded to all the target image sensors, the maintenance terminal 200 waits for the update of the dictionary data (Step S18). When the dictionary data is updated (Yes in step S18), the processing procedure returns to step S11.

  FIG. 13 is a sequence chart showing another example of the processing procedure between the maintenance terminal 200 and the image sensor 3 concerning distribution of dictionary data. FIG. 13 shows an example of a pull-type procedure in which the image sensor 3 mainly acquires dictionary data from the maintenance terminal 200. A procedure different from FIG. 12 will be mainly described.

  In FIG. 13, the distribution time of the set dictionary data is notified from the maintenance terminal 200 to the image sensor 3 (step S20). The image sensor 3 notified of the distribution time (step S53) stores the distribution time in the storage unit 32 (S54), and waits for the arrival of the distribution time (step S55). When the distribution time has arrived (Yes in S55), the image sensor 3 transmits a request to acquire dictionary data to the maintenance terminal 200 together with its own sensor ID (step S56).

  When receiving the acquisition request (Yes in step S21), the maintenance terminal 200 transmits dictionary data for the image sensor having the sensor ID to the image sensor that has issued the request (steps S13 and S14). The procedures of steps S50 to S52 and steps S15 to S18 are the same as those in FIG.

  As described above, in the first embodiment, a plurality of dictionary data is stored in the maintenance terminal 200, and a dictionary data set in which dictionary data corresponding to a requested service is set is selected for each image sensor. Then, the distribution time of the dictionary data set can be set by the user using the GUI, and when the distribution time comes, the dictionary data is downloaded from the maintenance terminal 200 to the image sensor in a push-type or pull-type procedure. .

  With this configuration, the dictionary data can be updated even after the installation (installation) of the image sensor 3 is completed. This makes it possible to update the latest functions and flexibly respond to changes in required services.

  In addition, since the user can determine the timing of download, it is possible to avoid data on weekdays when traffic is concentrated and to update data during the night or on holidays when the in-building network 500 is relatively vacant on weekdays. Convenience can be enhanced.

  From these facts, it is possible to provide a sensing system, a maintenance terminal device, a data distribution method, and an image sensor that further improve the usability.

[Second Embodiment] (A form in which dictionary data is installed in a full set on an image sensor)
In the first embodiment, an example can be considered in which dictionary data is downloaded to the image sensor and updated each time the service is changed. In the second embodiment, a form will be described in which a full set of dictionary data is installed in the image sensor in advance, and usable dictionary data is managed on the system side.

  FIG. 14 is a functional block diagram illustrating an example of the maintenance terminal 200 according to the second embodiment. The parts different from FIG. 5 will be mainly described. The processor 250 includes a limiting unit 250g as a processing function according to the second embodiment. The limiting unit 250g can be understood as a process generated during the execution of the program 240a. That is, the program 240a causes the maintenance terminal 200, which is a computer, to operate as the restriction unit 250g.

  FIG. 15 is a functional block diagram illustrating an example of the image sensor 3 according to the second embodiment. The parts different from FIG. 10 will be mainly described. The storage unit 32 of the image sensor 3 stores key data 32e. Further, the image sensor 3 downloads a full set of dictionary data 32d as shown in FIG. 16 from the maintenance terminal 200 and stores the dictionary data 32d in the storage unit 32.

  FIG. 16 is a diagram illustrating an example of the dictionary data 32d stored in FIG. For example, m-series dictionary data (m1 to m5) for "detection of people", C-series dictionary data (C1 to C5) for "chair detection", and O-series dictionary data for "detection of objects" ( O1 to O5), all of the a, b, c, d, and e dictionary data (m1 to m5) for “detection of a specific person” are stored in the storage unit 32 of the image sensor 3 together with the default dictionary data D. You.

  The restricting unit 250g in FIG. 14 restricts the use of the remaining dictionary data so that the dictionary data corresponding to the dictionary data set selected by the selecting unit 250a can be used in the corresponding image sensor. In order to separate the usable / unusable dictionary data from the dictionary data, for example, the key information generated by the key information generating unit 250f may be used. This key information is distributed from the maintenance terminal 200 to the image sensor 3 when a dictionary data set is downloaded, for example, and is stored in the storage unit 32 as key data 32e.

  FIG. 17 and FIG. 18 are diagrams for explaining that usable dictionary data is restricted according to service contents. FIG. 17 shows that when providing the service pack WWW for human detection, only dictionary data D, m1, and m2 can be used, and the other dictionary data is invalidated as [Not Available]. The invalidated data is in a state where the program 32b (application) of the image sensor 3 cannot be used due to the key data 32g.

  FIG. 18 shows the dictionary data for the service pack XXX. In addition to the dictionary data D, m1, and m2, the keys of the dictionary data O1, O2 are released. As a result, not only detection of humans but also of objects becomes a practical brain analysis.

  As described above, in the second embodiment, a full set of dictionary data is installed in the image sensor 3 in advance, and only the dictionary data that is permitted to be used is validated, and the remaining dictionary data is invalidated (not available). I did it. With this configuration, when the service content changes, new key information is generated, and only the key information needs to be distributed to the target image sensor. Therefore, it is not necessary to distribute dictionary data having a relatively large data amount each time, and it is possible to reduce the pressure on resources for communication.

[Third Embodiment] (A form in which occupation can be set in the image sensor)
In the third embodiment, a mode will be described in which a right (occupation right) of occupying and using the image sensor 3 for a certain period is given to a third party so that a new service can be developed.

  FIG. 19 is a block diagram illustrating an example of a sensing system according to the third embodiment of the present invention. Via a gateway 8, a server provided by a service provider (referred to as a vendor server 400) is connected to the in-building network 500.

  FIG. 20 is a functional block diagram illustrating an example of the maintenance terminal 200 according to the third embodiment. The processor 250 includes an exclusive right management unit 250h. The exclusive right management unit 250h is understood as a process generated during the execution of the program 240a, and the program 240a causes the maintenance terminal 200, which is a computer, to operate as the exclusive right management unit 250h.

  The exclusive right management unit 250h manages the exclusive right of the image sensor. For example, a fixed period is set in the same manner as described with reference to FIGS. 7 to 9, and all or a part of the image sensors 3-1 to 3-n are provided to the service provider having the vendor server 400 over the period. Give the right to occupy.

  Then, the image sensor 3 given the exclusive right is provided with an opportunity to download private dictionary data from the vendor server 400 and provide a unique service based on the dedicated dictionary data. Then, the charging unit 250c performs a charging process on the occupation right, and stores charging data for the service provider in the storage unit 200 of the maintenance terminal 200 (charging data 240c).

  Alternatively, as described in the second embodiment, the exclusive right to the image sensor that stores the full set of dictionary data is set, and the key data 32e shown in the storage unit 32 of FIG. In the same manner as described above, usable dictionary data / unusable dictionary data may be distinguished. By giving the key data 32e itself an expiration date, it is possible to set an expiration date of the exclusive right.

  Note that the distribution unit 250b of the maintenance terminal 200 may execute a process for distributing the dictionary data set to the image sensor permitted to be occupied from the vendor server 400 of the service provider to which the occupation right has been given.

  As described above, in the third embodiment, the exclusive right to occupy the image sensor 3 is given to the service provider of the third party so that the exclusive right can be charged. By doing so, it is possible to provide a variety of services.

Note that the present invention is not limited to the above embodiment.
For example, the term full set in the second embodiment does not necessarily mean all dictionary data. In short, a large number of dictionary data may be collectively transferred to the image sensor as far as the system request allows. By appropriately setting the transfer timing, it is possible to suppress resources such as transmission channel capacity from being squeezed as much as possible.

  In the first embodiment, the image sensors 3 are grouped for each tenant, and the download timing of dictionary data and the like are managed in units of groups. However, this is an example. Of course, it is also possible to individually set the download timing of the dictionary data for each image sensor 3. In addition, it is possible to manage the image sensors 3 in an arbitrary unit.

  The dictionary data is not always downloaded from the maintenance terminal 200 to all image sensors. For example, when the dictionary data is updated, only one image sensor for each group (or tenant) communicates with the maintenance terminal 200, and the acquired dictionary data is distributed as image data in the group, for example, in a relay format. May be.

  Furthermore, at least a part of the function of the sensing system of the embodiment may be configured by a cloud server device. That is, at least a part of the processing executed by the sensing system of the embodiment may be executed by cloud computing.

  FIG. 22 is a diagram illustrating a mode in which some functions are transferred to the cloud 600. The maintenance terminal 200 can communicate with the cloud 600 via the firewall 6 connected to the in-building network 500, and transfer some or all of the functions shown in FIGS. 5, 14, and 20 to the cloud 600. It is possible to

  This cloud computing includes SaaS (Software as a Service) that provides an application (software) as a service, PaaS (Platform as a Service) that provides a platform (platform) for operating the application as a service, At least one of IaaS (Infrastructure as a Service) that provides resources such as a server device, a central processing unit, and a storage as a service (public cloud) may be included. For example, the cloud computing may include remote operation via the Internet by a cloud service providing layer (PaaS). Then, the maintenance terminal 200 or the BEMS server 5 may be a cloud server.

  FIG. 23 is a diagram illustrating an example in which the functions according to the first embodiment are installed in the BEMS server 5 instead of the maintenance terminal 200. It goes without saying that the effect of the present invention can be obtained even in this case. The same applies to the second embodiment and the third embodiment. Further, some or all of the functions shown in FIG. 23 can be transferred to the cloud 600.

In addition, functions and effects in the embodiment of the present invention will be listed.
-The function restriction and schedule of the full-function dictionary of the image sensor shall be instructed from the host system to the image sensor.

  The dictionary of the image sensor can be updated by setting a dictionary to be downloaded and a schedule for each image sensor or each group.

  -Provide a function to distribute the dictionary to the image sensor on the host system side. It has a function and a setting screen that can set a dictionary to be delivered and a delivery schedule for each image sensor or each group.

  When updating the dictionary of the image sensor, it is assumed that the user can arbitrarily create a dictionary and distribute the dictionary directly to the image sensor using a maintenance PC terminal or the like.

  -With respect to the image sensor having the above functions, there is provided a mechanism for charging the user according to the dictionary function used (restriction of full-function software, addition / update of arbitrary functions). It is also assumed that the user has a mechanism that allows a user to occupy a specific group of image sensors for a fee.

  Regarding billing, there is a table indicating what dictionary function is assigned to each image sensor or each group in association with the contractor ID (or tenant ID), and this table transmits new dictionary data. The billing table updated at the timing and associated with the contractor ID (or tenant ID) is updated. Alternatively, the charging timing is performed when a response indicating that the update has been completed without any problem is received from the image sensor. It is assumed that a higher-level system has a mechanism for monitoring such charging timing.

  Here, the case where the number of the processor 33 and the storage unit 32 is one is described, but two or more processors and the storage unit may be provided. As an example, a case in which first and second processors are provided will be described. The first processor is a processor dedicated to image recognition capable of realizing image recognition at high speed, and has a function of a detecting unit 33a, a feature data calculating unit 33b, a learning unit 33c, an identifying unit 33d, and a determining unit 33e in FIG. It is possible to access a high-speed storage unit such as a DRAM that can read and write at high speed. The second processor is a general-purpose processor, has a function of storing, managing, and communicating image processing results recognized by the first processor, and is capable of accessing a large-capacity storage unit such as a flash memory.

  In this case, the dictionary data 32d is stored in a large-capacity storage unit accessible by the second processor, and the dictionary data D, m1, m2, O1, and O2 are stored. A dictionary data selection unit (not shown) executed by the first processor or the second processor selects dictionary data used by the first processor from dictionary data stored in the large-capacity storage unit. , And the first processor executes a predetermined operation.

  By using the processor dedicated to image recognition as described above, high-speed image processing can be realized, and it can be realized even when a high-speed response due to the presence or absence of a person or operation such as lighting control is required. Further, even when the detection target is changed with the change of the service pack, it is not necessary to rewrite the dictionary data 32d, and the detection target can be changed only by changing the target selected by the dictionary data selection unit. .

  While some embodiments of the present invention have been described, these embodiments are provided by way of example only and are not intended to limit the scope of the inventions. These new embodiments can be implemented in other various 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 their equivalents.

  1 (1-1, 1-2) ... lighting equipment, 2 ... air conditioning equipment, 3 (3-1 to 3-n) ... image sensor, 4 ... controller, 5 ... BEMS server, 6 ... firewall, 7, 8 ... Gateway, 10 ... Building, 15 ... Processor, 30 ... Register, 30a ... Camera information, 31 ... Imaging unit, 31a ... Fisheye lens, 31b ... Aperture mechanism, 31c ... Imaging element, 32 ... Storage unit, 32a ... Image data, 32b ... program, 32d ... dictionary data, 32e ... key data, 32g ... key data, 33 ... processor, 33a ... detection unit, 33b ... characteristic data calculation unit, 33c ... learning unit, 33d ... identification unit, 33e ... judgment unit, 34 ... Communication unit, 35 ... Internal bus, 41 ... Air-conditioning controller, 42 ... Elevator controller, 43 ... Security controller, 44 ... Disaster prevention controller, 45 ... Lighting controller , 70 ... database, 80 ... server, 100 ... sensor network, 200 ... maintenance terminal, 210 ... monitor, 220 ... ROM, 230 ... RAM, 240 ... storage unit, 240 a ... program, 240 b ... dictionary data, 240 c ... billing Data, 250 processor, 250a selection section, 250b distribution section, 250c billing section, 250d timing designation section, 250e period designation section, 250f key information generation section, 250g restriction section, 250h exclusive right Management unit 260 260 optical media drive 270 communication unit 300 communication network 400 vendor server 500 building network 600 cloud

Claims (27)

An image sensor that detects an object using a dictionary data set prepared for each detection item;
A data server for storing a plurality of dictionary data,
Selecting means for selecting a dictionary data set according to the requested service for each image sensor;
A distribution unit configured to distribute dictionary data corresponding to the selected dictionary data set from the data server to the image sensor. An image sensor that detects an object using a dictionary data set prepared for each detection item;
A data server for storing a plurality of dictionary data,
Distribution means for distributing a full set of dictionary data from the data server to the image sensor;
Selecting means for selecting a dictionary data set according to the requested service for each image sensor;
A limiting unit that enables dictionary data corresponding to the selected dictionary data set to be used in the image sensor. An image sensor that detects an object using a dictionary data set prepared for each detection item;
Management means for managing the exclusive right of the image sensor;
A distribution unit for distributing dictionary data corresponding to the dictionary data set from the data server of the entity to which the exclusive right has been given to the image sensor.   The sensing system according to claim 1, wherein the distribution unit transfers the dictionary data from the data server to the image sensor in a push-type procedure.   4. The sensing system according to claim 1, wherein the distribution unit acquires the dictionary data from the data server by a pull-type procedure using the image sensor. 5. A timing specification unit for specifying a distribution timing of the dictionary data,
The sensing system according to claim 1, wherein the distribution unit distributes the dictionary data at the designated timing.   3. The sensing system according to claim 1, further comprising a billing processing unit that manages billing information for billing a subscriber of the service. 4.   The sensing system according to claim 7, wherein the selection unit selects the dictionary data based on a billing plan for the requested service. The image sensor is installed in a building including a plurality of tenants,
The sensing system according to claim 1, wherein the selection unit selects the dictionary data for each tenant. A period designation unit for designating a period during which the dictionary data can be used by the restriction unit;
Key information generating means for generating key information for validating the dictionary data in the designated period,
3. The sensing system according to claim 2, wherein the distribution unit distributes the generated key information to a target image sensor. A period designation means for designating a validity period of the exclusive right;
Key information generating means for generating key information for validating the dictionary data during the validity period,
The sensing system according to claim 3, wherein the distribution unit distributes the generated key information to a target image sensor. A maintenance terminal device applicable to a sensing system having a plurality of image sensors,
A storage unit that stores dictionary data used in the image sensor;
A processor that functions based on the program,
The processor comprises:
A selection unit that selects a dictionary data set corresponding to the requested service for each of the image sensors;
A maintenance terminal device, comprising: a distribution unit that distributes dictionary data corresponding to the selected dictionary data set from the storage unit to the image sensor. A maintenance terminal device applicable to a sensing system having a plurality of image sensors,
A storage unit that stores dictionary data used in the image sensor;
A processor that functions based on the program,
The processor comprises:
A distribution unit that distributes a full set of dictionary data to the image sensor;
A selection unit that selects a dictionary data set corresponding to the requested service for each of the image sensors;
A maintenance terminal device comprising: a limiting unit that enables dictionary data corresponding to the selected dictionary data set to be used in the image sensor. A maintenance terminal device applicable to a sensing system having a plurality of image sensors,
A storage unit that stores dictionary data used in the image sensor;
A processor that functions based on the program,
The processor comprises:
A management unit that manages the exclusive right of the image sensor;
A maintenance unit, comprising: a distribution unit configured to distribute a dictionary data set from the data server of the entity to which the exclusive right has been given to the image sensor.   The maintenance terminal device according to claim 12, wherein the distribution unit transfers the dictionary data to the image sensor in a push-type procedure. The processor comprises:
A timing designation unit for designating a distribution timing of the dictionary data,
The maintenance terminal device according to any one of claims 12 to 14, wherein the distribution unit distributes the dictionary data at the designated timing.   14. The maintenance terminal device according to claim 12, further comprising a charging processing unit that manages charging information for charging a subscriber of the service.   The maintenance terminal device according to claim 17, wherein the selection unit selects the dictionary data based on a billing plan for the requested service. When the image sensor is installed in a building including a plurality of tenants,
The maintenance terminal device according to claim 12, wherein the selection unit selects the dictionary data for each tenant. A period designation unit for designating a period during which the dictionary data can be used by the restriction unit;
A key information generation unit that generates key information for validating the dictionary data in the specified period,
14. The maintenance terminal device according to claim 13, wherein the distribution unit distributes the generated key information to a target image sensor. A period designation unit for designating a validity period of the exclusive right;
A key information generation unit that generates key information that validates the dictionary data during the validity period,
The maintenance terminal device according to claim 14, wherein the distribution unit distributes the generated key information to a target image sensor. A data distribution method applicable to a sensing system including an image sensor that detects an object using a dictionary data set prepared for each detection item,
A step in which the computer selects a dictionary data set corresponding to the requested service for each image sensor;
Distributing dictionary data corresponding to the selected dictionary data set from a data server storing a plurality of dictionary data to the image sensor. A data distribution method applicable to a sensing system including an image sensor that detects an object using a dictionary data set prepared for each detection item,
A step of distributing a full set of dictionary data to the image sensor from a data server storing a plurality of dictionary data,
A step in which the computer selects a dictionary data set corresponding to the requested service for each image sensor;
Making the computer use dictionary data corresponding to the selected dictionary data set in the image sensor. A data distribution method applicable to a sensing system including an image sensor that detects an object using a dictionary data set prepared for each detection item,
A step in which a computer manages the exclusive right of the image sensor;
A computer distributing dictionary data corresponding to the dictionary data set from the data server of the entity to which the exclusive right has been given to the image sensor. An imaging unit that captures image data by capturing an image of a target space;
Using a dictionary data set prepared for each detection item, a detection unit that detects a target in the target space from the image data,
An acquisition unit that acquires dictionary data corresponding to a dictionary data set corresponding to the requested service;
An image sensor comprising: a storage unit that stores the acquired dictionary data. An imaging unit that captures image data by capturing an image of a target space;
A storage unit for storing a full set of dictionary data;
A detection unit that detects a target in the target space from the image data using dictionary data corresponding to a dictionary data set selected according to a requested service. An image sensor,
An imaging unit that captures image data by capturing an image of a target space;
Using a dictionary data set prepared for each detection item, a detection unit that detects a target in the target space from the image data,
An acquisition unit that acquires dictionary data from an entity that has been set the exclusive right to its own sensor;
An image sensor comprising: a storage unit that stores the acquired dictionary data.