JP5851108B2 - Image monitoring device - Google Patents

Description

  The present invention relates to an image monitoring apparatus that images a monitoring space and detects the presence of a suspicious person, and in particular, an object of the present invention is to provide an image monitoring apparatus that can accurately extract a person whose face is hidden by a helmet or the like.

  2. Description of the Related Art Conventionally, there has been known an image monitoring apparatus that extracts feature information of a person region from an image input from an imaging device and automatically outputs a report to the outside when the feature information matches a feature of a suspicious person or the like. Such an image monitoring apparatus detects that the human phase is hidden from the outside as a feature of the suspicious person.

  For example, Patent Document 1 determines whether or not a normal face image of a person can be acquired by capturing an image from a camera in order to detect a suspicious person who may withdraw cash from an automatic transaction apparatus illegally. A monitoring device is described. In Patent Document 1, it is detected that a part of the face is concealed with sunglasses, a mask, or a hand, or that a full-face helmet is worn, and a normal face image cannot be acquired. Judgment.

JP 2010-79750 A

  By the way, when focusing on a full-face helmet as a means for hiding the face described above, the full-face helmet is often extracted as an elliptical shape that fits in the head region in the image data, and facial features such as the eyes and nose and mouth Has a feature that cannot be extracted. This image feature is a feature similar to a human back of the head, and in order to detect a full-face helmet with high accuracy, it is necessary to clearly discriminate between the back of the human head and the full-face helmet.

  That is, the back of the head of a person is often extracted as an oval shape that fits within the head region, and the facial features such as the eyes, nose and mouth cannot be extracted. There is a possibility that it is determined as a concealed state.

  The present invention has been made in view of the above-described problems, and relates to an image monitoring apparatus that detects the presence of a suspicious person who has captured a monitoring space and concealed his face, and can distinguish between a full-face helmet and a person's back of the head. An object is to provide an image monitoring apparatus.

  In order to achieve the above object, an image monitoring apparatus according to the present invention is an image monitoring apparatus that detects a suspicious person whose face is concealed by a helmet or the like in a monitoring space, and periodically images the monitoring space to monitor images. An image capturing unit for acquiring a facial feature information of a person in advance, a head extracting unit for extracting an input head region corresponding to a person's head from the monitoring image, and the input head region A facial feature determination unit that determines whether facial feature information is included using the facial feature information; a high-luminance region extraction unit that determines whether a high-luminance region having a predetermined area or more exists in the input head region; A suspicious person detecting unit that determines that a suspicious person conceals a face when the face characteristic determining unit determines that there is no facial feature information and the high luminance region extracting unit determines the presence of a high luminance region; , Provided.

  In such a configuration, the image monitoring apparatus extracts a head region having no facial features from the monitoring image, and determines that a high-luminance region having a predetermined area or more exists in the head region. The head region is determined to be a suspicious person whose face is hidden by a full-face helmet.

The full-face helmet is formed in an approximately oval shape with few joints for ease of care, and the smooth curved surface reflects ambient ambient light such as lighting, and a certain amount of gloss is generated as gloss. On the other hand, since the head of a person has fine irregularities due to hair, ambient light such as illumination is diffused, and glossy luster is hardly generated.
According to the configuration of such an image monitoring apparatus, a full-face that is glossy unlike the back of the head is detected by detecting a full-face helmet on the condition that a high-luminance area of a predetermined area or more exists in the head area that conceals the face. It becomes possible to detect the helmet with high accuracy.

  In the image monitoring apparatus according to the present invention, the high luminance area extracting unit may determine whether there is a high luminance area having an area that is a predetermined ratio or more with respect to the area of the input head area. .

  According to such a configuration, by extracting a high-luminance region that is relatively larger than a predetermined area according to the size of the head region included in the monitoring image, the size of the head reflected on the image is obtained. Accordingly, it is possible to detect the full-face helmet with high accuracy.

  Furthermore, in the image monitoring apparatus of the present invention, the high brightness area extraction unit may set a predetermined upper range of the input head area as a search area and extract the high brightness area in the search area. Good.

In general, ambient light such as illumination is generally irradiated from above, and in such a case, gloss is generated by reflecting the ambient light on the upper portion of the smooth curved surface of the full-face helmet.
According to the configuration of such an image monitoring device, by extracting a high-luminance area that occurs at the top of the head area, it is possible to prevent erroneous detection of a shirt area on the back of the head as a high-luminance area. It is possible to detect a full-face helmet that produces gloss with high accuracy.

According to the present invention, it is possible to detect a full-face helmet on condition that a high-luminance region having a predetermined area or more exists in a head region where no facial feature information exists.
As a result, it has a smooth curved surface that prevents the back of the human head from being misdetected as a full-face helmet because it has minute irregularities due to hair and diffuses ambient light such as lighting and does not easily cause glossy shine. However, it is possible to accurately detect a full-face helmet that reflects ambient light such as lighting and generates a certain amount of glossy luster.

It is the schematic which shows the whole structure of the monitoring system by the image monitoring apparatus of this invention. It is a block diagram which shows the structure of the image monitoring apparatus of this invention. It is the figure which showed typically the suspicious person monitoring process of the image monitoring apparatus of this invention. It is a flowchart which shows the suspicious person monitoring process of the image monitoring apparatus of this invention. It is a flowchart which shows the high-intensity area | region determination process of the image monitoring apparatus of this invention.

Embodiments of the present invention will be specifically described below with reference to the drawings.
In the present embodiment, the case of monitoring the vicinity of important monitoring objects in an office area such as a financial institution or a store as a monitoring area (monitoring space) is illustrated, but the scope of the present invention is not limited to this, and It may be used to monitor the entire room or street as a monitoring area.

FIG. 1 is a configuration diagram showing a monitoring system 1 using the image monitoring apparatus of the present invention.
FIG. 1 schematically shows a monitoring area in which a storage 2 having a storage space inside a safe or the like and an image monitoring device 3 are installed as important monitoring objects. As shown in FIG. 1, the monitoring system 1 of the present embodiment communicates a monitoring device 3 placed on the upper part of a storage 2 fixedly installed on the floor of a monitoring area and a remote monitoring center 5. It is configured to be connected via the line network 4.

In the housing of the image monitoring apparatus 3, a monitoring camera 31 as an imaging unit is arranged in the same direction as the storage door. The monitoring camera 31 is arranged so that a person approaching the storage 2 can be imaged using the front of the storage door as an imaging field of view.
Note that the monitoring camera 31 is not limited to the example built in the housing of the image monitoring device 3, and a monitoring camera is separately installed in the upper space or the rear wall of the storage 2 so that at least a person in the monitoring area can take an image, It may be configured to be connected to the image monitoring apparatus 3. The image monitoring device 3 is not limited to the example of being placed on the upper part of the storage 2 and may be set in the upper space of the storage 2 or the rear wall surface.

  The monitoring camera 31 captures a monitoring area at every predetermined shooting interval (for example, 0.2 seconds), generates image data as a monitoring image, and outputs it. The image monitoring apparatus 3 determines whether or not there is a suspicious person around the storage 2 by referring to image data periodically captured based on information output from the monitoring camera 31.

  In this embodiment, a suspicious person refers to a person who may impair the maintenance of a monitored area such as a burglar, and specifically, a person whose appearance matches a predetermined feature pattern. In general, a suspicious person who performs a robbery or the like tends to hide his / her face in order to prevent recognition of the identity. Therefore, in the present embodiment, as the person characteristic information in the image data, for example, the face is covered with sunglasses, a mask, or a hand, or a part or all of the face is hidden by wearing a full face helmet or the like. A person whose facial condition is unknown, that is, a person who has no facial feature information such as eyes and nose and mouth and whose face is not sufficiently photographed is extracted and determined as a suspicious person.

In particular, as a characteristic matter in the present embodiment, the image monitoring device 3 prevents the person's occipital portion reflected in the image data from being determined as a suspicious person wearing a full-face helmet or the like, and a full-face helmet. This improves the accuracy of suspicious persons whose human phase cannot be determined.
When it is determined that there is a suspicious person, the image monitoring apparatus 3 transmits an emergency signal indicating that an emergency has occurred in the monitoring area to the remote monitoring center 5 and detects the suspicious person. The image data used in the above is transmitted to the monitoring center 5.

  The monitoring center 5 is a facility provided with a center device 51 operated by a security company or the like. The center device 51 is composed of one or a plurality of computers, and realizes the function of the monitoring center 5 related to the present invention. In the monitoring center 5, various devices are controlled by the center device 51, the emergency signal received from the image monitoring device 3 is recorded, and the image data transmitted from the image monitoring device 3 is displayed on the display 52, so that the monitoring staff Monitors multiple monitored areas.

<Image monitoring device>
Next, the configuration of the image monitoring apparatus 3 will be described with reference to FIG. FIG. 2 is a block diagram illustrating a configuration of the image monitoring apparatus 3.
The image monitoring device 3 is connected to the communication network 4 so as to be communicable with the monitoring center 5, and is fixedly placed on the upper part of the storage 2.

  The image monitoring apparatus 3 includes a monitoring camera 31 that captures the front of the storage, a communication unit 32 connected to the communication network 4, a storage unit 33 including an HDD and a memory, an MPU, a microcomputer, and the like. And a control unit 34 that controls each unit.

  The monitoring camera 31 generates a monitoring image of the monitoring area including the front of the storage. The monitoring camera 31 converts an image signal input from the image sensor into a digital signal at a predetermined shooting interval (for example, a cycle of 0.2 seconds, that is, 5 fps (frame / second)), performs compression encoding processing, and performs a predetermined standard. Image data compliant with (for example, JPEG standard) is generated. As a wavelength band used for image capturing, a visible light wavelength capable of capturing a color image is used. The image data generated by the monitoring camera 31 is output to the control unit 34.

  The communication unit 32 is connected to the center device 51 via the communication line network 4 and communicates with the monitoring center 5. When the control unit 34 determines that there is a suspicious person in the monitoring area, the communication unit 32 transmits an emergency signal including its own address information and the image data stored in the storage unit 33 to the monitoring center 5.

  The storage unit 33 is configured by a ROM, a RAM, or an HDD, stores address information for identifying itself and various programs, and further stores various information for operating the image monitoring apparatus 3. Specifically, the storage unit 33 determines the presence of a suspicious person, a reference image serving as background information for extracting a moving object, face feature information storing feature information of various facial images acquired in advance, and And a suspicious person image for storing the image at the time.

  The reference image is comparison reference information used to extract a moving object in the monitoring area in comparison with image data (hereinafter also referred to as an input image) input from the monitoring camera 31 in a fluctuation area extraction process described later. It is image data acquired by capturing an image of a monitoring area when there is no driver.

  The face feature information is the feature information for determining the face image of a person. For the face image obtained by capturing images of faces of various men and women from multiple directions in advance, the brightness pattern of each part such as the entire face and eyes, nose, mouth, etc. It is stored as facial feature information. Also, the brightness pattern of the face image stored in the face feature information is not only the face image of a normal person, but also a person wearing sunglasses, a person wearing a mask, a person whose face is hidden by hand, and a balaclava It also includes image information of the face and head of a person who is assumed to be a suspicious person, such as a person or a person wearing a full-face helmet, and the brightness associated with the attributes of the face image as the input source for these various face images The pattern is stored. The attributes of the face image are “normal” that does not hide the face, and “Sunglasses + mask”, “hand”, “balancing cap”, “full face”, etc. This is information indicating the state of the image.

  The suspicious person image is stored when the person included in the current image data is determined to be a suspicious person by the determination process by the control unit 34.

  The control unit 34 includes a microcomputer including a CPU, a ROM, a RAM, and the like and peripheral circuits thereof, and controls each unit described above. For this purpose, the control unit 34 includes, as a functional module realized by the microcomputer and a computer program executed on the microcomputer, a variable region extraction unit 341 that extracts a person region in the input image, and an input head from the input image. A head extraction unit 342 that extracts a human head region as a partial region; a face feature determination unit 343 that determines whether the head region in the input image is a head having facial feature information; A high-intensity region extraction unit 344 that determines whether or not the head region of the subject is glossy, and a suspicious person detection unit 345 that determines whether or not a person existing in the monitored area is a suspicious person whose face is hidden. Yes.

  The fluctuation region extraction unit 341 performs image processing on the input image to detect a person who becomes a moving object. The variation area extraction unit 341 compares the input image with the reference image stored in the storage unit 33, extracts the variation pixels whose luminance value variation is equal to or greater than a predetermined value, and sets a substantially continuous variation pixel group as one. Group as one variable area.

  The head extraction unit 342 extracts the region of the person's head part within the variation region extracted by the variation region extraction unit. The head extraction unit 342 extracts the edge component of the fluctuation region, detects an elliptical edge distribution that approximates the contour shape of the face in the edge image data, and determines the elliptical region surrounded by the edge distribution as the head of the person. Extract as a partial area. Various methods described in Japanese Patent Application Laid-Open No. 2005-25568 and Japanese Patent Application Laid-Open No. 2010-286274 by the present applicant can be adopted for the extraction process of the head region.

  Specifically, the head extraction unit 342 applies a known edge extraction filter such as a Sobel filter to the fluctuation region of the input image to obtain an edge strength and an edge angle (an edge direction with respect to the horizontal) to obtain an edge strength image. And generate an edge angle image. Then, the head extraction unit 342 performs shift matching on the edge strength image and the edge angle image using a plurality of ellipse templates having different sizes stored in advance, and obtains the similarity between the ellipse template and the edge component, A position having a high degree of similarity is extracted as a head region of a person, and is labeled with a label unique to each head region.

Note that the head region extraction method is not limited to this, and various known methods can be used. For example, the head region may be extracted using HOG (Histograms of Oriented Gradients) feature values. In this case, a luminance gradient direction histogram is obtained for each of a plurality of cells constituting the variable region to obtain a nine-dimensional feature vector, and the cell feature vector is normalized in the block region of the plurality of cells. A head region is extracted by obtaining a multidimensional feature vector for each block region and comparing it with a feature value of a head shape learned in advance. As a reference for HOG features, N. Dalal and
B. Triggs, "Histograms of oriented gradients for
human detection ", Proc. of IEEE Conference on Computer Vision and Pattern
Recognition (CVPR), pp.886-893, 2005, etc.

The face feature determination unit 343 covers the face of the head region extracted by the head extraction unit 342 with a face image of the face, sunglasses, a mask, a hand, or the like, or wearing a full-face helmet or the like. It is determined whether the face image is a face image in which a part or all of the part is hidden and the human phase is not known (no facial feature information).
The face feature determination unit 343 divides the extracted head region into a plurality of rectangular regions in the input image, and stores the divided head regions in the face feature information for each divided rectangular region and each block obtained by integrating adjacent divided rectangular regions. Pattern matching with the luminance pattern of the face image is performed. Then, from the attribute of the brightness pattern calculated with a high degree of similarity, an identification result as to which attribute face image is included or not included for each head region with a unique label Output.

For example, if a facial feature part (feature information) such as the eyes and nose can be extracted, it is determined that the face image has a “normal” attribute that does not conceal the face. When dark pixels are concentrated at the center in the direction and bright pixels are concentrated below the vertical direction, it is determined that the face is concealed as a face image having the “sunglasses + mask” attribute, and facial features such as the eyes, nose and mouth Cannot be extracted, and there are few edges in the head region, it is determined that the face is concealed as a face image having the “full face” attribute. Further, when a high similarity cannot be obtained with any of the patterns stored in the face feature information, it is determined that the head region is not a human head (a face image is not included).
The identification result of the face feature determination unit 343 is stored in the work area on the storage unit 33 in association with the input image and the unique label of the head area.

Note that the face image determination processing by the face feature determination unit 343 is not limited to this, and various known methods can be used. For example, an attribute identifier of the head region may be determined by an Adaboost discriminator using Haar-like features. The Haar-like feature is a luminance difference between a plurality of adjacent divided rectangular areas arbitrarily set in the head area of the input image. The Adaboost classifier includes a plurality of weak classifiers and a strong classifier that is determined by integrating the determination results of the weak classifiers. Each weak classifier calculates a different Haar-like feature from the input image region, and based on the calculated Haar-like feature, which attribute image is included in the head region or the face Outputs the identification result of whether an image is not included. Each weak classifier is generated by learning the Haar-like feature of the face image stored in the face feature information, and acquires the attribute of the face image accordingly. For details on Haar-like features and Adaboost classifiers, see, for example, Paul Viola and Michael Jones, "Rapid Object Detection using a
Boosted Cascade of Simple Features ", IEEE CVPR, vol.1, pp.511-518, 2001.

The high brightness area extraction unit 344 determines whether there is a high brightness area as gloss for each head area to which a unique label is attached.
The full-face helmet used by suspicious people as a means of concealing their face is formed into an almost elliptical shape with few joints for ease of care, and its smooth curved surface reflects the ambient ambient light such as lighting. As a result, a certain high-luminance region is generated. On the other hand, since the head of a person has fine irregularities due to hair, ambient light such as illumination diffuses and a high-brightness region as gloss is hardly generated. Therefore, the high brightness area extraction unit 344 extracts a high brightness area peculiar to the head wearing the full face helmet.

  The high brightness area extraction unit 344 binarizes the input image by a known method, normalizes the image in the head area to a fixed size for each head area to which a unique label is attached, and normalizes the normalized image. It is checked whether a white area having a predetermined area or more exists in the head image. The threshold value for binarization may be a value obtained by experiments. The binarized image is subjected to noise removal by expansion / contraction processing.

  Specifically, the high luminance area extraction unit 344 binarizes the input image using a threshold value obtained in advance through experiments, and performs known noise removal processing such as expansion / contraction processing on the black and white image. Then, normalization is performed by enlarging or reducing the image in the head region so that the circumscribed rectangle of the head region in the obtained black and white image becomes a preset fixed size (for example, 64 pixels × 64 pixels). A head image is generated. The high brightness area extraction unit 344 sets a search area for searching for a high brightness area in the obtained normalized head image. The search area is an area for searching for gloss generated by the full-face helmet reflecting ambient light, and based on the knowledge that ambient light such as illumination is irradiated from above, the lower part 1 in the vertical direction in the normalized head image The upper part excluding / 4 (that is, upper 64 pixels × 48 pixels) is set.

  The high-intensity area extraction unit 344 searches the search area of the normalized head image to extract white pixels, groups a group of substantially continuous white pixels as one white area, The area is calculated as the luminance candidate region. At this time, if a plurality of white areas are extracted in one normalized head image, only a predetermined number (for example, two) of areas having a large area are set as high brightness candidate areas of the head area. Then, for each normalized head image, the high luminance region extraction unit 344 determines the high luminance candidate region as a high luminance region if the total area of the high luminance candidate regions is equal to or larger than a predetermined determination area (for example, 20 pixels). Is determined. The determination result of the high luminance area extraction unit 344 is stored in the work area on the storage unit 33 in association with the input image and the unique label of the head area.

  That is, the high luminance region extraction unit 344 normalizes the image size in the head region and extracts a white region having a predetermined area or more as a high luminance region. In other words, it can be said that a white area having an area relatively larger than a predetermined ratio is extracted as a high luminance area.

  Note that the determination process by the high luminance region extraction unit 344 may be executed only for the head region in which the facial feature determination unit 343 determines the concealment of the face based on the “full face” attribute. In this case, the face feature determination unit 343 establishes the full face flag only in the head region determined as the “full face” attribute, and the high brightness region extraction unit 344 establishes the head in which the full face flag is established in the input image. Only when the region exists, the process of extracting the high brightness region for the head region is executed.

  The suspicious person detection unit 345 determines whether there is a suspicious person whose face is hidden in the monitoring area by integrating the determinations of the face feature determination unit 343 and the high brightness area extraction unit 344. When the suspicious person detection unit 345 determines that the head region of the input image includes an attribute in which the face feature determination unit 343 has concealed the face, that is, a face image having no facial feature information such as an eye-nose mouth, etc. The face image included in the head region to be determined is a suspicious person.

Here, in particular, when the facial feature determination unit 343 determines concealment of the face by the “full face” attribute for the head region of the input image, the suspicious person detection unit 345 performs a high-intensity region for the corresponding head region. With reference to the determination result of the extraction unit 344, if the presence of the high brightness region is determined, it is determined that the face image included in the head region is a suspicious person. On the other hand, if the presence of the high brightness region is not determined for the corresponding head region, it is determined that the face image included in the head region is not a suspicious person (normal).
Further, when the suspicious person detecting unit 345 determines that facial feature information such as the eyes and nose and mouth is extracted by the facial feature determining unit 343 for the head region of the input image and includes a facial image with normal attributes, and If it is determined that the face image is not included, it is determined that the face image included in the corresponding head region is not a suspicious person (normal).

  When the suspicious person detection unit 345 determines that the face image of the suspicious person is included in the input image, the suspicious person detection unit 345 generates an emergency signal including the address information of the suspicious person and attaches image data that determines the presence of the suspicious person. Then, the data is output to the communication unit 32 and transmitted from the communication unit 32 to the monitoring center 5. At this time, the image data determined to be present is stored in the storage unit 33 as a suspicious person image.

<Description of operation>
The operation of the monitoring system 1 configured as described above will be described with reference to the drawings. First, an outline of processing of the image monitoring apparatus 3 will be described with reference to FIG. FIG. 3 is a diagram schematically showing suspicious person monitoring processing by the image monitoring apparatus 3.

  FIG. 3A shows an input image captured by the monitoring camera 31. Image data is acquired by the monitoring camera 31 at predetermined intervals (for example, 0.2 seconds) and input to the control unit 34. When image data (input image) is input from the monitoring camera 31, the fluctuation region extraction unit 341 calculates and changes the difference between the input image and the reference image in the storage unit 33, as shown in FIG. Extract regions. Next, the head extraction unit 342 detects an elliptical edge distribution within the fluctuation region, and extracts an elliptical region surrounded by the edge distribution as a human head region.

  Next, as shown in FIG. 3C, the face feature determination unit 343 performs pattern matching between the extracted head region and the face feature information stored in the storage unit, and the calculated similarity is high. Read out the luminance pattern attribute, "normal" with facial feature information, "Sunglasses + mask", "hand", "balancing cap" with no facial feature information and concealed face ”,“ Full face ”, or any other attribute of the face image is included, or the identification result indicating whether the face image is not included is output. FIG. 3C shows an example in which the person on the left side in the figure is determined to be “normal” and the person on the right side in the figure is determined to be “full face”.

  Further, as shown in FIG. 3D, the high-intensity area extraction unit 344 binarizes the input image, normalizes the image in the head area to a fixed size (for example, 64 pixels × 64 pixels), and normalizes the input image. A white area (high brightness candidate area) is extracted using the upper part of the head image (for example, the upper 3/4 in the vertical direction) as a search area. Then, if the area of the high brightness candidate area is equal to or larger than a predetermined determination area (for example, 20 pixels), the high brightness area extraction unit 344 determines that the high brightness area exists in the head area.

  The suspicious person detection unit 345 receives the determination result of the face feature determination unit 343 shown in FIG. 3C and the determination result of the high brightness region extraction unit 344 shown in FIG. Detect people. In particular, as shown in FIG. 3E, the suspicious person detection unit 345 determines that the face feature determination unit 343 determines that the face is concealed based on the “full face” attribute, With reference to the determination result of the extraction unit 344, if the presence of the high-luminance region is determined, it is determined that the face image included in the head region is a suspicious person whose face is concealed with a full-face helmet. On the other hand, even if the face feature determination unit 343 determines a face based on the “full face” attribute, the suspicious person detection unit 345 includes the face image included in the head region unless the presence of the high brightness region is determined. Is determined not to be a suspicious person (normal).

  As described above, when determining the concealment of a face by a full-face helmet, it is a condition that there is a high-luminance region of a predetermined area or more, so a normal person's occipital region is erroneously determined as a full-face helmet. This can be prevented. In particular, since the search range for the high brightness area in the head area is limited to the upper part only, it is possible to prevent erroneous detection of a shirt area on the back of the head as a high brightness area. Determination accuracy can be improved.

  Further, as shown in FIG. 3E, the suspicious person detection unit 345 determines that the head region determined to be a face image having a normal attribute by the face feature determination unit 343 is not a suspicious person (normal), and the face The head region determined as a face image having an attribute that conceals a face other than the “full face” attribute by the feature determination unit 343 is determined to be a suspicious person based on the attribute. The determination result by the suspicious person detection unit 345 is reported from the communication unit 32 to the remote monitoring center 5.

Next, the operation of the suspicious person monitoring process by the image monitoring apparatus 3 shown in FIG. 3 will be described with reference to FIGS. FIG. 4 is a flowchart showing the operation of the monitoring program repeatedly executed by the control unit 34 of the image monitoring apparatus 3.
The image monitoring device 3 receives the output of the image data captured by the monitoring camera 31 every predetermined cycle (for example, 0.2 second cycle, that is, 5 fps (frame / second)) and inputs it to the control unit 34 (step ST1). The fluctuation area extraction unit 341 calculates the difference between the input image and the reference image in the storage unit 33 and extracts the fluctuation area (step ST2). If the fluctuation region cannot be extracted, the series of processes is terminated, and the process is executed from step ST1 at the next execution timing.

  In step ST3, the head extraction unit 342 extracts a person's head region from the variation region extracted by the variation region extraction unit 341. If the head region cannot be extracted, the series of processing ends, and the processing is executed from step ST1 at the next execution timing. Next, the face feature determination unit 343 performs pattern matching between the extracted head region and the face feature information stored in the storage unit 33 to determine which attribute of the face image is included or whether the face image is An identification result as to whether it is not included is output (step ST4). If face images are not included for all the head regions in the input image, the series of processing ends, and processing is executed from step ST1 at the next execution timing.

  In step ST5, the high brightness area extraction unit 344 executes a high brightness area determination process for determining whether a high brightness area exists for each head area. The high brightness area determination process will be described later.

  The suspicious person detection unit 345 refers to the result of the face feature determination process, and when there is a head region having an attribute that conceals a face that does not have facial feature information (step ST6-Yes), the head region is It is determined whether or not the face is hidden by the “full face” attribute (step ST7). If the face is concealed by the “full face” attribute (step ST7—Yes), it is checked whether or not the presence of a high brightness area is determined in the head area in the high brightness area determination process. If a high brightness area exists (step ST8-Yes), the head area is determined to be a suspicious person (step ST9). On the other hand, if it is not determined in step ST8 that a high-luminance region is present in the head region (step ST8-No), it is determined that the head region is not a full-face helmet such as the back of the head and a suspicious person is determined. Do not do. Further, the suspicious person detection unit determines that the head region determined to be masked by the face feature determination unit 343 other than the “full face” attribute (step ST7—No) is a suspicious person based on the attribute. .

  The suspicious person detection unit 345 determines whether or not there is a suspicious person in the input image by performing the processes of steps ST6 to ST9 for all the head regions in the input image to determine whether or not the suspicious person is present (step ST10). (Step ST11-Yes), an emergency signal including its own address information is transmitted from the communication unit 32 together with the image data for which the presence of the suspicious person is determined (Step ST12).

The basic operation of the image monitoring apparatus 3 has been described above.
Next, the high brightness area determination process in step ST5 of FIG. 4 will be described with reference to FIG. FIG. 5 is a flowchart of the high brightness area determination process performed by the high brightness area extraction unit 344. In FIG. 5, the high brightness area extraction unit 344 binarizes the input image and performs noise removal on the black and white image by expansion / contraction processing or the like (step ST21). Next, the image is enlarged or reduced for each head region so that the circumscribed rectangle of the head region in the monochrome image becomes a preset fixed size (for example, 64 pixels × 64 pixels), and the normalized head An image is generated (step ST22).

  In step ST23, the high-intensity region extraction unit 344 sets a search region in the upper portion (that is, upper 64 pixels × 48 pixels) excluding the lower 1/4 in the vertical direction in the normalized head image. Then, the high brightness area extraction unit 344 extracts a white area in the search area of the normalized head image as a high brightness candidate area (step ST24). At this time, if a plurality of white areas are extracted in one normalized head image, only a predetermined number (for example, two) of areas having a large area is set as a high brightness candidate area of the head area. .

The high luminance area extraction unit 344 determines, for each normalized head image, whether the area of the high luminance candidate area (the total of the areas when there are plural areas) is equal to or larger than a predetermined determination area (for example, 20 pixels) (step ST25). If it is equal to or larger than the determination area, the high brightness candidate area is determined as a high brightness area, and it is determined that the high brightness area exists in the head area (step ST26). On the other hand, if the area of the high brightness candidate area is less than the determination area (step ST25-No), the high brightness candidate area is not determined as the high brightness area.
The high-intensity area extraction unit 344 determines whether or not there is a high-intensity area by performing the processing of steps ST23 to ST26 for all head areas (normalized head images) in the input image (step ST27). The process ends.

As described above, the high-intensity region extraction unit 344 determines whether a high-intensity region having a predetermined area or more exists in the head region included in the input image, and the suspicious person detection unit 345 determines that the face is concealed. Only when it is determined that there is a high-luminance region for the head region, it is determined that there is a suspicious person with a full-face helmet. On the other hand, even if it is a head region similar to a full-face helmet, it is not determined as a suspicious person when there is no high luminance region.
As a result, it has a smooth curved surface that prevents the back of the human head from being misdetected as a full-face helmet because it has minute irregularities due to hair and diffuses ambient light such as lighting and does not easily cause glossy shine. However, it is possible to accurately detect a full-face helmet that reflects ambient light such as lighting and generates a certain amount of glossy luster.

  The embodiments of the present invention have been described above by way of example, but the scope of the present invention is not limited to these embodiments, and can be changed or modified according to the purpose within the scope of the claims. is there.

DESCRIPTION OF SYMBOLS 1 Monitoring system 2 Storage 3 Image monitoring apparatus 31 Monitoring camera 32 Communication part 33 Storage part 34 Control part 341 Fluctuation area extraction part 342 Head extraction part 343 Face feature determination part 344 High brightness area extraction part 345 Suspicious person detection part 4 Communication Network 5 Monitoring center 51 Center device 52 Display

Claims (3)

An image surveillance apparatus for detecting a suspicious individual concealed more face helmet in the monitoring space,
An imaging unit that periodically images the monitoring space to obtain a monitoring image;
A storage unit for storing face feature information of a person in advance;
A head extraction unit that extracts an input head region corresponding to a person's head from the monitoring image;
A facial feature determination unit that determines whether the input head region has facial feature information using the facial feature information;
A high-intensity region extraction unit that determines whether a high-intensity region of a predetermined area or more exists in the input head region;
A suspicious person detection unit that determines that there is no facial feature information in the face characteristic determination unit and that the high luminance region extraction unit determines the presence of the high luminance region is a suspicious person who conceals the face. When,
An image monitoring apparatus comprising:
The image monitoring apparatus according to claim 1, wherein the high-intensity region extraction unit determines whether there is a high-intensity region having an area that is a predetermined ratio or more with respect to the area of the input head region.
The image monitoring apparatus according to claim 1, wherein the high-intensity region extraction unit sets a predetermined upper range of the input head region as a search region, and extracts the high-intensity region in the search region.