Crime prevention system

Abstract

An infrared image capture device (4) captures infrared images of a user (3) that is trying on clothes in a fitting room (1). A determination device (5) detects the actions of the user (3) from the infrared images and determines that an infraction has occurred upon detecting that the user (3) has exited while still wearing a tried-on article. A warning-issuing device (6) issues a warning when the determination device (5) has determined that an infraction has occurred.

Description

Security system

[0001] The present disclosure relates to security systems.

[0002] Commercial facilities and the like are equipped with security cameras capable of acquiring image data to prevent theft, and a security system has been proposed that detects and processes the image data to determine whether theft has occurred (see, for example, Patent Document 1).

[0003] Japanese Patent Publication No. 2020-91832

[0004] It is difficult to install regular security cameras in private rooms where privacy is important, such as fitting rooms or changing rooms. Although it is possible to blur images to prevent individuals from being identified, the captured image data is recorded on the system, so privacy cannot be fully protected.

[0005] The present disclosure has been made to solve the above-mentioned problems, and its purpose is to provide a security system that can detect violations while protecting privacy.

[0006] The security system according to the present disclosure is characterized by comprising an infrared imaging device that photographs a user trying on clothes in a fitting room to obtain an infrared image, a determination device that detects the user's movements from the infrared image and determines that a violation has occurred if the determination device detects that the user has left the room while still wearing the clothes, and a warning device that issues a warning if the determination device determines that a violation has occurred.

[0007] In the present disclosure, infrared imaging can be used to detect violations while preserving privacy.

[0008] FIG. 1 is a diagram showing a security system according to embodiment 1. FIG. 2 is a flowchart showing the operation of the security system according to embodiment 1. FIG. 3 is a diagram showing an infrared image of a user getting changed. FIG. 4 is a flowchart showing the operation of the security system according to embodiment 2. FIG. 5 is a flowchart showing the operation of the security system according to embodiment 3. FIG. 6 is a diagram showing a security system according to embodiment 4. FIG. 7 is a flowchart showing the operation of the security system according to embodiment 5. FIG. 8 is a diagram showing an infrared image of a user getting changed.

[0009] A security system according to an embodiment will be described with reference to the drawings. The same or corresponding components are designated by the same reference numerals, and repeated description may be omitted.

[0010] Embodiment 1. Figure 1 is a diagram showing a security system according to embodiment 1. A door 2 is provided in a fitting room 1. A user 3 changes clothes in the fitting room 1. An infrared imaging device 4, such as an infrared camera, is installed in the fitting room 1 and takes pictures of the inside of the fitting room 1 to obtain infrared images. A judgment device 5 judges whether or not a violation has occurred based on the infrared image. The judgment device 5 is realized by a processing circuit, such as a CPU or system LSI, that executes a program stored in memory. Furthermore, multiple processing circuits may work together to perform the above functions. A warning issuance device 6 issues a warning to an administrator depending on the judgment result.

[0011] FIG. 2 is a flowchart of the operation of the security system according to the first embodiment. First, user 3 opens door 2 and enters fitting room 1 with clothes to try on (step S1). Next, infrared imaging device 4 captures user 3 trying on clothes in fitting room 1, obtaining an infrared image (step S2). FIG. 3 shows an infrared image of a user getting changed. In the infrared image, the clothes being tried on by user 3 appear cooler than the clothes originally worn by user 3. User 3's exposed skin, such as his face and hands, appears to be the hottest. Because the infrared image does not contain any information that could identify user 3, it is effective in protecting his privacy.

[0012] Next, the motion detector 5a of the determination device 5 detects the body parts of the user 3 from the infrared image, and detects the motion of the user 3 based on the temperature change of the body parts caused by putting on or taking off clothes (step S3).

[0013] Here, since the fitting room 1 is a limited area and the range captured by the infrared imaging device 4 and the position of the user 3 can be specified to some extent, the user's movements may be detected based on the overall brightness change of the infrared image. Specifically, the change in the frequency distribution of brightness in the infrared image can be used to determine whether the user 3 has entered the room. Next, when the user takes off their clothes, the temperature of their body parts approaches the temperature close to that of their body surface, so the brightness distribution of the infrared image changes from the time of their entry. Therefore, the movement detection unit 5a can detect the user's movements based on the overall brightness change of the infrared image, without detecting the user's body parts. However, detecting the user's body parts improves the accuracy of movement detection. The movement detection unit 5a may also detect the user's movements by processing the infrared image using artificial intelligence (AI).

[0014] Next, the action determination unit 5b of the determination device 5 determines that the user 3 has left the room while still wearing the clothes as a violation (step S4). Specifically, the action determination unit 5b determines that the user 3 has left the room as a violation if the temperature state of the human body immediately after entering the room differs from the temperature state of the human body immediately before leaving the room in the infrared image.

[0015] If the determination device 5 determines that a violation has occurred, the warning device 6 issues a warning to a manager (step S5). The manager may be, for example, a store clerk. The warning device 6 may be, for example, a buzzer or speaker that issues an alarm to the clerk, a light, a display that shows a visible alarm, or a transmitter that sends an alarm signal to a tablet carried by the clerk or an intercom worn by the clerk. Upon receiving the warning, the clerk visually checks the user 3 as he or she leaves the fitting room 1 to see if he or she is still wearing the clothes to try on.

[0016] As described above, in this embodiment, by using infrared images, it is possible to detect violations while protecting privacy. Furthermore, by using infrared images for the primary judgment of violation detection, the monitoring burden on store staff is reduced.

[0017] 4 is a flowchart of the operation of the security system according to embodiment 2. First, as in embodiment 1, a user 3 enters the fitting room 1 carrying an item to try on (step S1). Next, the infrared imaging device 4 captures an infrared image of the user 3 trying on clothes in the fitting room 1 (step S2).

[0018] Next, the motion detection unit 5a of the determination device 5 detects the body parts of the user 3 from the infrared image and detects the actions of the user 3 putting on or taking off clothes using the temperature changes that occur when the user puts on or takes off clothes (step S3). For example, when removing clothes, the body surface is exposed or becomes lightly dressed, so the temperature of the body parts in the infrared image rises. On the other hand, when trying on clothes, the body surface is covered, so the temperature of the body parts in the infrared image drops. Such temperature changes are used to detect the putting on or taking off of clothes. Note that the motion detection unit 5a of the determination device 5 may also detect the actions of the user 3 putting on or taking off clothes by processing the infrared image using AI.

[0019] Next, when the action determination unit 5b of the determination device 5 detects that the user 3 has put on clothes (step S6) and then left the fitting room 1 without taking off the clothes (step S7) (step S8), it determines that a violation has occurred. That is, the action determination unit 5b determines that a violation has occurred when there is no consecutive action of "putting on" followed by "taking off." If the determination device 5 determines that a violation has occurred, the warning issuance device 6 issues a warning to the administrator (step S5).

[0020] The temperature of the items being tried on is lower than the temperature of the body parts of user 3. Therefore, the action determination unit 5b determines that user 3 has taken the action of putting on clothes when the body parts of user 3 in the infrared image change from high to low, and determines that user 3 has taken the action of taking off clothes when the body parts change from low to high. If user 3 leaves the room while still wearing the items being tried on, the change will not be from low to high, so it is determined to be a violation as there was no "taking off" action.

[0021] For example, if User 3 puts on a fitting item over his or her own clothes and leaves the room, this is determined to be a violation because there is no consecutive action of "taking off" after "putting on." On the other hand, if User 3 enters fitting room 1 and leaves without trying on clothes, the action determination is not a violation because "putting on" is not detected.

[0022] Furthermore, if a person enters a room wearing thick clothes such as winter clothes and then leaves wearing different thick clothes, the surface temperature of the clothes does not change much after entering the room and immediately before leaving. For this reason, it is difficult to detect a violation using the method of embodiment 1, but the method of embodiment 2, which detects the continuous actions of "putting on" and "taking off," can detect a violation. The other configurations and effects are the same as those of embodiment 1.

[0023] 5 is a flowchart of the operation of the security system according to the third embodiment. The input data unit 5c of the determination device 5 stores a plurality of putting-on and taking-off action patterns of infrared images corresponding to the putting-on and taking-off action of a plurality of types of clothing, such as jackets or pants. The putting-on and taking-off action patterns are, for example, patterns of putting on and taking off an article of clothing, such as a T-shirt, by passing it over the head and arms, putting on an outer garment such as a coat by passing it over the arms, and putting on bottoms such as pants by passing it over the legs.

[0024] The motion detection unit 5a of the determination device 5 detects the putting on and taking off of clothes by the user 3 by comparing the temperature change in the infrared image that occurs when putting on and taking off clothes with multiple putting on and taking off motion patterns. By using the putting on and taking off motion patterns, the accuracy of determining putting on and taking off motions, such as whether to put on a jacket or pants, is improved. By looking at the temperature change in the upper part of the infrared captured image, it is possible to focus on the upper body, and by looking at the temperature change in the lower part of the screen, it is possible to focus on the lower body. Similarly, when using AI, etc., the accuracy of determining putting on and taking off motions is improved by using the putting on and taking off motion patterns. Other configurations and effects are the same as those of embodiment 2.

[0025] Fourth Embodiment. Figure 6 is a diagram showing a security system according to a fourth embodiment. Because privacy protection standards are looser in public areas than inside the fitting room 1, it is possible to obtain visible information of the user 3. Therefore, a surveillance camera 7 is installed in the public area outside the fitting room 1. The surveillance camera 7 captures visible information by photographing the user 3 who opens the door 2 and exits the fitting room 1 and is outside the fitting room 1. The behavior determination unit 5b of the determination device 5 uses AI or the like to process the visible information and detect violations. The rest of the configuration is the same as in the second embodiment.

[0026] 7 is a flowchart of the operation of the security system according to embodiment 4. After detecting that user 3 has left fitting room 1, the operation determination unit 5b of determination device 5 detects user 3's clothing based on visible information, and determines that a violation has occurred if user 3's clothing has changed between before and after entering fitting room 1 (step S12). Other operations are the same as those in embodiment 2.

[0027] As explained above, in this embodiment, violations are determined based on both infrared images from inside the fitting room 1 and visible information from outside the fitting room 1. Visible information can accurately detect the clothing of the user 3, improving the accuracy of violation determination compared to embodiment 2. In particular, visible information can compensate for the erroneous determination made in embodiment 2, which determined that a violation had occurred when the consecutive actions of "putting on" and "taking off" were not performed. Other effects are the same as those of embodiment 2.

[0028] Fifth Embodiment Fig. 8 shows a security system according to a fifth embodiment. A heat source 8 such as an RFID tag that can be detected by an infrared imaging device 4 is attached to an article of clothing to be tried on. The rest of the configuration is the same as in the first embodiment.

[0029] 9 is a flowchart of the operation of the security system according to embodiment 5. First, as in embodiment 1, a user 3 enters the fitting room 1 carrying an article of clothing to be tried on (step S1). However, a heat source 8 is attached to the article of clothing. Next, the infrared imaging device 4 captures an infrared image of the user 3 and the heat source 8 while they are trying on clothes in the fitting room 1 (step S2).

[0030] 10 shows an infrared image of a user getting changed. The temperature of the heat source 8 is 40°C or higher, which is higher than the temperature of the human body, so the heat source 8 can be distinguished from the body parts of the user 3 in the infrared image. However, if the temperature of the heat source 8 is kept below the temperature of a hand warmer (around 50°C), there is no risk of burns from the heat source 8, and there is no safety issue.

[0031] Next, the position detection unit 5d of the determination device 5 detects the positions of the user 3 and the heat source 8 from the infrared image (step S13). The action determination unit 5b of the determination device 5 detects whether the user 3 is wearing the clothing based on the relative positions of the user 3 and the heat source 8, and determines that the user 3 has committed a violation if they leave the room while still wearing the clothing (step S14). For example, if the positions of the user 3's body and the heat source 8 overlap in the thermal image, it is determined that the clothing is being tried on. If the heat source 8 is located at the user 3's hand, it is determined that the user has removed the clothing and is holding it in their hand. If the heat source 8 is completely hidden, it cannot be captured in the infrared image, and it is determined that the user is trying on clothing. If the determination device 5 determines that a violation has occurred, the warning issuance device 6 issues a warning to the administrator (step S5).

[0032] As described above, in this embodiment, by using infrared images, it is possible to detect violations while protecting privacy. Furthermore, by using the heat source 8, it is possible to accurately detect whether the user 3 is trying on an item of clothing based on the relative positions of the user 3 and the heat source 8.

[0033] 1 fitting room, 3 user, 4 infrared imaging device, 5 determination device, 6 warning device, 7 surveillance camera, 8 heat source

Claims

1. A security system comprising an infrared imaging device that captures infrared images of a user trying on clothes in a fitting room, a determination device that detects the user's movements from the infrared images and determines that a violation has occurred if the determination device detects that the user has left the room while still wearing the clothes, and a warning device that issues a warning if the determination device determines that a violation has occurred.

2. The security system according to claim 1, wherein the determination device detects the user's movements based on temperature changes in the user's body caused by putting on or taking off clothes.

3. The security system of claim 2, wherein the determination device determines that a violation has occurred if the temperature state of the human body part immediately after entering the room differs from the temperature state of the human body part immediately before leaving the room in the infrared image.

4. The security system according to claim 1, wherein the determination device detects the user's actions based on a change in overall brightness of the infrared image.

5. The security system described in claim 1, characterized in that the judgment device determines that a violation has occurred when it detects that the user has put on clothes and then left the fitting room without taking off the clothes.

6. The security system described in claim 5, characterized in that when the part of the user's body in the infrared image changes from high to low temperature, it is determined that the user has put on clothes, and when the part of the user's body in the infrared image changes from low to high temperature, it is determined that the user has taken off clothes.

7. The security system according to claim 5, characterized in that the infrared image is processed using artificial intelligence to detect the user's putting on and taking off actions.

8. A security system as described in any one of claims 5 to 7, characterized in that it stores multiple patterns of putting on and taking off clothing, each corresponding to the action of putting on and taking off multiple types of clothing, and detects the user's putting on and taking off actions by comparing the temperature changes in the infrared image caused by putting on and taking off clothing with the multiple putting on and taking off action patterns.

9. A security system as described in any one of claims 1 to 8, further comprising a surveillance camera that photographs the user outside the fitting room to obtain visual information, and the judgment device detects the user's clothing based on the visual information, and judges that a violation has occurred if the user's clothing has changed before and after entering the fitting room.

10. The security system described in claim 1 further comprises a heat source attached to the clothing item, and the determination device detects the positions of the user and the heat source from the infrared image and determines whether the user is wearing the clothing item based on the relative positions of the user and the heat source.

11. The security system described in claim 10, characterized in that the determination device determines that the clothing is being worn when the position of the user's body part and the position of the heat source overlap in the infrared image.

Images