Monitoring device, monitoring method and computer program for monitoring

Abstract

To provide a monitoring device capable of detecting entry of a person into a predetermined prohibited area.SOLUTION: A monitoring device includes: a detection part 21 for detecting a person from each of a plurality of images of time series generated by an imaging part 2; a track part 22 for tracking the person in one or more images representing the detected person among the plurality of images; and a determination part 23 for determining whether or not a position of the person detected on the images over a first period is included within a first range on the images corresponding to a prohibited area 1b on the basis of a result of tracking, determining whether or not the position of the person detected on the images over a second period longer than the first period is included within a second range on the images provided around the first range, and determining that the detected person enters the prohibited area 1b when the position of the person detected on the images is included within the first range over the first period or is included within the second range over the second period.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The present invention relates to a monitoring device, a monitoring method, and a monitoring computer program for monitoring a predetermined area using an image representing the predetermined area. [Background technology]

[0002] A technology has been proposed for monitoring the status of a predetermined area using an image depicting that area (see Patent Document 1). The in-vehicle monitoring system disclosed in Patent Document 1 recognizes people and luggage included in an in-vehicle image captured by an imager mounted on the ceiling of a public vehicle, and further estimates whether the recognized people are sitting or standing. Based on the positions of the recognized luggage and people, the in-vehicle monitoring system estimates whether there are any luggage-occupied seats and whether there are any overlapping seats where a seated person is sitting across multiple seats. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2023-3974 Summary of the Invention [Problem to be solved by the invention]

[0004] There are cases where no-entry areas are provided inside a vehicle where it is undesirable for passengers to enter, and it is necessary to detect passengers entering such areas.

[0005] SUMMARY OF THE INVENTION It is therefore an object of the present invention to provide a monitoring device that can detect the intrusion of a person into a prohibited area. [Means for solving the problem]

[0006] One aspect of the present invention provides a monitoring device that includes a detection unit that detects a person from each of a plurality of time-series images generated by an imaging unit configured to capture an area including a prohibited area, a tracking unit that tracks the detected person in one or more of the images in which the detected person is depicted, and a determination unit that determines, based on the tracking results, whether the position of the detected person on the image is within a first range on the image corresponding to the prohibited area over a first period of time and whether the position of the detected person on the image is within a second range on the image that is provided around the first range over a second period of time that is longer than the first period of time, and determines that the detected person has entered the prohibited area when the position of the detected person on the image is within the first range over the first period of time or within the second range over the second period of time.

[0007] In one embodiment, the detection unit detects at least two different parts of a person from each of a plurality of images in a time series, the tracking unit tracks each of the at least two detected parts, and the determination unit determines that the person has entered a prohibited area when, for any of the at least two detected parts, the position of that part on the image is within a first range for a first period of time, or the position of that part on the image is within the first range for a second period of time.

[0008] In this case, the first range and the second range are set for each of the at least two regions.

[0009] According to another embodiment, there is provided a monitoring method including: detecting a person from each of a plurality of time-series images generated by an imaging unit configured to capture an area including a prohibited area; tracking the person in one or more of the plurality of images in which the detected person is depicted; determining, based on a result of the tracking, whether a position of the detected person on the image is within a first range on the image corresponding to the prohibited area over a first period of time and whether a position of the detected person on the image is within a second range on the image surrounding the first range over a second period of time longer than the first period of time; and determining that the detected person has entered the prohibited area when the position of the detected person on the image is within the first range over the first period of time or within the second range over the second period of time.

[0010] According to yet another embodiment, there is provided a monitoring computer program, the monitoring computer program including instructions for causing a computer to: detect a person from each of a plurality of time-series images generated by an imaging unit configured to capture an area including a prohibited area; track the detected person in one or more of the images in which the detected person is depicted; determine, based on a result of the tracking, whether a position of the detected person on the images is within a first range on the images corresponding to the prohibited area over a first period of time and whether a position of the detected person on the images is within a second range on the images surrounding the first range over a second period of time longer than the first period of time; and determine that the detected person has entered the prohibited area when the position of the detected person on the images is within the first range over the first period of time or within the second range over the second period of time. [Effects of the Invention]

[0011] The monitoring device according to the present disclosure has the effect of being able to detect the entry of a person into a prohibited area. [Brief explanation of the drawings]

[0012] [Figure 1] 1 is a schematic configuration diagram of a vehicle in which a monitoring device according to an embodiment is installed; [Figure 2] FIG. [Figure 3] FIG. 1 is a schematic configuration diagram of a monitoring device. [Figure 4] FIG. 2 is a functional block diagram of a processor related to monitoring processing. [Figure 5] 1(a) to 1(c) are diagrams each illustrating an outline of a monitoring process. [Figure 6] 10 is an operational flowchart of a monitoring process. DETAILED DESCRIPTION OF THE INVENTION

[0013] A monitoring device, a monitoring method, and a monitoring computer program will be described below with reference to the drawings. The monitoring device detects a person within a predetermined area, including a prohibited area, from each of a plurality of time-series images depicting the predetermined area, and tracks the detected person across each image. The monitoring device also determines, for each person being tracked, whether the person's position on the image is within a first range on the image corresponding to the prohibited area and whether the person is within a second range on the image surrounding the first range. The monitoring device determines that the person has entered the prohibited area when the duration during which the person's position on the image is within the first range reaches a first period, or when the duration during which the person's position on the image is within the second range reaches a second period.

[0014] In the following, an example will be described in which the monitoring device is applied to monitoring the interior of a vehicle that can accommodate multiple passengers. Passengers are an example of people to be detected. However, the monitoring device is not limited to this example and may also be used to monitor no-entry areas set up inside a moving object that passengers or crew members can board, such as a railway vehicle, or to monitor no-entry areas set up in some kind of building or facility.

[0015] Fig. 1 is a schematic diagram of a vehicle equipped with a monitoring device according to one embodiment. Fig. 2 is a diagram of the interior of the vehicle, seen from above, equipped with the monitoring device. The vehicle 1 equipped with the monitoring device is a vehicle, such as a bus, that can accommodate multiple passengers and has enough interior space for passengers to stand and move around. The vehicle 1 has a camera 2, a notification device 3, and a monitoring device 4.

[0016] Additionally, inside the vehicle 1, a prohibited area 1b is set around the entrance 1a through which passengers get on and off the vehicle 1. The prohibited area 1b is an area into which passengers are prohibited from entering when the door provided at the entrance 1a is opened or closed, in order to prevent passengers from being put in danger when the door is opened or closed.

[0017] The camera 2 is an example of an imaging unit, and is mounted, for example, near the ceiling of the interior of the vehicle 1 at the entrance 1a of the vehicle 1, facing vertically downward so that its imaging range includes a predetermined area 1c inside the vehicle around the entrance 1a of the vehicle 1. In this embodiment, the camera 2 is mounted so that the entrance 1a is shown at the bottom of the image generated by the camera 2. The predetermined area 1c is set to include the entire prohibited area 1b and be larger than the prohibited area 1b so that passengers who enter the prohibited area 1b can be detected from the image generated by the camera 2. The camera 2 generates an image of the predetermined area 1c around the entrance 1a at a predetermined imaging period (e.g., 1 / 30 to 1 / 10 seconds). The image obtained by the camera 2 may be a color image or a grayscale image. If the vehicle 1 has multiple entrances, a camera 2 capable of imaging the predetermined area around each entrance may be provided for each entrance. Every time the camera 2 generates an image, it outputs the generated image to the monitoring device 4 via the in-vehicle network.

[0018] The notification device 3 is a device that can issue predetermined notifications to passengers located around the boarding / alighting entrance 1a, and has, for example, a speaker, buzzer, or display device, and is attached near the boarding / alighting entrance 1a inside the vehicle 1. In response to a notification signal from the monitoring device 4, the notification device 3 outputs a predetermined notification, for example, a sound that indicates a notification that warns that a passenger has entered the prohibited area 1b, or displays a message corresponding to the notification.

[0019] The monitoring device 4 performs monitoring processing based on the images generated by the camera 2.

[0020] Fig. 3 is a hardware configuration diagram of the monitoring device 4. As shown in Fig. 3, the monitoring device 4 has a communication interface 11, a memory 12, and a processor 13. The communication interface 11, the memory 12, and the processor 13 may each be configured as separate circuits, or may be configured integrally as a single integrated circuit.

[0021] The communication interface 11 has an interface circuit for connecting the monitoring device 4 to the in-vehicle network. Each time the communication interface 11 receives an image from the camera 2, it passes the received image to the processor 13. Furthermore, when the communication interface 11 receives a notification signal from the processor 13 to be output to the notification device 3, it outputs the notification signal to the notification device 3.

[0022] The memory 12 is an example of a storage unit and includes, for example, a volatile semiconductor memory and a non-volatile semiconductor memory. The memory 12 stores various programs and various data used in the monitoring process executed by the processor 13 of the monitoring device 4. For example, the memory 12 stores parameters for identifying a classifier used to detect an occupant, the positions and ranges of various areas on an image, etc. The memory 12 also temporarily stores images received from the camera 2 and various data generated during the monitoring process.

[0023] The processor 13 includes one or more central processing units (CPUs) and their peripheral circuits. The processor 13 may further include other arithmetic circuits such as a logic unit, a numerical calculation unit, or a graphics processing unit. The processor 13 executes monitoring processing.

[0024] 4 is a functional block diagram of the processor 13 related to the monitoring process. The processor 13 has a detection unit 21, a tracking unit 22, a determination unit 23, and a notification processing unit 24. Each of these units of the processor 13 is, for example, a functional module realized by a computer program running on the processor 13. Alternatively, each of these units of the processor 13 may be a dedicated arithmetic circuit provided in the processor 13.

[0025] The detection unit 21 detects passengers located within a predetermined area from each of a plurality of time-series images generated by the camera 2. In this embodiment, the detection unit 21 detects passengers from the latest image obtained by the camera 2 at predetermined intervals. The detection unit 21 only needs to perform the same processing on each image, so the processing on one image will be described below.

[0026] In this embodiment, the detection unit 21 individually detects passengers from the image based on at least two of their attributes, belongings, and body parts. The attributes, belongings, and body parts of passengers individually set as detection targets include “person” (i.e., the entire passenger), “head,” “infant,” “wheelchair,” “stroller,” and “suitcase.” The attributes, belongings, and body parts to be detected are not limited to the above examples. For example, if a situation is anticipated in which only the passenger's hands or only the passenger's feet are shown in the image, “hands” or “feet” may be additionally set as body parts to be detected. Furthermore, depending on the positional relationship between the camera 2 and the prohibited area, it may not be necessary to individually detect any of the above attributes, belongings, and body parts. Furthermore, if the positional relationship between the passenger's position and the prohibited area can be grasped without individually setting the attributes, belongings, and body parts to be detected, the detection unit 21 may only detect the passenger itself. Hereinafter, for convenience of explanation, the attributes, belongings, and body parts of passengers will be simply referred to as “body parts.”

[0027] The detection unit 21 detects these body parts by inputting the images received by the monitoring device 4 from the camera 2 into a classifier that has been trained in advance to detect these body parts. Such a classifier is based on a so-called deep neural network (DNN). For example, a DNN with a convolutional neural network (CNN)-type architecture, such as Single Shot MultiBox Detector or YOLO, or a DNN with an attention mechanism, such as Vision Transformer, may be used. Alternatively, a classifier based on another machine learning method, such as AdaBoost or a support vector machine, may be used. The classifier is trained in advance according to a predetermined learning method, such as backpropagation, using a large number of training images including images depicting the body parts to be detected.

[0028] The classifier outputs regions (hereinafter referred to as object regions) in the input image that represent the body parts to be detected and the reliability of each object region. When multiple object regions representing the same type of body parts overlap, the detection unit 21 performs Non-Maximum Suppression (NMS) or Soft NMS to prevent multiple detections of the same passenger body part. That is, the detection unit 21 calculates the intersection over union (IoU) of multiple overlapping object regions representing the same body part, and if the IoU is equal to or greater than a predetermined threshold, deletes object regions other than the object region with the highest reliability. Alternatively, the detection unit 21 decreases the reliability as the IoU increases, and deletes object regions whose reduced reliability is below a predetermined detection threshold.

[0029] Note that different parts of the same passenger may be detected separately in one image. For example, an object region showing the entire passenger and an object region showing the passenger's head may be detected separately in one image. Also, an object region showing the entire passenger and an object region showing the suitcase carried by the passenger may be detected separately in one image.

[0030] For each part of a passenger detected from the image, the detection unit 21 notifies the tracking unit 22 and the determination unit 23 of the passenger part and the position and range of the object region in which the passenger part is represented.

[0031] The tracking unit 22 tracks the detected passenger in one or more images in which the passenger is depicted, among a plurality of time-series images generated by the camera 2. In this embodiment, each body part is detected individually, so the tracking unit 22 performs tracking processing for each detected body part of the passenger. In other words, the tracking unit 22 associates, among the object regions depicting the body parts of each passenger, object regions depicting the same body part of the passenger across a plurality of images. Note that, when detection is targeted not for each body part but only for the entire passenger, the tracking unit 22 may perform the following processing for each detected passenger.

[0032] To achieve this, the tracking unit 22 applies a predetermined tracking method, such as KLT tracking or ByteTrack, to each object region in the latest image. As a result, the tracking unit 22 associates the passenger's body part depicted in each object region in the latest image with the object region detected in a previously acquired image (hereinafter referred to as a past image) and depicting the body part of the same passenger currently being tracked. Each time the tracking unit 22 receives a detection result for the latest image from the detection unit 21, the tracking unit 22 repeats the above process to track the body part of each passenger and assigns a unique identification number (hereinafter referred to as a passenger ID) to the body part of each passenger currently being tracked. For an object region detected in the latest image that cannot be associated with any object region depicting a passenger currently being tracked in a past image, the tracking unit 22 considers the body part of the passenger depicted in the object region to be that of a passenger who has newly entered a predetermined area and starts new tracking. Conversely, if the object area representing any part of the passenger being tracked in the past image is not associated with any object area in the latest image, the tracking unit 22 determines that the part of the passenger being tracked has left the specified area and terminates tracking.

[0033] If multiple different body parts are detected for the same passenger, each detected body part may be tracked and assigned a separate passenger ID. For example, if the entire passenger is detected as a "person" and the passenger's "head" is detected and tracked, a passenger ID for the entire passenger and a passenger ID for the head may be assigned separately.

[0034] Based on the tracking results of the tracking unit 22, the determination unit 23 determines whether the position of the detected passenger on the image is included within a first range on the image corresponding to the prohibited area 1b over a first period. The determination unit 23 also determines whether the position of the detected passenger on the image is included within a second range on the image that is set around the first range over a second period longer than the first period. Even if any part of the passenger has entered the prohibited area 1b, that part may fall outside the first range on the image depending on the height of that part from the floor of the vehicle interior. Therefore, the second range is set near the outer boundary of the prohibited area 1b so as to include such a part within the prohibited area 1b. The second range has a size of, for example, approximately 5% to 100% of the width of the first range in either the vertical or horizontal direction.

[0035] The determination unit 23 determines that a passenger has entered the prohibited area 1b when the detected position of the passenger on the image is within a first range for a first period of time or within a second range for a second period of time. On the other hand, for any passenger, if the duration of the state in which the passenger's position on the image is within the first range does not reach the first period of time and the duration of the state in which the passenger's position on the image is within the second range does not reach the second period of time, the determination unit 23 determines that no passenger has entered the prohibited area at the time of determination. Furthermore, for a passenger who has once been determined to have entered the prohibited area 1b, the determination unit 23 may determine that the passenger has exited the prohibited area 1b when the passenger's position on the image is outside the first range and the second range for a predetermined duration of time.

[0036] In this embodiment, the determination unit 23 executes the above process for each body part of a passenger assigned the same passenger ID. Therefore, the determination unit 23 can accurately determine whether or not a passenger has entered the prohibited area 1b even if the entire passenger's body is not included in the prohibited area 1b.

[0037] In this embodiment, as described above, the boarding / alighting door 1a is depicted at the bottom of the image, and the camera 2 is mounted so as to capture images vertically downward from the ceiling of the vehicle interior. Therefore, it is estimated that the bottom end of the object region represents the position of the bottom end of the passenger's body part depicted in the object region. That is, if the passenger's body part depicted in the object region is a "person" itself, it is assumed that the bottom end of the object region represents the position of the passenger's feet. Therefore, for each passenger's body part, if the bottom end of the object region is within a first range, the determination unit 23 determines that the passenger's position is within the first range. Conversely, if the bottom end of the object region is outside the first range, the determination unit 23 determines that the passenger's position is not within the first range. Similarly, for each passenger's body part, if the bottom end of the object region is within a second range, the determination unit 23 determines that the passenger's position is within the second range. Conversely, if the bottom end of the object region is outside the second range, the determination unit 23 determines that the passenger's position is not within the second range. In order for the passenger's position to be determined to be within the first range, it is not necessary for the entire bottom edge of the object region to be included within the first range; it is sufficient that at least a predetermined percentage (e.g., 10% to 30%) of the bottom edge of the object region is included within the first range. The same applies to the second range. In addition to this example, determination unit 23 may determine that the passenger's position is included within the first range or the second range if at least a predetermined percentage of the area of ​​the object region is included within the first range or the second range. The predetermined percentage may be set individually for each part. This makes it possible to more accurately determine whether the passenger's position is included within the first range or the second range.

[0038] The first period may be, for example, a period corresponding to the image generation cycle of camera 2 or a period several times that period, and the second period may be, for example, a period several times that period. By setting the periods in this manner, when a passenger is located within the first range where it is assumed that the passenger has definitely entered prohibited area 1b, the passenger's entry into prohibited area 1b is detected early and in a short period. On the other hand, even when a passenger is located within the second range where it is assumed that the passenger may have entered prohibited area 1b, this is detected over a relatively long second period, and the passenger's entry into prohibited area 1b is accurately detected.

[0039] 5(a) to 5(c) are diagrams each illustrating an outline of determining whether a passenger has entered a prohibited area. In this example, shown in FIGS. 5(a) to 5(c), an entrance / exit 1a is depicted near the bottom of an image 500 representing a predetermined area 1c inside the vehicle 1, and a range on the image 500 corresponding to a prohibited area 1b adjacent to the entrance / exit 1a is set as a first range 501. Furthermore, a second range 502 is set above the first range 501 and adjacent to the first range 501. The second range may also be set as a range adjacent to a side of the first range.

[0040] 5(a), the lower end of the object region 510 in which the passenger is depicted is included in the first range 501. Therefore, if this state continues for the first period, it is determined that the passenger depicted in the object region 510 has entered the prohibited region 1b.

[0041] 5(b), the lower end of object region 520 in which the passenger is depicted is not included in first range 501, but is included in second range 502. Therefore, if this state continues for the second period, it is determined that the passenger depicted in object region 520 has entered prohibited region 1b.

[0042] 5(c), the lower end of object region 530 in which the passenger is depicted is not included in either first range 501 or second range 502. Therefore, as long as this state continues, it is determined that the passenger depicted in object region 530 has not entered prohibited region 1b.

[0043] When the determination unit 23 determines that any passenger has entered the prohibited area 1b, it notifies the notification processing unit 24 of that fact.

[0044] When the determination unit 23 notifies the notification processing unit 24 that a passenger has entered the prohibited area 1b, the notification processing unit 24 outputs a notification signal, which indicates a warning that a passenger has entered the prohibited area 1b, to the notification device 3 via the communication interface 11. This alerts the passenger to the prohibited area 1b via the notification device 3. Alternatively, the notification processing unit 24 may output an entry warning signal, which indicates that a passenger has entered the prohibited area 1b, to an electronic control unit (ECU) of the vehicle 1 via the communication interface 11. The ECU may stop opening or closing the door of the entrance 1a while receiving the entry warning signal. Note that the notification processing unit 24 may output the notification signal to the notification device 3 or the entry warning signal to the ECU only during the period from when the monitoring device 4 receives a warning signal from the ECU of the vehicle 1 notifying the opening or closing of the door of the entrance 1a until when it receives an opening / closing signal indicating that the door has actually been opened or closed. This prevents unnecessary warnings from being issued even if a passenger enters the prohibited area 1b when the boarding / alighting door 1a is not being opened or closed, thereby reducing the inconvenience to the passengers.

[0045] 6 is an operational flowchart of the monitoring process. The processor 13 executes the monitoring process in accordance with the operational flowchart shown below.

[0046] The detection unit 21 detects passengers from the image generated by the camera 2 (step S101). The tracking unit 22 tracks the detected passengers (step S102).

[0047] The determination unit 23 determines whether the position of each detected passenger on the image is within a first range for a first period of time (step S103). If the position of any passenger is within the first range for a first period of time (step S103-Yes), the determination unit 23 determines that the passenger has entered the prohibited area 1b (step S104). The notification processing unit 24 then warns the passenger of the entry into the prohibited area 1b via the notification device 3 (step S105).

[0048] Furthermore, if the position of any passenger is not included in the first range or the state in which the position is included in the first range has not continued until the first period (step S103-No), determination unit 23 determines whether the position of each detected passenger on the image is included in the second range over the second period (step S106).If the state in which the position of any passenger is included in the second range has continued over the second period (step S106-Yes), processor 13 executes the processes of steps S104 and S105.

[0049] After step S105, or if in step S106 the passenger's position on the image is not included in the second range, or if the state in which the position is included in the second range does not continue until the second period (step S106-No), the processor 13 terminates the monitoring process.

[0050] As described above, the monitoring device detects and tracks each person in a time-series of images, and determines whether the person's position on the image is within a first range on the image corresponding to a prohibited area, and whether the person is within a second range on the image surrounding the first range. The monitoring device then determines that the person has entered the prohibited area when the duration during which the person's position on the image is within the first range reaches a first period, or when the duration during which the person's position on the image is within the second range reaches a second period. This allows the monitoring device to accurately detect the person's entry into the prohibited area.

[0051] Depending on the camera's mounting position and shooting direction, the positions of individual body parts of a person in an image may differ when the person is located within a prohibited area. For example, if the camera is mounted to capture the prohibited area from diagonally above, the positions of the person's feet and head may differ significantly in the image, even if the person is standing within the prohibited area. Therefore, according to a modified example, the first and second ranges may be individually set according to the person's body parts. In this case, the first range on the image for each body part corresponding to the prohibited area is set according to the expected height of the body part as the range in which that body part appears when the person is located within the prohibited area. The second range for each body part may be set around the first range so as to include the position on the image when that body part may have entered the prohibited area. The determination unit 23 may determine, for each body part of a person, whether the object area containing that body part is included in the first or second range corresponding to that body part. This modified example enables the monitoring device to more accurately detect a person who has entered a prohibited area.

[0052] A computer program that causes a computer to execute the processing executed by the processor 13 of the monitoring device 4 according to the above embodiment or modification may be recorded on a recording medium such as an optical recording medium or a magnetic recording medium and distributed.

[0053] As described above, those skilled in the art can make various modifications to the embodiments within the scope of the present invention. [Explanation of symbols]

[0054] REFERENCE SIGNS LIST 1 vehicle, 1a entrance / exit, 1b prohibited area, 2 camera, 3 notification device, 4 monitoring device, 11 communication interface, 12 memory, 13 processor, 21 detection unit, 22 tracking unit, 23 determination unit, 24 notification processing unit

Claims

1. a detection unit that detects a person from each of a plurality of time-series images generated by an imaging unit that is provided to capture an image of a predetermined area including a prohibited area; a tracking unit that tracks the detected person in one or more images in which the person is depicted, among the plurality of images; a determination unit that determines, based on a result of the tracking, whether a position of the detected person on the image is included within a first range on the image corresponding to the prohibited area over a first period of time, and determines whether a position of the detected person on the image is included within a second range on the image that is set around the first range over a second period of time that is longer than the first period of time, and determines that the detected person has entered the prohibited area when the position of the detected person on the image is included within the first range over the first period or is included within the second range over the second period of time; A monitoring device having:

2. the detection unit detects at least two different parts of the person from each of the plurality of images; The tracking unit tracks each of the at least two detected regions; 2. The monitoring device of claim 1, wherein the determination unit determines that the person has entered the prohibited area when, for any of the at least two detected body parts, the position of the body part on the image is included in the first range over the first period, or the position of the body part on the image is included in the first range over the second period.

3. The monitoring device according to claim 2 , wherein the first range and the second range are set for each of the at least two regions.

4. Detecting a person from each of a plurality of time-series images generated by an imaging unit provided to capture an image of a predetermined area including a prohibited area; tracking the detected person in one or more images in which the person is depicted among the plurality of images; determining whether or not a position of the detected person on the image is included within a first range on the image corresponding to the prohibited area over a first period of time based on a result of the tracking, and determining whether or not a position of the detected person on the image is included within a second range on the image that is set around the first range over a second period of time that is longer than the first period of time; determining that the detected person has entered the prohibited area when the position of the detected person on the image is included within the first range for the first period or included within the second range for the second period; A monitoring method comprising:

5. Detecting a person from each of a plurality of time-series images generated by an imaging unit provided to capture an image of a predetermined area including a prohibited area; tracking the detected person in one or more images in which the person is depicted among the plurality of images; determining whether or not a position of the detected person on the image is included within a first range on the image corresponding to the prohibited area over a first period of time based on a result of the tracking, and determining whether or not a position of the detected person on the image is included within a second range on the image that is set around the first range over a second period of time that is longer than the first period of time; determining that the detected person has entered the prohibited area when the position of the detected person on the image is included within the first range for the first period or included within the second range for the second period; A monitoring computer program that causes a computer to do things.

Images