JP5752976B2 - Image monitoring device - Google Patents

Description

The present invention provides an image to be notified to a remote monitoring center when a person existing in a monitoring space is determined to be a suspicious person based on an analysis result of image information obtained by photographing the monitoring space in a space in which important monitoring objects are installed. It relates to a monitoring device. More specifically, an object of the present invention is to provide an image monitoring apparatus that can prevent a person's occipital head from being mistaken for a suspicious person with a mask.

Conventionally, in a monitoring system that detects a person who enters a monitoring area such as a store or an office and notifies a remote monitoring center, the characteristic information of the person area is extracted from an image captured by a camera, There is known an image monitoring apparatus that automatically outputs a report to a remote monitoring center when the feature is met, and enables the monitoring center operator to remotely monitor the image.

  In such a monitoring system using an image, when an alarm signal indicating that a suspicious person has been detected is notified from an image monitoring device installed in the monitoring area, the operator of the monitoring center checks the image and makes a determination. . When it is determined that the detection is not actually a suspicious person but an erroneous detection, the operator performs a reset operation to return to the normal monitoring state.

  Here, for example, a suspicious person may be a person whose face is hidden or a person whose behavior is suspicious. For example, in Patent Document 1, facial features such as eyes, ears, nose and mouth cannot be extracted because of sunglasses or a mask from an image of a visitor's face in a facility used by an unspecified number of people. In this case, an alarm device that reports to a manager or the like as a suspicious person candidate is described.

Japanese Patent Laid-Open No. 5-35992

In the example of the alarm device of Patent Document 1, the camera is installed at a position where the operator of the automatic cash payment corner can be photographed in front. However, in the case of an image monitoring device that monitors a wider imaging range, the image is not captured. The person is not always facing the front. For example, if a person reflected in the image is facing backwards, and then each part of the face is not detected from the head, the person may be mistaken as a suspicious person and report to a remote monitoring center.

As described above, there is a problem in that the processing load of the monitoring operator and the communication cost are increased by erroneously detecting a non-malicious third person reflected in the image as a suspicious person.

The present invention has been made in view of the above problems, and prevents image monitoring devices installed in a monitoring area from erroneously detecting a normal person as a face concealer as much as possible, and particularly as an actual face concealer. An object of the present invention is to provide an image monitoring apparatus that can detect a person with a masked face without failing even if he / she crawls.

In order to achieve the above object, the image monitoring apparatus according to the present invention provides an imaging unit that acquires an image obtained by imaging a monitoring area, and an alarm when determining that a suspicious person has been detected by processing the input images sequentially acquired by the imaging unit. An image monitoring apparatus including an image signal processing unit that generates a signal and an output unit that outputs the warning signal, wherein the image signal processing unit extracts a head candidate region of a human body from the input image. Part candidate area extracting means, face concealment determining means for determining whether or not a face is concealed based on luminance information of the extracted head candidate area, and detecting a suspicious person based on the face concealment determination result Suspicious person determination means for determining, the face concealment determination means further includes a skin region extraction means for extracting a skin region in the head candidate region, and a face concealment determination result based on the luminance information; By the skin area extracting means Determining the presence or absence of a face hiding based on the position of the extracted skin regions.
According to such a configuration, for example, it is possible to reliably identify a case where a person with a masked face and a person's occipital head crawl, to prevent erroneous determination, and to accurately determine that a suspicious person has been detected.

Also, in a preferred aspect of the present invention, the face concealment determining means determines that a face has been concealed when the skin region exists within a predetermined region including the center of the head candidate region. According to such a configuration, it is possible to accurately determine a suspicious person whose face is hidden based on the position of the skin region of the eye part of the covering surface.

In a preferred aspect of the present invention, the face concealment determining means determines that the face is not concealed when the skin region is present in a region outside a predetermined region including the center of the head candidate region.
According to this configuration, it is possible to prevent the person's occipital region from being erroneously determined as a suspicious person whose face is hidden by the covering surface based on the position of the skin region such as the neck and ears of the occipital region.

Furthermore, in a preferred aspect of the present invention, the face concealment determining means includes a black pixel ratio calculating means, and when the ratio of black pixels in the head candidate area is less than a predetermined value, the skin area It is determined that the face is hidden regardless of the position. According to this configuration, when the luminance in the head candidate region is low in black pixels, it is highly likely that the hair is not the head hair of the person's occipital region. Can be identified.

It is an example in which the image monitoring apparatus according to the present invention is installed in an office of a store. It is a schematic block diagram of the image monitoring apparatus concerning this Embodiment. It is a whole flowchart showing operation | movement of the image monitoring apparatus concerning this Embodiment. It is an operation | movement flowchart of the face concealment determination process of the image monitoring apparatus concerning this Embodiment. It is a figure showing the example of face concealment detection of the image monitoring apparatus concerning this Embodiment.

Hereinafter, referring to the drawings, as an embodiment of the image monitoring apparatus according to the present invention, the image monitoring apparatus is installed in an office room of a store such as a supermarket and is present in the vicinity of an important monitoring object such as a safe in the office room. An example realized as a monitoring device for detecting a suspicious person will be described. In addition, this image monitoring device can be realized as a part of the function that constitutes the security device, and it is possible to monitor not only during the absence of people such as at night, but also during the opening of security such as opening a store. Assumed. In the office, during opening hours, employees and part-time workers can enter the office as well as persons who can unlock safes such as store managers. It is also assumed that there is a possibility that a suspicious person approaches the safe by looking at the gap between the employee and the part-time job, or the suspicious person approaches the safe by restraining the employee or the part-time job. Since surveillance cameras are installed in these stores and offices, suspicious individuals who attempt to steal or robbery often hide their faces with masks, sunglasses, masks, and the like.

The image monitoring apparatus according to the present embodiment, when a person is in the vicinity of an important object such as a safe, extracts a face part of the person from a camera installed in the vicinity of the important object and conceals the face part. As a suspicious person, an emergency call is made to a remote monitoring center, and a captured image in the monitoring area is transmitted.

Fig.1 (a) is a schematic diagram showing a mode that the image monitoring apparatus 1 concerning this invention was installed in the office. Examples of the installation location include an office room and a backyard with a storage where products before being displayed at a store are arranged on a shelf. In FIG. 1 (a), a safe 6 is installed in the corner of the floor of the office.

The imaging unit 2 of the image monitoring apparatus 1 is installed above the safe 6 in a substantially horizontal direction, and the field of view of the imaging unit 2 includes the entire office. Within this field of view is the monitoring area. The image monitoring apparatus processes the image acquired by the imaging unit 2, and determines whether or not a person included in the image is concealed. The determination of the presence / absence of face concealment is to determine whether or not the suspicious person conceals his / her face with sunglasses and a mask, a mask, a full-face helmet, etc. to make it difficult to identify a person.

An image acquired from the imaging unit 2 is referred to as an input image in the present embodiment. An example of the input image is shown in FIG. As can be seen from FIG. 1B, the human phase can be grasped if the person in the image has the face facing the imaging unit 2 by making use of the image of the camera oriented in a substantially horizontal direction. By using the face concealment determination technique, it is possible to determine whether there is face concealment. In addition, since the input image can acquire not only the human phase but also the information on clothes and the appearance of the person in the image, it can also be used for recording as an image for the purpose of ensuring trailability.

FIG. 2 is a schematic configuration diagram of an image monitoring apparatus 1 according to the present invention as one embodiment. The image monitoring apparatus 1 includes an imaging unit 2, a storage unit 3, an image signal processing unit 4, and an output unit 5.

The imaging unit 2 is composed of at least one camera, a CCD or C-MOS, or the like, a two-dimensional detector composed of a photoelectric converter having sensitivity to visible light, and an image of a monitoring area on the two-dimensional detector. An image forming optical system for forming an image is included. The imaging unit 2 can be, for example, a camera that continuously shoots according to the NTSC standard. Alternatively, the imaging unit 2 may generate a higher resolution image such as so-called high vision.

In the present embodiment, the imaging unit 2 uses an image taken in the office as a grayscale image or a color image in which the luminance of each pixel is expressed in 256 gradations, for example, at a predetermined frame interval (for example, an interval of 0.5 seconds). Generate every time. The imaging unit 2 is connected to an interface unit (not shown) of the image signal processing unit 4 and outputs the generated image as an input image to the image signal processing unit 4 every time the imaging unit 2 generates an image.

The storage unit 3 includes a storage device such as a nonvolatile semiconductor memory such as a flash memory, a volatile semiconductor memory, or a magnetic disk (HDD). The storage unit 3 stores various programs and setting data used in the image monitoring apparatus 1. In addition, the storage unit 3 stores, as a background image, an input image in which a person is not captured, which is acquired from the imaging unit 2 when the image monitoring apparatus 1 is activated or periodically.

In addition, the storage unit 3 stores information on the person area extracted from the input image as person area information. Further, the storage unit 3 stores a template image, setting data, and the like under various conditions in order to make a head candidate region and face concealment determination from the input image.

The image signal processing unit 4 determines a suspicious person according to whether or not a person in the input image input from the imaging unit 2 is hiding the face, and performs a warning signal transmission process according to the determination result. . The image signal processing unit 4 includes a person area extraction unit 41, a head candidate area extraction unit 42, a face concealment determination unit 43, a suspicious person determination unit 44, and a control unit 45. Each of these constituent means can be realized by a program module stored in the storage unit 3. Next, each means of the image signal processing unit 4 will be described.

The person area extraction unit 41 obtains a difference for each pixel between the input image acquired from the imaging unit 2 and the background image stored in the storage unit 3, has a predetermined luminance change, and is set based on the person A change area having a size within a predetermined range is extracted as a person area. The background image is an image that is updated every predetermined time with an input image when the room is unattended. The person area extracting means 41 determines whether or not the extracted person area is the same moving body as the person area extracted in the previous frame. If the person area newly appears, a new management number is assigned. It is given (labeled) and stored in the storage unit 3 as person area information together with information such as its size and position.

If extracted from the current frame but presumed to be from the same moving object as the person area extracted in the previous frame, information such as position and size is additionally stored in the person area information of the management number. . Since the background difference process and the labeling process are well-known techniques in the field of image processing technology, further detailed description thereof is omitted.

The head candidate region extraction unit 42 extracts a region that is highly likely to be a human head on the person region as a head candidate region. As a method for extracting the head candidate area, a head contour pattern such as an elliptical pattern is stored in the storage unit 3 as a template, and an area having a high similarity to the template is extracted as a head candidate area in the person area. It is possible to adopt a technique such as For this technique, the technique described in Japanese Patent Application Laid-Open No. 2005-25568 by the present applicant can be adopted.

The prepared head contour pattern is not limited to the elliptical pattern, and may be a pattern that simulates the contour of the face shape.

Further, as a method for extracting the head candidate region from the person region, a detection method based on a HOG (Histogram of Oriented Gradients) feature amount can be used. The HOG feature value is a feature value focused on the edge (luminance gradient) direction in the local region cut out from the image with an arbitrary size. A feature that is useful for identifying head candidate regions by preparing a large number of face image data and images unrelated to face images as learning data in advance, searching for local regions of various sizes in the entire learning image Select the amount. Since HOG features are features with a very large number of dimensions, Adaboost, which is one of the statistical learning methods, is used for feature selection, and a set of HOG features that are effective for identifying head candidate regions Sort out.

Using this selected set of feature amounts, a region having edge features of head candidates can be extracted as a head candidate region on the person region extracted from the input image. For HOG feature-based face detection methods, see, for example, Dalal N., Triggs B .: “Histograms
of Oriented Gradients for Human Detection. ”IEEE Conf. CVPR, vol.1, pp.886-893, 2005.

The face concealment determination unit 43 determines the presence or absence of face concealment based on the luminance information in the extracted head candidate area candidate. Specifically, by analyzing the image features in the extracted head candidate region, the face such as non-face concealment, which is like a natural face, sunglasses and mask, cover (balancing cap), full face helmet, etc. Calculate the concealment numerically. A plurality of template images are prepared for the face image data of the faces of young and old men and women and the various types of face concealment image data prepared in advance, and the brightness information of the extracted head candidate area and the similarity between each template image When the threshold value set in advance for the most similar template image is exceeded, the head candidate region is determined to be a face concealer or a face concealer whose face is concealed by some shielding object.

In addition, a determination method based on the Haar-Like feature amount can be used for determining the face concealment. The Haar-Like feature value is a feature value that focuses on the average luminance difference between two adjacent rectangular areas. Like the HOG feature value, the face image of the face image can be obtained using Adaboost for learning image data prepared in advance. Select Haar-Like features that are effective for identification. As face image data for learning, face image data of a face, face image data for each face concealment type, and data unrelated to the face image are prepared under various conditions. By pre-learning, a feature amount effective for identifying a face and a set of feature amounts effective for identifying each face concealment are selected and prepared as a searcher used for identifying each face concealment type. Using each of these searchers, the head face candidate area is obtained by quantifying the degree of similarity between the luminance features of the face-likeness and the various face concealment. If the similarity for the searcher with the highest degree of similarity increases the preset similarity, the head candidate area is determined to be a face concealer who is hiding the face with a natural face or some kind of shielding object. .

For this Haar-Like feature-based face detection method, for example, P. Viola and M. Jones: Rapid
Object Detection using a Boosted Cascade of Simple (CVPR2001).

The face concealment determination unit 43 includes a skin region extraction unit 431 and a black pixel ratio calculation unit 432.

The skin area extracting means 431 extracts the area of the bare skin portion in the detected head candidate area.

For the extraction of the bare skin portion, a method of extracting the skin color portion using color information can be adopted. This method of extracting the skin color region is a known method, and for example, the method described in Japanese Patent Application Laid-Open No. 2005-049979 by the present applicant can be adopted. The skin area is extracted in order to identify the face concealer by the human occipital area and the mask, and even if the face mask by the mask is high, the position of the skin area in the head candidate area is not near the center. The extracted skin region is likely to be, for example, the neck portion of the back of the head, and in this case, it can be used to determine that it is not a face concealer. On the other hand, when the position of the skin region is near the center, there is a high possibility that the skin area is an eye-opening portion.

The black pixel ratio calculation means 432 obtains the ratio of black pixels in the extracted head region. The ratio of black pixels is obtained in order to identify the face concealer by the human occipital region and the mask, and the degree of face masking by the mask is high and the ratio of black pixels in the head candidate region is small. Regardless of the position of the skin area, there is a high possibility that the surface is colored. On the other hand, when the proportion of black pixels is large, it is difficult to distinguish between the case of a face concealer by a mask and the case of a head portion of a human head, so that the position of the skin region needs to be determined.

The suspicious person determination unit 44 determines that the face concealer is a suspicious person when the face concealment determination unit 43 includes a face concealer in the monitoring area and satisfies the suspicious person determination condition. As an example of a suspicious person determination condition, a suspicious person is determined when the number of times a face concealer is detected is counted within a predetermined number of consecutive frames (for example, 5 frames) for a preset number of times (for example, 3 times). And so on.

The control means 45 controls each part of the image monitoring apparatus 1 in an integrated manner. Moreover, it is a means to control the output part 5 from the suspicious person determination result by the suspicious person determination means 44, and to determine whether an alarm signal is output.

The output unit 5 has a function of receiving an instruction from the control unit 45 and outputting an alarm signal to a previously registered output destination. Here, the alarm signal is reported to a monitoring center such as a security company via a communication line. The output destination of the alarm signal is not limited to the above. For example, a warning sound or a warning message may be issued from a speaker or the like provided in the monitoring target. Further, it may be notified to a mobile phone such as a user registered in advance via a communication line.

The configuration of the image monitoring apparatus according to the present embodiment has been described above.

Next, an example of the operation of the image monitoring apparatus 1 according to the present embodiment will be described with reference to the flowcharts shown in FIGS. FIG. 3 is a main flow diagram of the image signal processing unit 3 according to the present embodiment. In FIG. 3, the processing of step S11 to step S20 is executed every time the image signal processing unit 3 acquires an input image from the imaging unit 2 at a predetermined frame period (for example, every 0.5 s).

The image monitoring apparatus 1 starts operation when the power is turned on and the initial setting is completed. As an initial setting, processing such as storing an input image input from the imaging unit 2 as a background image in the storage unit 3 is performed. This background image is appropriately updated at predetermined time intervals.

In the flowchart of FIG. 3, first, in step S <b> 11, an input image is acquired from the imaging unit 2. The acquired input image is temporarily stored in the storage unit 3. The storage unit 3 is provided with a storage area capable of storing a predetermined number of input images from the current time to a predetermined time ago. When the storage area becomes full, the oldest stored image is deleted. A new input image is stored. The stored image may be backed up regularly to an external hard disk or the like.

In step S12, the person area extraction unit 41 processes the input image acquired in step S11 and extracts a person area. The person area may be extracted by using a general method such as a background difference method in which an area where the difference between the background image stored in the storage unit 3 and the input image is equal to or larger than a predetermined value is extracted as a person area.

If a person area that satisfies the predetermined condition is not extracted (No at Step S13), the monitoring area is assumed to be unattended and the process returns to Step S11. When the person area is extracted (step S13—Yes), the process proceeds to step S14.

In step S14, the person area extraction unit 41 refers to the person area information acquired from the input image of the previous frame stored in the storage unit 3, and extracts the person area extracted in the current frame and the person extracted in the previous frame. Perform area mapping processing. If no person area is extracted in the previous frame, a new management number is assigned to the person area extracted in the current frame, and information such as the size and position is stored in the storage unit 3 as person area information.

In step S15, the head candidate area extraction means 42 searches the person area by template matching or the like to extract the person head candidate area. In step S16, face concealment detection processing is performed. In step S17, the face concealment determination unit 43 conceals the majority of the face with the extracted head candidate region using sunglasses, a mask, a mask, a full face helmet, and the like. It is determined whether or not. The process of step S16 is made into a subroutine, and details will be described later.

If it is determined in step S17 that the face is concealed (step S17-Yes), the suspicious person degree (suspicious person score) for the label is added in step S18, and the process proceeds to step S19. If it is determined in step S17 that the face is not concealed, the process returns to step S11. Here, the suspicious person score is obtained from the type of face concealment, the number of detections within a predetermined number of frames in the case of a natural face, and the like.

Next, in step S19, it is determined whether or not the suspicious person degree of the person area (label) whose face is concealed satisfies the suspicious person determination condition. As described above, the suspicious person determination condition is determined by, for example, detecting a specific type of face concealer within a predetermined predetermined frame (for example, 5 frames) a predetermined number of times (for example, 3 frames). When the suspicious person determination condition is satisfied (step S19-Yes), it is determined that a suspicious person is detected in step S20, and a notification is made to a predetermined report destination.

If the suspicious person determination condition is not satisfied (step S19-No), the process returns to step S11 to process the next frame.

The suspicious person determination process of the image signal processing unit 3 has been described above. Next, the face concealment determination process in step S16 will be described with reference to the flowchart of FIG. Note that the processing in the flowchart of FIG. 4 is performed individually for each of the head candidate regions when a plurality of candidate head regions are extracted from the input image. In addition, when the head candidate area to be processed is determined to be face concealment according to the flowchart of FIG. 4, the face concealment flag is turned on. This face concealment flag is set for each of a plurality of head candidate areas.

First, in step S151, the face concealment degree is calculated. The calculation of the degree of face concealment is based on the luminance information in the head candidate area, and the preset “Sunglasses + glasses”, “cover (bald cap)”, “ The most probable values for the face helmet, the concealment by the palm, etc. are calculated. Note that other types can be appropriately set as the face concealment type.

In step S152, it is determined whether any type of face concealment degree exceeds a set threshold value.

It should be noted that a plurality of suspicious face classifications can be set here, and the threshold value may be exceeded for a plurality of classifications. In this case, it may be determined that the face is concealed if any of the face concealment degrees is exceeded, or the highest numerical value is determined as the concealment means made for the head candidate area. Also good. Further, if the likelihood of a face exceeds a predetermined numerical value, it may be determined that the face is a face even if any of the face hiding levels exceeds a set threshold.

When none of the face concealment conditions is satisfied (step S152-No), this routine is exited and the process returns to the flowchart of FIG.

Next, when one or a plurality of face concealment conditions are satisfied in step S152, it is determined in step S153 whether or not the face concealment condition by the cover (eye cap) is satisfied. When only the face concealment condition other than the mask is satisfied, or when the plausibility by the other mask is higher than the mask by the mask, the process proceeds to step S156, the face mask flag is turned on, and the process returns to the flowchart of FIG.

If it is determined in step S153 that the face is masked, the black pixel ratio calculation means 432 obtains the luminance value of each pixel in the head candidate area in step S154, and the ratio of the black pixels to the whole is calculated. . This is a process for identifying mainly whether the candidate head region to be processed is concealed by a masked surface or a human back head. Specifically, since it is highly likely that the face is a masked face when the color is other than black, if the ratio of black pixels in the head candidate region is equal to or less than a predetermined value (step S154-No), it is a masked face. If the possibility is high, the process proceeds to step S156, the face concealment flag is turned on, and the process returns to the flowchart of FIG. On the other hand, if the ratio of black pixels in the head candidate region exceeds a predetermined value, it means that the ratio of black pixels is large, and therefore it is difficult to identify whether it is a black covering surface or a human back of the head. Proceed to

In step S155, the skin region extraction unit 431 extracts a skin region in the head candidate region, and determines whether or not the center of gravity position is within a predetermined region including the center in the head candidate region. If the center of gravity position of the skin region is outside the predetermined region, it is determined that there is a high possibility of the occipital region, and this routine is exited and the process returns to the flowchart of FIG. On the other hand, when the barycentric position of the skin area is within the predetermined area, the face concealment flag is turned on because it is highly possible that the face is concealed by the mask, and this routine is exited and the process returns to the flowchart of FIG. The process of step S155 will be specifically described with reference to FIG.

FIG. 5A is an example in which a face concealer with a mask is captured in an input image. Assume that the head candidate region 501 is extracted in FIG. In this case, the skin area of the face concealer by the masking surface is 503 that is an eye-opening portion, and the center of gravity includes the center in the head candidate area 501 even if the face concealer faces the front or crawls. It exists in the predetermined area 502. On the other hand, FIG. 5B is an example in which the human occipital region is captured in the input image. In this case, the vicinity of the neck at the back of the person is extracted as the skin region 506. This skin region 506 exists at a position away from the center in the head candidate region 504. Therefore, the center of gravity position of the skin region 506 is not included in the predetermined region 505. Therefore, it is possible to identify whether the face is a face concealer or a human back of the head by the position of the center of gravity of the skin area existing in the head candidate area. The predetermined area in the head candidate area used for determination of the center of gravity position can be set as a rectangular area that includes the center of the head candidate area and excludes a predetermined ratio (for example, 10%) of the top, bottom, left, and right of the head candidate area. . Or you may set the area ratio with respect to a head candidate area | region, and set as an area | region where a center corresponds with a head candidate area | region. Moreover, it is not limited to a rectangular area, and may be set as an elliptical area. In this case, the lengths of the major axis and the minor axis may be set according to the size of the head candidate region, or may be set by an area ratio.

Note that the skin region is not necessarily extracted in the extracted head candidate region. In particular, when a suspicious person who covers the covering surface crawls, the skin region may not be extracted. Therefore, when the skin region (centroid) is extracted in the predetermined region including the center in the head candidate region in the process of step S155 in FIG. 4, it is not determined that the face is concealed, and the center of the head candidate region It may be determined that the face is not concealed when the skin region (center of gravity) is extracted in a region outside the predetermined region including. In the latter case, the extracted skin region may be a skin portion such as a neck or ear on the human back of the head. In this case, it can be determined that the person is not a face concealer.

The image monitoring apparatus of the present invention has been described above. Each process in the image monitoring apparatus does not necessarily have to be processed in time series in the order described in the flowchart, and may include parallel or subroutine processing. In the present embodiment, exception processing is performed at the time of face concealment by a mask, but processing according to each feature can be added to other face concealment conditions.

DESCRIPTION OF SYMBOLS 1 ... Image monitoring apparatus 2 ... Imaging part 3 ... Memory | storage part 4 ... Image signal processing part 5 ... Output part 6 ... Important monitoring thing

Claims (4)

An imaging unit for acquiring an image obtained by imaging the monitoring area;
An image signal processing unit that processes an input image sequentially acquired by the imaging unit and generates an alarm signal when it is determined that a suspicious person is detected;
An image monitoring apparatus comprising an output unit that outputs the alarm signal,
The image signal processor is
Head candidate region extraction means for extracting a human head candidate region from the input image;
Face concealment determining means for determining whether or not the face concealment type is at least concealed as a face concealment type based on the luminance information of the extracted head candidate area;
Suspicious person determination means for determining detection of a suspicious person based on the face concealment determination result,
The face concealment determining means includes
A skin region extracting means for extracting a skin region in the head candidate region;
An image monitoring apparatus that determines whether or not there is face concealment based on the position of the skin region extracted by the skin region extracting unit when the face concealment determining unit determines that the face is concealed by a covering surface . The face concealment determining means includes
The image monitoring apparatus according to claim 1, wherein when the skin area exists in a predetermined area including a center of the head candidate area, it is determined that the face is concealed. The face concealment determining means includes
The image monitoring apparatus according to claim 1, wherein when the skin area exists in an area outside a predetermined area including a center of the head candidate area, it is not determined that the face is concealed. The face concealment determining means includes
Furthermore, it has a black pixel ratio calculation means,
The image according to claim 2 or 3, wherein when the proportion of black pixels in the head candidate region is less than a predetermined value, it is determined that the face is concealed regardless of the position of the skin region. Monitoring device.