JP7448722B2 - Cleaning status detection system - Google Patents

Description

The present invention relates to a cleaning situation detection system, and particularly to a cleaning situation detection system that can automatically determine the cleaning situation.

Conventionally, the main method for understanding the cleaning status has been for a cleaner or manager to visually confirm the cleaning details. On the other hand, in recent years, behavior analysis techniques using deep learning techniques and the like have been developed. By automatically analyzing people's behavior from surveillance camera images, it is used to support surveillance operations and monitor elderly people by detecting abnormal behavior.

Further, Patent Document 1 discloses a system that monitors forest fires using a plurality of visible cameras.

Japanese Patent Application Publication No. 2013-196655

However, when checking the cleaning content visually, it is difficult to visually determine whether cleaning has been performed or not, and there are cases in which confirmation is omitted, or in which detailed cleaning details cannot be confirmed. On the other hand, with conventional deep learning technology, the detection of human behavior is mainly focused on detecting abnormal behavior, and there have been no examples of detection systems that can grasp cleaning status. Further, Patent Document 1 describes a technology for forest fire monitoring, and this technology cannot be directly applied to detecting cleaning conditions.

SUMMARY OF THE INVENTION In view of the above problems, an object of the present invention is to provide a cleaning status detection system that can automatically determine cleaning status.

In order to achieve the above object, one of the typical cleaning status detection systems of the present invention includes an imaging device and an image processing device, and the image processing device detects cleaning conditions based on images taken by the imaging device. The present invention is characterized by comprising an image determination unit that determines the cleaning status in the image by identifying a person who is cleaning the person and identifying a cleaned area based on the actions of the cleaner.

According to the present invention, the cleaning status detection system can automatically determine the cleaning status using images, so it is possible to solve problems such as failure to visually confirm the presence or absence of cleaning and inability to properly confirm the cleaning status. .
Problems, configurations, and effects other than those described above will be clarified by the following embodiments.

FIG. 1 is a block diagram showing an embodiment of the cleaning situation detection system of the present invention. FIG. 2 is a block diagram showing an example of the image processing device shown in FIG. FIG. 3 shows a first example of a display screen on a display device in the cleaning situation detection system of the present invention. FIG. 4 shows a second example of the display screen on the display device in the cleaning situation detection system of the present invention. FIG. 5 is a flowchart showing an example of the entire process in the cleaning situation detection system of the present invention. FIG. 6 is a flowchart showing an example of cleaning status determination processing in the cleaning status detection system of the present invention. FIG. 7 is a conceptual diagram showing an example of detection in the cleaning situation detection system of the present invention. FIG. 8 is a conceptual diagram showing an example of detection of determination processing in the cleaning state detection system of the present invention. FIG. 9 is a conceptual diagram showing an example of a non-detection case in the determination process in the cleaning state detection system of the present invention.

A mode for carrying out the present invention will be described.

FIG. 1 is a block diagram showing an embodiment of the cleaning situation detection system of the present invention. The cleaning situation detection system shown in FIG. 1 includes an imaging device 1, an image processing device 10, an image recording device 21, a display device 22, and a printing device 23. These are each connected to a network 30.

The imaging device 1 includes a camera configuration and can be placed in various locations. For example, it may be placed as a surveillance camera at a monitoring location. The imaging device 1 can have a camera configuration that obtains information by forming an image of incident light on an image sensor through a lens or an aperture. Examples of the image sensor here include a CCD (Charge-Coupled Device) image sensor, a CMOS (Complementary Metal Oxide Semiconductor) image sensor, and the like. The imaging device 1 captures video at, for example, 3 frames per second (3 fps) or more, and the information is sent to the image processing device 10 and the image recording device 21. A plurality of imaging devices 1 can be installed depending on the situation.

The image processing device 10 includes the functions of a control section 11 , a user interface section 12 , a report creation section 13 , an image judgment section 14 , and an image judgment recording section 15 .

The control unit 11 is capable of exchanging information with the network 30 and controls the user interface unit 12 , report creation unit 13 , image determination unit 14 , and image determination recording unit 15 . The user interface unit 12 performs processing such as accepting information input or operated by a user, such as the display device 22 . The report creation unit 13 performs processing to create reports such as daily reports. The image determination unit 14 performs image determination processing, which will be described later, using information captured by the imaging device 1. The image judgment recording section 15 records the contents based on the result of the judgment processing performed by the image judgment section 14 . For example, when the user interface section 12 acquires a signal regarding completion of cleaning or report creation from the display device 22, the report creation section 13 automatically creates a report based on the determination result of the image determination section 14 and records it in the image determination recording section 15. Record.

The image recording device 21 is a device that records images captured by the imaging device 1. Furthermore, images and results processed by the image processing device 10 may be recorded. As the image recording device 21, an appropriate system can be applied as needed, such as a HDD (Hard Disk Drive), an SSD (Solid State Drive), or a DDS (Digital Data Storage).

The display device 22 is a device that can display the content processed by the image processing device 10. For example, the information is displayed using a liquid crystal display (LCD), an organic EL (OEL) display, a touch panel, or the like. The number of display devices 22 can be used as required. Further, the display device 22 may be provided with operation buttons.

The printing device 23 is a device capable of printing the display contents on the display device 22 and information on the image processing device 10, and is provided as necessary.

The network 30 is a line that connects each device and allows data communication. It is applicable regardless of the type of line, such as a leased line, an intranet, or an IP network such as the Internet.

FIG. 2 is a block diagram showing an example of the image processing device shown in FIG. A specific example of the hardware configuration of the image processing apparatus 10 will be explained using the computer system 300 in FIG.

The main components of computer system 300 include one or more processors 302 , memory 304 , terminal interface 312 , storage interface 314 , I/O (input/output) device interface 316 , and network interface 318 . These components may be interconnected via memory bus 306, I/O bus 308, bus interface 309, and I/O bus interface 310.

Computer system 300 may include one or more processing devices 302A and 302B, collectively referred to as processor 302. Each processor 302 executes instructions stored in memory 304 and may include onboard cache. Examples of the processing device include a CPU (Central Processing Unit), an FPGA (Field-Programmable Gate Array), a GPU (Graphics Processing Unit), and a DSP (Digital Signal Processing Unit). (occessor) etc. can be applied.

Memory 304 may include random access semiconductor memory, storage devices, or storage media (either volatile or nonvolatile) for storing data and programs. Memory 304 also represents the entire virtual memory of computer system 300 and may include virtual memory of other computer systems connected to computer system 300 via a network. Although memory 304 may be conceptually considered a single entity, it may be a more complex arrangement, such as a hierarchy of caches and other memory devices.

Memory 304 may store all or some of the programs, modules, and data structures that implement the functions described in this embodiment. For example, memory 304 may store application 350. Application 350 may include instructions or writings that perform functions described below on processor 302, or may include instructions or writings that are interpreted by other instructions or writings. Application 350 may be implemented in hardware via semiconductor devices, chips, logic gates, circuits, circuit cards, and/or other physical hardware devices instead of or in addition to processor-based systems. may be done. Application 350 may include data other than instructions or descriptions. Other data input devices, such as cameras and sensors, may also be provided to communicate directly with bus interface 309, processor 302, or other hardware of computer system 300.

Computer system 300 may include a bus interface 309 that provides communication between processor 302 , memory 304 , display system 324 , and I/O bus interface 310 . I/O bus interface 310 may couple with I/O bus 308 for transferring data to and from various I/O units. I/O bus interface 310 connects multiple I/O interfaces 312, 314, 316, and 318, also known as I/O processors (IOPs) or I/O adapters (IOAs), via I/O bus 308. You may communicate with Display system 324 may include a display controller, display memory, or both. A display controller may provide video, audio, or both data to display device 326. Computer system 300 may also include devices, such as one or more sensors, configured to collect data and provide the data to processor 302. Display system 324 may be connected to a display device 326, such as a standalone display screen, a television, a tablet, or a handheld device. Display device 326 may include speakers for rendering audio. Alternatively, a speaker for rendering audio may be connected to the I/O interface. Alternatively, the functionality provided by display system 324 may be implemented by an integrated circuit that includes processor 302. Similarly, the functionality provided by bus interface 309 may be implemented by an integrated circuit that includes processor 302.

The I/O interface provides the ability to communicate with various storage or I/O devices. For example, terminal interface 312 may include a user output device such as a video display device, a speaker television, or a user input device such as a keyboard, mouse, keypad, touch pad, trackball, buttons, light pen, or other pointing device. User I/O devices 320 can be attached. Using the user interface, a user operates a user input device to input input data and instructions to user I/O device 320 and computer system 300, and to receive output data from computer system 300. Good too. The user interface may be displayed on a display device or played through a speaker via user I/O device 320, for example.

Storage interface 314 is capable of attaching one or more disk drives or direct access storage devices 322 . Storage device 322 may be implemented as any secondary storage device. The contents of memory 304 may be stored in storage device 322 and read from storage device 322 as needed. I/O device interface 316 may provide an interface to other I/O devices. Network interface 318 may provide a communication pathway so that computer system 300 and other devices can communicate with each other. This communication path may be, for example, network 330.

Although computer system 300 includes a bus structure that provides a direct communication path between processor 302, memory 304, bus interface 309, display system 324, and I/O bus interface 310, computer system 300 has a hierarchical configuration. , star, or web configurations, multiple hierarchical buses, and parallel or redundant communication paths. Further, although I/O bus interface 310 and I/O bus 308 are shown as a single unit, in reality, computer system 300 may include multiple I/O bus interfaces 310 or multiple I/O buses 308. may be provided. Also, although multiple I/O interfaces are shown to separate I/O bus 308 from various communication paths leading to various I/O devices, some or all of the I/O devices may It may also be connected directly to the system I/O bus.

Computer system 300 may be a device that receives requests from other computer systems (clients) without a direct user interface, such as a multi-user mainframe computer system, a single-user system, or a server computer.

When the computer system 300 in FIG. 2 is applied to the image processing apparatus 10 in FIG. 1, the display system 324 and the display device 326 have an arbitrary configuration, and may or may not be included. Further, the display device 326 may be provided as a display device similar to the display device 22 in addition to the display device 22. Further, a display device 326 may be provided instead of the display device 22. Further, the storage device 322 can be applied to the image determination recording section 15. Furthermore, a storage device 322 may be provided in place of the image recording device 21. Further, the network 330 can be applied as the network 30.

FIG. 3 shows a first example of a display screen on a display device in the cleaning situation detection system of the present invention. FIG. 4 shows a second example of the display screen on the display device in the cleaning situation detection system of the present invention.

A display screen 100 shows the display screen on the display device 22 of FIG. The examples in FIGS. 3 and 4 show display examples when a touch panel configuration is applied to the display screen 100.

On the display screen 100, a cleaning status screen 120 is displayed. Furthermore, the display screen 100 displays a cleaning start button 101, a cleaning end button 102, an imaging device area button 103, a cleaning status update button 104, and a report creation button 105 as buttons. When these buttons are touched, the information is sent to the user interface unit 12 of the image processing device 10 via the network 30 shown in FIG. Then, the image processing device 10 performs processing according to the sent information. The display screen 100 is configured to display information such as a cleaning start date and time 111, a cleaning end date and time 112, camera identification information 113, and a report creation date and time 114.

When the cleaner starts cleaning, when the cleaner touches the cleaning start button 101, the time is recorded and the date and time is displayed in the cleaning start date and time 111. Furthermore, when the cleaner touches the cleaning end button 102 when the cleaning is finished, the time is recorded and the date and time is displayed in the cleaning end date and time 112. The information is also sent to the image processing device 10.

The camera identification information 113 displays identification information of the imaging device 1 that is photographing the image displayed on the cleaning status screen 120. The identification information can be expressed as a code such as a number, and can specify which camera the image was taken with. Furthermore, by touching the imaging device area button 103, it is possible to change to another imaging device 1. When changing to another imaging device 1, the code display of the camera identification information 113 is changed, and the cleaning status screen 120 is displayed on the cleaning status screen 120 based on the image of the other imaging device 1 that has been switched.

When the cleaner touches the cleaning status update button 104, the status is reflected on the cleaning status screen 120. The report creation button 105 is a button for creating a report. When the cleaner (or administrator) touches this button, the time is recorded and the date and time is displayed in the report creation date and time 114. The information is also sent to the image processing device 10. The report is created as a report containing information on the display screen 100 at this time.

On the cleaning status screen 120, an image photographed by the imaging device 1 is displayed, and the image is partially processed and displayed so that the cleaned area 121 and the uncleaned area 122 can be seen. For example, the cleaned area 121 is displayed in a light color, shaded with light shading, or surrounded by a frame of a specific color so that the person checking it can understand, and the uncleaned area 122 is not processed in any way. It is. Of course, a display may be displayed in the uncleaned area 122 to distinguish it from the cleaned area 121. These image processes can be performed using information based on the determination results of the image processing device 10, which will be described later.

FIG. 3 shows a state in which a cleaner is performing cleaning work by touching the cleaning start button 101. Therefore, no information is displayed in the cleaning end date and time 112 and the report creation date and time 114. FIG. 4 shows a state in which the cleaner has finished the cleaning work and touched the cleaning end button 102 to end the cleaning. Furthermore, the cleaner (or administrator) touches the report creation button 105 to create a report. Therefore, information on the cleaning end date and time 112 and the report creation date and time 114 are displayed.

FIG. 5 is a flowchart showing an example of the entire process in the cleaning situation detection system of the present invention. The processing here is performed by the image processing device 10 shown in FIG.

When the process is started (S101), a cleaning status determination process is first performed (S102). The process is started, for example, when information about the touch of the cleaning start button 101 in FIGS. 3 and 4 is sent from the display device 22 to the image processing device 10, and the user interface unit 12 recognizes this fact. The cleaning status determination process will be explained with reference to FIG.

Next, when the cleaning status determination process is completed, a cleaning status update process (S103) is performed. This is a process of updating cleaning status information according to the result of the cleaning status determination process.

Next, it is determined whether the cleaning has been completed (S104). If it is determined that the cleaning has been completed, the process advances to S105, and if it is determined that the cleaning has not been completed, the process returns to the cleaning status determination process of S102. The determination here is made, for example, based on whether or not the information that the cleaning end button 102 in FIGS. be exposed. That is, if the cleaning end button 102 is touched, it is determined that the cleaning has been completed, and if it is not touched, it is determined that the cleaning is not completed.

In S105, it is determined whether report creation is incomplete (S105). If it is determined that the report creation is incomplete, the process advances to S106, and if it is determined that the report creation is not incomplete, the process advances to S107. The determination here can be made based on whether or not a report has been created before this. For example, it is assumed that after the cleaner finishes cleaning and presses the report creation button 105 in FIGS. 3 and 4, the cleaner touches the cleaning start button 101 again to resume additional cleaning work. When the cleaner touches the cleaning end button 102 after completing additional cleaning, the process proceeds to S107 because a report has already been created. This determination can be made based on whether the report was created within a certain predetermined time.

In S106, a report creation process is performed, and then the process ends (S109). This process is performed by the report creation unit 13 of the image processing device 10. For example, the report shown in FIG. 4 can be created as this report.

In S107, it is determined whether or not to update the report (S107). If it is determined that the report should be updated, the process advances to S108, and if it is determined that the report is not to be updated, the process advances to S109 and the process ends. The determination here is, for example, if there is a report that has already been created, it is displayed and it is confirmed whether or not to update it. When the cleaner touches the corresponding button, the information is sent from the display device 22 to the image processing device 10. When the user interface unit 12 recognizes this, it is determined that the update is to be performed.

In S108, a report creation process is performed, and then the process ends (S109). The processing here is similar to S106, but an updated report is created.

FIG. 6 is a flowchart showing an example of cleaning status determination processing in the cleaning status detection system of the present invention. Here, specific processing of the cleaning status determination processing in S102 shown in FIG. 5 is shown. These processes are performed by the image determination unit 14 of the image processing apparatus 10 in FIG. 1 unless otherwise specified.

When the cleaning status determination process is started (S201), first, a person detection process is performed (S202). This is a process for identifying a person who is a cleaner based on an image captured by the imaging device 1. To determine whether the person is the relevant person, a known person detection mechanism may be used, or inference processing may be performed using AI (Artificial Intelligence) based on the person's characteristics and movements. The inference process here is, for example, a process of extracting feature amounts using a neural network, deep learning, or the like. For example, a cleaner can be identified based on movement in the video. In addition to this, in order to make it easier to identify the cleaner, processing may be performed to identify the uniform worn by the cleaner. This identifies the person as a cleaner based on the uniform's overall design, armbands, marks, and other features of the uniform. Further, the determination may be made by combining characteristics such as movement and uniform. Then, the identified cleaner may obtain an image of the skeleton within the image, for example, as described later with reference to FIG. This makes it easier to identify the movements of the cleaner. The identification process for uniforms, etc. may also be performed using the above-mentioned AI inference process.

Next, detection area determination processing is performed (S203). Here, the area for determining cleaning is determined. For this determination, for example, a range may be determined in advance. If the imaging device 1 is a fixed camera such as a surveillance camera, the range can be determined in advance because the imaging range does not move. In addition to this, the detection area may be determined by performing identification processing from the image of the imaging device 1. In the case of handrails, desk tops, tables, etc., it is possible to identify detection areas that require cleaning based on their characteristics. Additionally, walls, passages, etc. can also be identified as detection areas. In addition to this, the cleaning range may be determined based on past cleaning situations. A cleaning person records the areas that have been cleaned in the past, and the detection area can be identified from the contents. These identification processes may be performed using the above-mentioned AI inference process.

Next, detected feature amount extraction processing is performed (S204). The feature amount here is a process for extracting the feature amount necessary for the next cleaning determination process. For example, by extracting the movement of the identified person as a feature quantity, it can be used in the cleaning determination process. Furthermore, by extracting cleaning tools as feature quantities, the accuracy of cleaning determination processing can be increased. Examples of cleaning tools include various tools used for cleaning, such as rags, mops, brooms, brushes, sponges, and vacuum cleaners.

Next, cleaning determination processing is performed (S205). In this determination, the cleaning area is determined for the detection area specified in S203 using the feature amount extracted in S204. Whether cleaning is being performed or not can be determined by setting predetermined conditions. For example, it can also be performed using the above-mentioned AI inference processing. In this case, based on the feature extracted in S204, if the confidence level that the action performed by the cleaner identified in S202 corresponds to cleaning is higher than a predetermined level, it is determined that the cleaning person is cleaning. . At this time, it is determined whether the detection area has been cleaned by comparing the extracted feature amount with the feature amount of the dataset trained in advance. Further, whether a specific cleaning tool is used can be used as a material for determination, and if the tool used for a cleaning area is different from the specified one, it can be determined that cleaning is not being performed. Furthermore, the moving direction of the cleaning tool may be taken into consideration. A specific example of specifying the cleaning range will be described later with reference to FIGS. 8 and 9.

Furthermore, in S205, it is determined whether cleaning has been completed for the detection area. If cleaning has been completed for a detection area that requires cleaning, it is determined that cleaning in this imaging range has been completed. Furthermore, if there is an uncleaned area in the detection area that requires cleaning, that area is identified and determined to be uncleaned.

Next, a determination result recording process is performed (S206). The result of the cleaning determination process in S205 is recorded in the image determination recording section 15. This content is, for example, the content of the cleaning status screen 120 shown in FIGS. 3 and 4. Furthermore, these determination results can also be reflected on the map. If the location of each imaging device 1 is specified in advance, it can be compared with map information of a specific area such as inside a building and kept as a record, for example. This makes it possible to visually understand where cleaning has been completed and where there are uncleaned parts.

Next, it is determined whether the determination has been completed (S207). If the determination process has been completed for the current image from the imaging device 1, the process advances to S208 and the cleaning status determination process ends. Furthermore, if the determination process has not been completed, the process returns to S202.

FIG. 7 is a conceptual diagram showing an example of detection in the cleaning situation detection system of the present invention.

The cleaning person C001 is identified by the person detection process in S202 of FIG. As shown in FIG. 7, by forming a skeletal model through the person detection process, analysis for identifying a person can be easily performed. A skeletal model is a simplified model in which the joints are rotatable nodes and the joints are connected with lines.

The moving direction F001 and the cleaning tool K001 are specified by the detection feature extraction process in S204 of FIG. 6. In the example of FIG. 7, a diagram is shown in which a cleaning tool K001 held by a cleaner C001 is moved in a moving direction F001 in an uncleaned area 122a. The image determination unit 14 of the image processing device 10 detects this state and determines that the uncleaned area 122a has been cleaned. Note that it is also possible to make the determination by detecting the state of the cleaner C001's hand in the moving direction F001 without detecting the cleaning tool K001.

By making these determinations, it becomes possible to determine the cleaned range 121 and the uncleaned range 122, as shown in FIG. The results can be displayed on the cleaning status screen 120 of the display device 22.

FIG. 8 is a conceptual diagram showing an example of detection of determination processing in the cleaning state detection system of the present invention. FIG. 9 is a conceptual diagram showing an example of a non-detection case in the determination process in the cleaning state detection system of the present invention.

8 and 9 show an example of the cleaning determination process in S205 of FIG. 6. The detection area 150, which is the range that requires cleaning, is subdivided using grid lines or the like. As a result, a plurality of divided small areas 151 exist. The number of small regions 151 may be divided into four or more, or ten or more, depending on the situation, for example.

In the examples shown in FIGS. 8 and 9, in the cleaning determination process, it is determined whether or not cleaning has been performed based on two elements: the cleaning direction and the range. That is, if the moving direction of the cleaning tool K001 is within a predetermined direction range and it is determined that all of the small area 151 has been cleaned, it is determined that the small area 151 has been cleaned. Here, the predetermined direction is, for example, a direction in which the cleaning tool K001 is moved from a certain direction to a predetermined direction. These conditions can be set in advance, or can be determined by the above-described inference processing using AI.

In FIG. 8, the moving direction F001 of the cleaning tool K001 is a predetermined direction, and all of the small areas 151 on the left side of the detection small area A001 are cleaned. Therefore, all of these areas are determined to have been cleaned. Thereby, the image processing device 10 detects that cleaning has been performed.

In FIG. 9, the moving direction F001 of the cleaning tool K001 is not a constant direction but meandering, so the moving direction F001 does not satisfy the predetermined conditions. Therefore, even if there is a small area 151 through which the cleaning tool K001 has passed, all the small areas 151 on the left side of the detection small area A001 are determined to be uncleaned. As a result, the image processing device 10 does not detect that cleaning has been performed.

(effect)
As described above, in this embodiment, the cleaning situation can be accurately grasped by analyzing the behavior of the cleaner based on the information from the imaging device 1. Furthermore, more accurate determination is possible by using inference processing using AI. At this time, since the imaging device 1 can be used in common with an existing surveillance camera, the system becomes inexpensive and easy to construct. Furthermore, since a report can be created based on the display on the display device 22, the reporting burden on the cleaner can be reduced. Further, since the cleaning status can be shared on the display screen 100, it is possible to grasp the cleaning status from a remote location. At this time, it is possible to display the uncleaned areas in an easy-to-understand manner on the cleaning status screen 120 of the display screen 100, thereby constructing an easy-to-understand configuration.

Furthermore, as shown in FIG. 7, by using a skeleton model, the cleaning determination process can be easily performed. Furthermore, as shown in FIGS. 8 and 9, accurate cleaning determination processing is possible based on the cleaning direction and range. In this case, it is also possible to accurately determine, for example, whether the cleaning direction is appropriate for cleaning, such as the direction of cleaning to prevent the spread of viruses.

(Modified example of embodiment)
As a modification of the embodiment, an infrared camera may be used in the imaging device 1 to measure the surface temperature of the object to be cleaned. When alcohol, water, etc. are used during cleaning, the surface temperature is likely to decrease due to the heat of vaporization. Information on such surface temperature changes is taken into account and used in the extraction of feature quantities in S204 of FIG. 6 and the cleaning determination process in S205. In this case, cleaning determination processing can be performed by adding information regarding the surface temperature of the object to be cleaned during cleaning to the feature amount. This enables more accurate cleaning determination.

Alternatively, a sensor capable of measuring moisture in the object to be cleaned may be used, and information on the amount of moisture may be taken into consideration for extraction of the feature amount in S204 of FIG. 6 and cleaning determination processing in S205. In this case, there is a high possibility that the amount of moisture on the surface to be cleaned increases once during cleaning, and then decreases due to vaporization. Therefore, cleaning determination processing can be performed by adding this factor to the feature amount. This enables more accurate cleaning determination.

Although the embodiments of the present invention have been described above, the present invention is not limited to the above-described embodiments, and includes various modifications. For example, the above-described embodiments have been described in detail to explain the present invention in an easy-to-understand manner, and the present invention is not necessarily limited to having all the configurations described. Furthermore, it is possible to add, delete, or replace some of the configurations of each embodiment with other configurations.

For example, in FIG. 1, it has been explained that the image processing device 10, the image recording device 21, the display device 22, and the printing device 23 are connected via the network 30, but these may be directly connected to each other. Further, the image processing device 10 and the display device 22 may be configured as one unit. In addition, the image processing device 10 may be configured integrally within the imaging device 1.

Further, although FIGS. 3 and 4 show a configuration using a touch panel, the configuration is not limited to this, and instead of a button display, a dedicated operation switch, a keyboard, etc. may be used.

DESCRIPTION OF SYMBOLS 1... Imaging device, 10... Image processing device, 11... Control unit, 12... User interface unit, 13... Report creation unit, 14... Image judgment unit, 15... Image judgment recording unit, 21... Image recording device, 22... Display Device, 23...Printing device, 30...Network, 100...Display screen, 101...Cleaning start button, 102...Cleaning end button, 103...Imaging device area button, 104...Cleaning status update button, 105...Report creation button, 111... Cleaning start date and time, 112...Cleaning end date and time, 113...Camera identification information, 114...Report creation date and time, 120...Cleaning status screen, 121...Cleaned area, 122, 122a...Uncleaned area, 150...Detection area, 151...Small Area, 300...Computer system, 302...Processor, 302A, 302B...Processing device, 304...Memory, 306...Memory bus, 308...I/O bus, 309...Bus interface, 310...I/O bus interface, 312...Terminal Interface, 314...Storage interface, 316...I/O device interface, 318...Network interface, 320...User I/O device, 322...Storage device, 324...Display system, 326...Display device, 330...Network, 350...Application , A001...Detection small area, C001...Cleaner, F001...Movement direction, K001...Cleaning tool

Claims (6)

Equipped with an imaging device and an image processing device,
The image processing device identifies a cleaning person based on the image taken by the imaging device, and determines the cleaning status in the image by identifying a cleaned area based on the cleaning person's actions. Equipped with a judgment section,
The cleaning status detection system is characterized in that the cleaning status is determined by inference processing by AI (Artificial Intelligence) using a neural network and deep learning, and at least the behavior of the cleaning person is treated as a feature quantity . The cleaning status detection system according to claim 1,
The cleaning state detection system is characterized in that the cleaning state is determined by determining that the cleaning state has not been cleaned if there is a part that has not been cleaned in the detection area set in the image. The cleaning status detection system according to claim 1,
The cleaning situation detection system is characterized in that the cleaning situation is determined by identifying a cleaning tool, and if the cleaning tool is not moving in a predetermined direction, determining that the area has not been cleaned. . The cleaning status detection system according to claim 1,
Equipped with a display device,
The cleaning situation detection system is characterized in that the display device displays a determination result of the cleaning situation in the image processing device using the photographed image. The cleaning status detection system according to claim 4,
The image processing device may include a report creation unit that automatically creates a report based on a determination result of the cleaning status in the image processing device when a signal regarding completion of cleaning or report creation is obtained from the display device. Cleaning status detection system. The cleaning status detection system according to claim 1,
The imaging device has an infrared camera function,
The cleaning status detection system is characterized in that the image processing device uses temperature information acquired from the imaging device to determine the cleaning status.

Images