JP5044207B2 - Imaging device - Google Patents

Description

  The present invention relates to an imaging apparatus that is used in a door phone system and detects a human body existing within a predetermined area.

  Conventionally, an imaging apparatus (sensor camera) having a function of performing human body detection (human body detection), tracking, and the like by image processing has been proposed (for example, see Patent Documents 1 and 2).

Here, as an image pickup apparatus that detects a human body by image processing, an image pickup unit that picks up a predetermined area, a contour extractor that extracts a contour from an image picked up by the image pickup unit, and a contour extracted by the contour extractor are moved. Extracted by a moving contour extracting means for extracting a contour of a body, a moving area extracting means for detecting a moving area consisting of a rectangular area circumscribing the contour of the moving body extracted by the moving contour extracting means, and a moving area extracting means. Based on the edge direction value distribution created by the area feature quantity detection means that extracts the direction value of the moving edge part in the movement area based on the movement area and creates the edge direction value distribution, and based on the edge direction value distribution created by the area feature quantity detection means A thing provided with a human body detection means which performs human body detection is proposed.
JP 2005-115932 A JP-A-8-249471

  By the way, the edge direction value distribution is used for detecting the human body because the contour (edge) of the human body has more curved portions than the straight portions and has a complicated shape, so the edge directions are distributed in all directions. On the other hand, edges such as shadows of structures have many linear components, and this is based on the reason that the distribution of edges tends to be biased.

  However, since the degree of distribution in the edge direction differs depending on the physique and posture of the person, if the allowable range for determining the human body is narrowed, the number of cases where it is determined that the human body is not a human body increases. On the other hand, if the permissible range is widened, the number of cases where a moving region by a moving body other than the human body is determined to be a human body increases.

  In particular, plants and neon signs using neon tubes have many curved parts in their contours. For example, if there are moving objects such as plants swayed by the wind in the imaging area, such moving objects In many cases, it is determined that the moving area by the human body is a human body, and a moving body other than the human body is erroneously detected as a human body.

  The present invention has been made in view of the above points, and an object of the present invention is to provide an imaging device capable of suppressing erroneous detection of a moving body other than a human body as a human body and improving the reliability of human body detection. There is to do.

According to the first aspect of the present invention, there is provided an imaging device connected to a door phone master unit for a door phone system that enables a call between a house and an outside, from an imaging unit that captures a predetermined area and an image captured by the imaging unit. A contour extracting unit for extracting a contour, a moving contour extracting unit for extracting a contour of a moving object from the contour extracted by the contour extracting unit, and a rectangular region circumscribing the contour of the moving object extracted by the moving contour extracting unit A moving area extracting means for detecting a moving area; a human body detecting means for detecting a human body based on the moving area; and a transmitting means for transmitting an image captured by the imaging means to the intercom master unit. Tracking a movement area between a plurality of images arranged in time series order, calculating a motion vector between images adjacent in time series in the plurality of images for the movement area, and calculating the calculated motion Human body detection that calculates a percentage of the total number of motion vectors for each direction of the turtle and determines that the moving region is due to a human body if the percentage of motion vectors in a predetermined direction or the percentage of motion vectors in all directions is greater than or equal to a predetermined percentage It is comprised so that determination may be performed.

According to the first aspect of the present invention, while the movement area by the human body often exhibits a behavior that moves in a predetermined direction, the movement area by the moving body other than the human body such as a plant swaying in the wind reciprocates. Paying attention to the relatively frequent behavior that moves, calculate the motion vector between adjacent images in time series in multiple images arranged in time series, and for each direction of the calculated motion vector Since the ratio to the total number of motion vectors is calculated, and if the ratio of motion vectors in a predetermined direction or the ratio of all motion vectors in all directions is equal to or greater than the predetermined ratio, the moving area is determined to be a human body. Can be prevented from being erroneously detected as a human body, and the reliability of human body detection can be improved. Further, since only the arithmetic processing in the human body detecting means needs to be added, it is not necessary to add a new device or the like, and the cost can be reduced.

According to a second aspect of the present invention , there is provided an imaging device connected to a door phone master unit for a door phone system that enables a telephone call between a house and an outside , wherein the imaging device captures a predetermined area and an image captured by the imaging device. A contour extracting unit for extracting a contour, a moving contour extracting unit for extracting a contour of a moving object from the contour extracted by the contour extracting unit, and a rectangular region circumscribing the contour of the moving object extracted by the moving contour extracting unit A moving area extracting means for detecting a moving area; a human body detecting means for detecting a human body based on the moving area; and a transmitting means for transmitting an image captured by the imaging means to the intercom master unit. The size of the motion vector when moving linearly from the position of the moving area of the first image in time series to the position of the moving area of the last image in time series in a plurality of images arranged in time series order is added. Calculated as a moving distance of the moving region, and calculates a motion vector between chronologically adjacent images in the plurality of images for the movement area, the ratio of the total number of motion vectors for each direction of the calculated motion vector Calculating and detecting the human body if the moving distance is equal to or greater than a predetermined value, and if the ratio of motion vectors in a predetermined direction or the ratio of all motion vectors in all directions is equal to or greater than a predetermined ratio, It is comprised so that it may perform.

According to the invention of claim 2, while the movement area by the human body is relatively likely to move in a predetermined direction, the movement area by the moving body other than the human body such as a plant swaying in the wind is reciprocated. Focusing on the relatively frequent behavior that moves, the movement distance of the movement area is calculated from a plurality of images arranged in chronological order, and if the movement distance is a predetermined distance or more, the movement area is Since it determines with a human body, it can suppress misdetecting a mobile body other than a human body as a human body, and can improve the reliability of a human body detection. Further, since only the arithmetic processing in the human body detecting means needs to be added, it is not necessary to add a new device or the like, and the cost can be reduced. In addition, according to the present invention, the magnitude of the motion vector when moving linearly from the position of the moving area of the first image in time series to the position of the moving area of the last image in time series is tracked. Since the moving distance is the moving area, it becomes easy to distinguish the moving area that moves in a predetermined direction from the moving area that moves back and forth, and a moving body other than the human body is erroneously detected as a human body. Can be further suppressed, and the reliability of human body detection can be improved. Furthermore, in performing human body detection determination, considering not only the moving distance of the moving area but also the direction of the motion vector of the moving area, it is possible to further suppress erroneous detection of a moving body other than a human body as a human body, The reliability of human body detection can be further improved.

According to a third aspect of the present invention, there is provided an imaging device connected to a door phone master unit for a door phone system that enables a call between a house and an outside , from an imaging unit that images a predetermined area and an image captured by the imaging unit. A contour extracting unit for extracting a contour, a moving contour extracting unit for extracting a contour of a moving object from the contour extracted by the contour extracting unit, and a rectangular region circumscribing the contour of the moving object extracted by the moving contour extracting unit A moving area extracting means for detecting a moving area; a human body detecting means for detecting a human body based on the moving area; and a transmitting means for transmitting an image picked up by the imaging means to the intercom. When the moving area group whose distance between the moving areas is equal to or less than a predetermined value exists in the extracted moving area group, the integrated moving area composed of a rectangular area of the minimum range including these moving area groups Is configured to create the human body detecting means, when linearly to the position of the moving region of the sequence to the last image when the position of the moving region of the time series the first image in a plurality of images arranged in chronological order The magnitude of the motion vector at the time of movement is calculated as the movement distance of the movement area to be tracked. If the movement distance is equal to or greater than a predetermined distance, human body detection determination is performed to determine that the movement area is due to a human body, An integrated moving area is used for tracking the area, and a moving area is used for calculating the moving distance.

According to the invention of claim 3, while the movement area by the human body is relatively often shown to move in a predetermined direction, the movement area by the moving body other than the human body such as a plant swaying in the wind reciprocates. Focusing on the relatively frequent behavior that moves, the movement distance of the movement area is calculated from a plurality of images arranged in chronological order, and if the movement distance is a predetermined distance or more, the movement area is Since it determines with a human body, it can suppress misdetecting a mobile body other than a human body as a human body, and can improve the reliability of a human body detection. Further, since only the arithmetic processing in the human body detecting means needs to be added, it is not necessary to add a new device or the like, and the cost can be reduced. In addition, according to the present invention, the magnitude of the motion vector when moving linearly from the position of the moving area of the first image in time series to the position of the moving area of the last image in time series is tracked. Since the moving distance is the moving area, it becomes easy to distinguish the moving area that moves in a predetermined direction from the moving area that moves back and forth, and a moving body other than the human body is erroneously detected as a human body. Can be further suppressed, and the reliability of human body detection can be improved. Furthermore, since an integrated moving area is created based on the moving distance and the moving area is tracked using the integrated moving area, tracking can be performed even if the moving area is divided into multiple areas, and the tracking accuracy of the moving area is improved. Can be improved. In addition, since the center of gravity position is different between the moving area and the integrated moving area including the moving distance, there is a possibility that a correct moving distance may not be obtained due to the difference in the center of gravity position. Since the movement area is used without being used, it is possible to prevent the correct movement distance from being obtained.

According to a fourth aspect of the present invention, there is provided an imaging device connected to a door phone master unit for a door phone system that enables a telephone call between a house and an outside , wherein the imaging device captures a predetermined area and the image captured by the imaging device. A contour extracting unit for extracting a contour, a moving contour extracting unit for extracting a contour of a moving object from the contour extracted by the contour extracting unit, and a rectangular region circumscribing the contour of the moving object extracted by the moving contour extracting unit A moving area extracting means for detecting a moving area; a human body detecting means for detecting a human body based on the moving area; and a transmitting means for transmitting an image captured by the imaging means to the intercom master unit. The magnitude of the motion vector when moving linearly from the position of the moving area of the first image in time series to the position of the moving area of the last image in time series in a plurality of images arranged in time series order, Calculated as a moving distance of the moving area of marks, if the movement distance is more than a predetermined distance and the moving region is configured to perform determining a human body detection determined by the human body, according to the moving direction of the moving region Thus, the moving distance of the moving area in the moving direction is weighted.

According to the invention of claim 4, while the movement area by the human body is relatively often shown to move in a predetermined direction, the movement area by the moving body other than the human body such as a plant swaying in the wind reciprocates. Focusing on the relatively frequent behavior that moves, the movement distance of the movement area is calculated from a plurality of images arranged in chronological order, and if the movement distance is a predetermined distance or more, the movement area is Since it determines with a human body, it can suppress misdetecting a mobile body other than a human body as a human body, and can improve the reliability of a human body detection. Further, since only the arithmetic processing in the human body detecting means needs to be added, it is not necessary to add a new device or the like, and cost can be reduced. In addition, according to the present invention, the magnitude of the motion vector when moving linearly from the position of the moving area of the first image in time series to the position of the moving area of the last image in time series is tracked. Since the moving distance is the moving area, it becomes easy to distinguish the moving area that moves in a predetermined direction from the moving area that moves back and forth, and a moving body other than the human body is erroneously detected as a human body. Can be further suppressed, and the reliability of human body detection can be improved. Further, when the moving direction of the human body is likely to be biased, for example, the moving distance in the moving direction having a high probability of being the moving direction of the human body is given a weight so that the moving distance becomes larger than the other moving directions. Thus, it becomes easy to distinguish between the human body and other mobile bodies, and it is possible to further suppress erroneous detection of a mobile body other than the human body as a human body.

According to the invention of claim 5 , there is provided an imaging device connected to a door phone master unit for a door phone system capable of making a call between a house and an outside , from an imaging means for imaging a predetermined area and an image taken by the imaging means. A contour extracting unit for extracting a contour, a moving contour extracting unit for extracting a contour of a moving object from the contour extracted by the contour extracting unit, and a rectangular region circumscribing the contour of the moving object extracted by the moving contour extracting unit A moving area extracting means for detecting a moving area; a human body detecting means for detecting a human body based on the moving area; and a transmitting means for transmitting an image captured by the imaging means to the intercom master unit. The magnitude of the motion vector when moving linearly from the position of the moving area of the first image in time series to the position of the moving area of the last image in time series in a plurality of images arranged in time series order, Calculated as a moving distance of the moving area of marks, if the movement distance is more than a predetermined distance and the moving region is configured to perform determining a human body detection determined by the human body, the moving direction of the moving area is the same When moving in the direction, the moving direction is given a weight.

According to the invention of claim 5, while the movement area by the human body is relatively often shown to move in a predetermined direction, the movement area by the moving body other than the human body such as a plant swaying in the wind reciprocates. Focusing on the relatively frequent behavior that moves, the movement distance of the movement area is calculated from a plurality of images arranged in chronological order, and if the movement distance is a predetermined distance or more, the movement area is Since it determines with a human body, it can suppress misdetecting a mobile body other than a human body as a human body, and can improve the reliability of a human body detection. Further, since only the arithmetic processing in the human body detecting means needs to be added, it is not necessary to add a new device or the like, and the cost can be reduced. In addition, according to the present invention, the magnitude of the motion vector when moving linearly from the position of the moving area of the first image in time series to the position of the moving area of the last image in time series is tracked. Since the moving distance is the moving area, it becomes easy to distinguish the moving area that moves in a predetermined direction from the moving area that moves back and forth, and a moving body other than the human body is erroneously detected as a human body. Can be further suppressed, and the reliability of human body detection can be improved. Furthermore, when the moving direction of the moving region continues in the same direction, the moving direction is given a weight, so that, for example, the moving speed is extremely slow but the moving speed is extremely slow to move in the same direction. Even a moving region where the distance does not exceed the predetermined distance and is not determined to be a human body can be determined as a human body, so that the reliability of human body detection can be increased.

According to the sixth aspect of the present invention, there is provided an imaging device connected to a door phone master unit for a door phone system that enables a call between a house and an outside , from an imaging unit that captures a predetermined area and an image captured by the imaging unit. A contour extracting unit for extracting a contour, a moving contour extracting unit for extracting a contour of a moving object from the contour extracted by the contour extracting unit, and a rectangular region circumscribing the contour of the moving object extracted by the moving contour extracting unit A moving area extracting means for detecting a moving area, a human body detecting means for detecting a human body based on the moving area, a transmitting means for transmitting an image picked up by the image pickup means to the doorphone master unit, and detecting a wind speed of the predetermined area and a wind velocity meter for the human body detecting means, when the position of the moving area of the time series the first image in the case, when arranged in chronological order a plurality of image output anemometer is a predetermined value or more sequences Next, the magnitude of the motion vector when moving linearly to the position of the moving area of the last image is calculated as the moving distance of the moving area to be tracked. It is configured to perform the human body detection determination that determines that the above is.

According to the invention of claim 6, while the movement area by the human body is relatively often shown to move in a predetermined direction, the movement area by the moving body other than the human body such as a plant swaying in the wind reciprocates. Focusing on the relatively frequent behavior that moves, the movement distance of the movement area is calculated from a plurality of images arranged in chronological order, and if the movement distance is a predetermined distance or more, the movement area is Since it determines with a human body, it can suppress misdetecting a mobile body other than a human body as a human body, and can improve the reliability of a human body detection. Further, since only the arithmetic processing in the human body detecting means needs to be added, it is not necessary to add a new device or the like, and the cost can be reduced. In addition, according to the present invention, the magnitude of the motion vector when moving linearly from the position of the moving area of the first image in time series to the position of the moving area of the last image in time series is tracked. Since the moving distance is the moving area, it becomes easy to distinguish the moving area that moves in a predetermined direction from the moving area that moves back and forth, and a moving body other than the human body is erroneously detected as a human body. Can be further suppressed, and the reliability of human body detection can be improved. Furthermore, when the output of the anemometer is less than a predetermined value, for example, when there is a low probability that the plant will not be shaken by the wind and the plant is erroneously detected as a human body, the human body detection determination is not performed, and the anemometer output is greater than or equal to the predetermined value Since the human body detection determination is performed only when there is a high probability that a plant will be erroneously detected as a human body, the processing speed can be improved.

According to the seventh aspect of the present invention, there is provided an imaging device connected to a door phone master unit for a door phone system that enables a telephone call between a house and an outside , from an image picked up by an image pickup means and an image picked up by the image pickup means. A contour extracting unit for extracting a contour, a moving contour extracting unit for extracting a contour of a moving object from the contour extracted by the contour extracting unit, and a rectangular region circumscribing the contour of the moving object extracted by the moving contour extracting unit A moving area extracting means for detecting a moving area; a human body detecting means for detecting a human body based on the moving area; and a transmitting means for transmitting an image captured by the imaging means to the intercom master unit. The magnitude of the motion vector when moving linearly from the position of the moving area of the first image in time series to the position of the moving area of the last image in time series in a plurality of images arranged in time series order, Calculated as a moving distance of the moving area of marks, if the movement distance is more than a predetermined distance and the moving region is configured to perform determining a human body detection determined by the human body, the movement between the plurality of images When the area does not move outside the predetermined range, the predetermined distance is set to a value larger than the maximum movement distance of the movement area.

According to the invention of claim 7, while the movement area by the human body is relatively often shown to move in a predetermined direction, the movement area by the moving body other than the human body such as a plant swaying in the wind reciprocates. Focusing on the relatively frequent behavior that moves, the movement distance of the movement area is calculated from a plurality of images arranged in chronological order, and if the movement distance is a predetermined distance or more, the movement area is Since it determines with a human body, it can suppress misdetecting a mobile body other than a human body as a human body, and can improve the reliability of a human body detection. Further, since only the arithmetic processing in the human body detecting means needs to be added, it is not necessary to add a new device or the like, and the cost can be reduced. In addition, according to the present invention, the magnitude of the motion vector when moving linearly from the position of the moving area of the first image in time series to the position of the moving area of the last image in time series is tracked. Since the moving distance is the moving area, it becomes easy to distinguish the moving area that moves in a predetermined direction from the moving area that moves back and forth, and a moving body other than the human body is erroneously detected as a human body. Can be further suppressed, and the reliability of human body detection can be improved. Furthermore, a moving area that remains within a predetermined range has a low probability of being a human body to be detected such as an intruder, and the predetermined distance is set to a value larger than the maximum moving distance of such a moving area. Since the distance is not determined as a human body, it is possible to further suppress erroneous detection of a moving body other than a human body as a human body.

According to an eighth aspect of the present invention, there is provided an imaging device connected to a doorphone master unit for a doorphone system that enables a call between a house and an outside , from an imaging unit that images a predetermined area and an image captured by the imaging unit. A contour extracting unit for extracting a contour, a moving contour extracting unit for extracting a contour of a moving object from the contour extracted by the contour extracting unit, and a rectangular region circumscribing the contour of the moving object extracted by the moving contour extracting unit Moving area extracting means for detecting a moving area, human body detecting means for detecting a human body based on the moving area, transmitting means for transmitting an image captured by the imaging means to the intercom master unit, and moving area by the moving area extracting means the moving area after extraction and a region information storage means for moving area information is stored with the position and the moving distance of the moving area of until the disappearance from the image Human body detection means, the time series motion vector when moved linearly to a position of the moving region of the time series the last image from the position of the moving region of the first image in the time series order in a plurality of images aligned The size is calculated as the moving distance of the moving area to be tracked. If the moving distance is equal to or greater than the predetermined distance, human body detection determination is performed to determine that the moving area is due to a human body, and the movement stored in the area information storage unit If the moving area represented by the area information is not a human body, the moving area represented by the moving area information similar to the moving area information is determined not to be a human body. And

According to the invention of claim 8, while the movement area by the human body is relatively often shown to move in a predetermined direction, the movement area by the moving body other than the human body such as a plant swaying in the wind reciprocates. Focusing on the relatively frequent behavior that moves, the movement distance of the movement area is calculated from a plurality of images arranged in chronological order, and if the movement distance is a predetermined distance or more, the movement area is Since it determines with a human body, it can suppress misdetecting a mobile body other than a human body as a human body, and can improve the reliability of a human body detection. Further, since only the arithmetic processing in the human body detecting means needs to be added, it is not necessary to add a new device or the like, and cost can be reduced. In addition, according to the present invention, the magnitude of the motion vector when moving linearly from the position of the moving area of the first image in time series to the position of the moving area of the last image in time series is tracked. Since the moving distance is the moving area, it becomes easy to distinguish the moving area that moves in a predetermined direction from the moving area that moves back and forth, and a moving body other than the human body is erroneously detected as a human body. Can be further suppressed, and the reliability of human body detection can be improved. Furthermore, since it is determined that the moving area represented by the moving area information similar to the moving area information representing the moving area determined not to be a human body is not a human body, a moving body other than the human body is erroneously detected as a human body This can be further suppressed.
The invention according to claim 9 is the invention according to any one of claims 2 to 8, wherein the human body detecting means is configured to change the value of the predetermined distance in accordance with the position of the moving region on the image. It is characterized by being.
According to the ninth aspect of the invention, it is possible to correct the amount of change in the moving distance of the moving area due to the influence of the distortion of the lens of the image pickup means, the peripheral light amount ratio, and the like, and the reliability can be improved. .
According to a tenth aspect of the present invention, in any one of the first to ninth aspects, the human body detecting means determines whether or not the moving area is a human body based on the size of the moving area. It is configured.
According to the invention of claim 10, since it is determined whether or not it is a human body depending on the size of the moving region, it is possible to further suppress erroneous detection of a moving body other than the human body as a human body.
According to an eleventh aspect of the present invention, in any one of the first to tenth aspects, the direction value of the moving edge portion in the moving area is extracted based on the moving area of the moving body detected by the moving area extracting means. Region feature quantity detection means for creating the edge direction value distribution, and the human body detection means is configured to perform human body detection based on the edge direction value distribution obtained from the area feature quantity detection means. And
According to the eleventh aspect of the present invention, since the edge of the human body is more complicated than the straight line portion and has a complicated shape, the moving region is distributed in all directions. Therefore, it is possible to further suppress erroneous detection of a moving body other than a human body as a human body.
According to a twelfth aspect of the present invention, in any one of the first to eleventh aspects of the present invention, the human body detector using infrared rays having the predetermined area as a detection range is provided, When the human body is detected, the human body detection determination is performed.
According to the twelfth aspect of the present invention, the human body detection determination is performed only when the human body is detected by the human body detector. Since it does not perform, it can further suppress that a mobile body other than a human body is erroneously detected as a human body.

  While the present invention relatively often shows a behavior in which a moving area of a human body moves in a predetermined direction, a movement area of a moving body other than the human body such as a plant swaying in the wind behaves in a reciprocating manner. Since it is determined whether or not the moving region is due to a human body, it is possible to suppress erroneous detection of a moving body other than a human body as a human body, and the reliability of human body detection There is an effect of improving the sex.

(Embodiment 1)
As shown in FIG. 2, the image pickup apparatus A (see FIG. 1) of the present embodiment has a function of monitoring an image obtained by the image pickup apparatus A and a doorphone master unit B installed indoors in a house D, Together with the doorphone sub-unit C installed outside the house D, the doorphone system that enables a call between the inside and outside of the house is configured. Note that the imaging apparatus A is installed in the garden of the house D.

  The imaging device A is, for example, a sensor-equipped camera connected to the door phone master unit B. As shown in FIG. 1, the imaging device A is in the predetermined area based on an image obtained by the imaging means 10 that images the predetermined area. An image processing type human body detection device 1 that detects the presence of a person, a hot-wire type human body detector (PIR) 2 that uses infrared rays (heat rays) with the predetermined area as a detection range, and threatens intruders And a notification means 3 for this purpose.

  The human body detection device 1 is an image processing type human body detection device. As shown in FIG. 1, the human body detection device 1 mainly transmits an image capturing unit 10 that captures an image of a predetermined area, and transmits an image obtained by the image capturing unit 10 to the intercom base unit B. Transmission means 15, image processing means 12 for detecting a human body based on the image obtained by the imaging means 10, and signal processing means 14 for controlling these operations.

  The image pickup means 10 generates a grayscale image by converting an image output device (not shown) such as a CCD image sensor that continuously images the predetermined area in time series and an image output from the image pickup device into digital data. And an A / D converter that outputs the YUV signal. In addition to the CCD image sensor, a CMOS image sensor or the like may be used as the image sensor. In general, a CMOS image sensor manufactured by a system-on-chip (SoC) technology includes a processing circuit such as an A / D converter in a package. Therefore, unlike a case where a CCD image sensor is used, an A / D converter is used. May not be provided separately.

  The image output from the imaging unit 10 is input to the output data converter 11 and the image processing unit 12. Here, the output data converter 11 has a YUV / NTSC conversion function for converting an image composed of a YUV signal output from the imaging means 10 into an image composed of an NTSC (National TV Standards Committee) signal. The converted image is output to the transmission means 15.

  The image processing means 12 is for detecting a person in a predetermined area based on the image information obtained by the image pickup means 10, and as shown in FIG. 1, from the image picked up by the image pickup means 10. Based on the contour extraction means 12a for extracting the contour, the moving contour extraction means 12b for extracting the contour of the moving object from the contour extracted by the contour extracting means 12a, and the moving region based on the contour of the moving object extracted by the moving contour extracting means 12b Region extracting means 12c for extracting the region, region feature amount detecting means 12d for creating the edge direction value distribution of the moving region extracted by the moving region extracting unit 12c, and human body detection based on the moving region and its edge direction value distribution And a human body detecting means 12e.

  The contour extraction unit 12a performs differential processing (calculates a differential value of each pixel) on the image obtained from the imaging unit 10 by using a generally known SOBEL filter or the like, and extracts a contour (edge). The contour image of each image is stored in the contour image storage means 13 comprising a storage device such as a RAM for a certain period. The contour extracting unit 12a is configured to start an operation when a start signal described later is received from the signal processing unit 14. That is, the image processing unit 12 starts to operate when a start signal is output from the signal processing unit 14.

  The moving contour extraction unit 12b performs logical synthesis using the time-series contour images stored in the contour image storage unit 13, and extracts a combined image obtained by extracting only the contour of the moving body (hereinafter referred to as “moving contour”). To create.

  The moving area extracting means 12c detects the area corresponding to the moving body (hereinafter referred to as “moving area”) by labeling the composite image created by the moving contour extracting means 12b. The region is configured to be represented by a rectangular (quadrangle) region (moving frame) circumscribing the moving contour.

  The area feature quantity detection means 12d extracts the direction value of the moving edge portion in the moving area based on the edge image stored in the contour image storage means 13 and the moving area of the moving object detected by the moving area extraction means 12c. Then, the edge direction value distribution is created, and the edge direction value distribution is output as a feature amount. Here, the direction value (direction code) is a value indicating the change direction of the density value of the differential value of each pixel calculated in the contour extracting means 12a, and is an integer value associated with each of the 8 directions in increments of 45 degrees. It is represented by In addition, the direction value is set so as to represent a direction orthogonal to the direction in which the density value change is maximized in the image. Therefore, the direction indicated by the direction value in each pixel substantially coincides with the direction indicating the pixel on the edge (the three pixels adjacent to each other within the range of ± 45 degrees with respect to the direction indicated by the direction code of each pixel are Likely to be pixels on the edge). The edge direction value distribution is obtained by creating a frequency distribution related to the direction value obtained as described above. In creating the edge direction value distribution, the direction values that differ by 180 degrees may be treated as being the same.

  The human body detection unit 12e is configured to perform human body detection based on the movement region obtained by the movement region extraction unit 12c and the edge direction value distribution obtained by the region feature amount detection unit 12d.

  The human body detection operation by the human body detection unit 12e will be described below. First, the human body detecting unit 12e determines whether or not the moving region is a human body based on the size of the moving region obtained from the moving region extracting unit 12c (first determination). For example, in the first determination, when the size of the moving area is included within a predetermined range, the moving area is determined to be a human body. Here, the predetermined range is determined based on the size of the moving area of the human body. For example, the vertical length of the moving area (that is, the number of pixels in the vertical direction of the moving area) and the horizontal direction If each of the lengths (that is, the number of pixels in the horizontal direction of the moving area) is a value within a predetermined range and the vertical length is larger than the horizontal length, the moving area is determined by the human body. Is determined.

  According to the first determination described above, a movement area that is not due to a human body is removed from the plurality of movement areas detected by the movement area extraction unit 12c, and a movement area that has not been removed, that is, a movement area that is not removed by the human body according to the first determination. For the moving region determined to be a thing, the human body detection determination which is the second determination is performed.

  In the human body detection determination, a moving area is tracked between a plurality of images arranged in time series, and the moving distance is calculated from the plurality of images for the tracked moving area. It is determined that the area is due to the human body. In addition, it is preferable that the time for tracking the moving area is a period from when the moving area is extracted until the moving area disappears from the image.

  The human body detection determination will be described below with reference to FIGS. 3 (a) and 3 (b). As a method for tracking a moving area between images, a conventionally known method such as calculating the similarity of moving areas can be used, so detailed description is omitted, and only a method for calculating a moving distance is described. To do. Further, in FIGS. 3A and 3B, the moving regions F are obtained in the nine images arranged in time series order, and here, in order to distinguish the time series, the time series is obtained as necessary. The moving area F is denoted by reference signs F1 to F9 in order from the oldest moving area F. However, in FIG. 3B, the movement area F1 and the movement area F9 are the same, the movement area F2 and the movement area F8, the movement area F3 and the movement area F7, and the movement area F4 and the movement area F6 are the same. Located in position.

  In calculating the movement distance of the moving area F in the human body detection determination, first, a motion vector between adjacent images in time series is calculated for the tracked moving area F. The motion vector can be calculated by calculating a difference in coordinates of the center of gravity position of the moving area F. Next, a total value of the calculated motion vectors is calculated, and this total value is used as the moving distance of the moving area. If the moving distance is equal to or greater than a predetermined distance, it is determined that the moving area is due to a human body. . Here, the predetermined distance used for determining whether or not it is a human body may be set to a suitable value based on the movement distance of the movement area actually obtained.

For example, if the motion vector when moving from the moving area Fn to the moving area Fn + 1 (n = 1 to 8) is Vn = (xn, yn), the moving distance of the moving area F is (x1 ² + y1 ² ) ^{1 / 2} + (x2 ² + y2 ² ) ^1/2 + (x3 ² + y3 ² ) ^1/2 + (x4 ² + y4 ² ) ^1/2 + (x5 ² + y5 ² ) ^1/2 + (x6 ² + y6 ² ) ^{1 / 2} + (x7 ² + y7 ² ) ^1/2 + (x8 ² + y8 ² ) ^1/2

  If the movement distance thus obtained is equal to or greater than a predetermined distance, it is determined that the movement area F is due to a human body, while if it is less than the predetermined distance, it is determined that the movement area F is not due to a human body. .

  In addition to the above method, the movement distance may be evaluated using the total value of the absolute values of the components of the motion vector. In such a case, the X-axis direction component (image) of the movement distance may be used. If the horizontal component) is equal to or greater than a predetermined distance for the X-axis direction and the Y-axis direction component (vertical component of the image) is equal to or greater than the predetermined distance for the Y-axis direction, the moving region F is determined by the human body. Judge that there is. For example, in the motion vectors V1 to V8 described above, the X-axis direction component of the movement distance is | x1 | + | x2 | + | x3 | + | x4 | + | x5 | + | x6 | + | x7 | + | The y-axis direction component is given by | y1 | + | y2 | + | y3 | + | y4 | + | y5 | + | y6 | + | y7 | + | y8 |. In this way, it is possible to reduce the amount of calculation for calculating the movement distance and improve the processing capability.

  That is, in the human body detection determination, when the moving area F is a human body, as shown in FIG. 3A, the movement area F shows a behavior that moves in a predetermined direction, whereas the moving area F is other than a human body such as a plant. In the case of a moving body, as shown in FIG. 3B, paying attention to the behavior of reciprocating movement by wind, the moving distance F is calculated from a plurality of images arranged in time series. If the movement distance is greater than or equal to the predetermined distance, it is determined that the movement area F is due to a human body.

  By the way, the human body detecting unit 12e extracts the moving region F by the moving region extracting unit 12c and then the moving distance and the position of the moving region F until the moving region F disappears from the image (for example, the position of the center of gravity). The movement area information consisting of is stored in the area information storage means 16 including a storage device such as a RAM.

  In addition, if the moving area F represented by the moving area information stored in the area information storage means 16 is not due to a human body, the human body detecting means 12e will be represented by moving area information similar to the moving area information. It is configured to determine that the movement area F to be performed is not a human body.

  Therefore, when performing the human body detection determination, in addition to the human body determination based on the moving distance of the moving area F as described above, moving area information including the position and moving distance of the moving area F is stored in the area information storage unit 16. It is determined whether or not it is similar to the movement area information of the movement area F that is not a human body. As a result of this determination, if the movement area information is similar, it is determined that the movement area F has a movement distance equal to or greater than the predetermined distance and is not due to a human body. Whether the moving area information is similar or not is determined based on how much the position and moving distance of the moving area F to be subjected to the human body detection determination are equal to the position and moving distance of the moving area information stored in the area information storage means 16. Depending on whether they are different.

  For the moving region determined to be due to the human body by the human body detection determination described above, human body detection is performed based on the edge direction value distribution obtained from the region feature amount detection means 12d (third determination). That is, in the third determination, a determination is made as to whether or not the moving area is a human body for the moving area that has not been removed by the first determination and the second determination. In this third determination, the contour (edge) of the human body has more curved portions than the straight portions and has a complicated shape, so the edge directions are distributed in all directions, while the shadows of structures, etc. The human body is detected using the fact that there are many linear components and the distribution in the edge direction tends to be biased.For example, if the edge direction value distribution is evenly distributed, Judge that there is. In order to determine whether or not the moving region represents a human body, the edge direction value distribution may be stored in a table, and the edge direction value distribution table based on the movement of the human body may be compared with each other's distribution. Various other methods can be used.

  The signal processing means 14 is constituted by a CPU or the like, and realizes a function for controlling the operation of each means of the human body detection device 1 by software or the like. The signal processing means 14 is connected to the notification means 3. Has been. The signal processing unit 14 outputs the above-described start signal to the image processing unit 12 when a human body detection signal (described later) of the human body detector 2 is received, and then the human body detection signal is output from the image processing unit 12. Upon receipt, it is configured to output a transmission start signal to the transmission means 15 and output a notification start signal to the notification means 3.

  Further, the signal processing means 14 is configured to output a transmission end signal to the transmission means 15 after a predetermined time has elapsed after receiving the human body detection signal. Further, the signal processing unit 14 is configured to output a notification end signal to the notification unit 2 after a predetermined time has elapsed since the human body detection signal was received. The timing for outputting the transmission end signal and the notification end signal may be set freely by the user.

  The transmission means 15 modulates the NTSC signal output from the output data conversion means 11 into a signal for transmission and outputs it to the intercom base unit B. When the transmission start signal is received from the signal processing means 14, it is transmitted. The transmission is terminated when a transmission end signal is received. Note that the transmission timing of the image data from the transmission unit 15 to the intercom base unit B is synchronized with the imaging timing of the imaging unit 10.

  The human body detector 2 detects a human body in a detection area by a method different from that of the human body detection apparatus 1 and does not cause a decrease in sensitivity even at night, and constitutes an optical system that collects heat rays from the detection area Lens 2a, pyroelectric element 2b for converting the change of the condensed heat ray into an electrical signal, amplification circuit 2c for amplifying the electrical signal, and comparing the level of the amplified signal with a threshold value for the person in the detection region A comparator 2d for detecting stay, and when the human body is detected by a heat ray emitted from the human body, the above-mentioned human body detection signal is output to the signal processing means 14.

  The notification means 3 is for intimidating notification to an intruder, and is a light 3a used for visual intimidation, or an electroacoustic transducer such as a buzzer or speaker used for auditory intimidation. (Not shown) and the like, and the light 3a is turned on and the sound is output from the electroacoustic transducer from when the notification start signal is received from the signal processing means 14 until the notification end signal is received. It is configured as follows.

  The imaging apparatus A is configured as described above. Next, the doorphone master unit B will be described. As shown in FIG. 1, the intercom base unit B includes a monitoring device B <b> 1 that displays an image based on the image data transmitted from the image capturing apparatus A, and a telephone call for performing a call with the intercom unit C. A device B2 is provided.

  The monitoring device B1 includes a transmission means (hereinafter referred to as “parent-side transmission means”) 4, a signal processing means (hereinafter referred to as “parent-side signal processing means”) 5, an image display such as a liquid crystal display (LCD). Means 6, recording means 7, storage means 7 a comprising a storage device such as a RAM, reproduction means 8, and input means 9 comprising a transparent touch panel or the like installed in front of the image display means 6. . The parent-side transmission unit 4 is for communicating with the transmission unit 15 of the imaging apparatus A, and is connected to the transmission unit 15 of the imaging apparatus A by a connection line L.

  The parent-side signal processing means 5 comprises, for example, a CPU or the like, and realizes the function of demodulating the image received by the parent-side transmission means 4 and displaying them sequentially on the image display means 6 by software or the like. The recording unit 7 sequentially records the images transmitted from the imaging device A in the storage unit 7a. The reproduction means 8 displays the image recorded in the storage means 7a on the image display means 6.

  The input means 9 is used for the user to select various functions of the doorphone master unit B. Further, the input unit 9 informs the imaging apparatus A that the moving area F is not due to a human body when the determination is incorrect for the moving area F that is determined by the imaging apparatus A to be due to a human body. It is also used to output a correction signal to be notified to the imaging apparatus A.

  Correspondingly, the master side signal processing means 5 is configured to output the correction signal from the master side transmission means 4 when an input for outputting the correction signal is made by the input means 9. Has been. The correction signal output from the parent-side transmission unit 4 is transmitted to the signal processing unit 14 of the imaging apparatus A through the connection line L and the transmission unit 15.

  Here, the signal processing unit 14 of the imaging apparatus A is configured to output a false detection signal indicating that the determination by the human body detection unit 12e is an error to the image processing unit 12 when the correction signal is received. ing. In addition, the human body detecting means 12e corrects the moving area F determined to be a human body when it receives the false detection signal as not being a human body. Specifically, the human body detecting means 12e is stored in the area information storage means 16. The movement area information is rewritten, and thereafter, the movement area F represented by the movement area information similar to the rewritten movement area information is determined not to be a human body. .

  Accordingly, when the moving area F that is not caused by the human body is determined as a human body in the image pickup apparatus A, the human body detecting unit 12e indicates the error by the input unit 9, so that the human body detecting unit 12e subsequently detects the erroneously detected movement. Since the moving area F having moving area information similar to the moving area information of the area F is not determined to be a human body, it is possible to further suppress erroneous detection of a moving body other than a human body as a human body.

  The call device B2 is for making a call with the doorphone slave unit C, and is a communication unit (not shown) for transmitting and receiving voice data to and from the doorphone slave unit C, and for voice input. Microphone (not shown), a speaker for voice output (not shown), and the like. If the doorphone slave unit C is equipped with a camera, an image captured by the camera of the doorphone slave unit C may be displayed on the image display means 6 when the doorphone slave unit C is operated. In addition, since the conventionally well-known thing can be employ | adopted about the door phone subunit C, description is abbreviate | omitted.

  The imaging apparatus A is configured as described above, and the operation of the imaging apparatus A will be described below. While the image pickup apparatus A is activated, the image pickup means 10 always picks up a predetermined area, and the image obtained by the image pickup means 10 is sent to the image processing means 12 while the output data conversion means 11. And sent to the transmission means 15.

  Here, when a human body is detected by the human body detector 2 and a human body detection signal is transmitted to the signal processing means 14, a start signal is output from the signal processing means 14 to the image processing means 12 and sent to the image processing means 12. As described above, the image is subjected to analysis processing by the image processing unit 12, and when a person is detected, a human body detection signal is output from the image processing unit 12 to the signal processing unit 14.

  The signal processing unit 14 that has received the human body detection signal outputs a transmission start signal to the transmission unit 15 and also outputs a notification start signal to the notification unit 3, and the notification unit 3 provides a threatening notification to the intruder. . This notification is continued until, for example, a notification end signal is received from the signal processing means 14. On the other hand, in the transmission means 15 that has received the transmission start signal, the image data converted from the YUV signal to the NTSC signal by the output data conversion means 11 is modulated for transmission and sequentially transmitted to the doorphone master unit B. This transmission is continued until a transmission end signal is output from the signal processing means 14.

  According to the imaging apparatus A of the present embodiment described above, while the movement region F due to the human body shows relatively a behavior that moves in a predetermined direction as shown in FIG. Paying attention to the fact that the movement region F due to a moving body other than the human body such as a plant swaying in a reciprocating manner as shown in FIG. If the movement distance of the movement area F is calculated from the image and the movement distance is equal to or greater than a predetermined distance, it is determined that the movement area F is a human body, so that a moving body other than the human body is erroneously detected as a human body. It can be suppressed and the reliability of human body detection can be improved. Further, since only the arithmetic processing in the human body detecting means 12e needs to be added, it is not necessary to add a new device or the like, and the cost can be reduced.

  Further, the human body detection unit 12e performs the first determination for determining whether or not the moving area F is a human body based on the size of the moving area F, thereby determining whether or not the human body is also a human body depending on the size of the moving area F. Therefore, it is possible to further suppress erroneous detection of a moving body other than a human body as a human body. In addition, a region feature amount detection unit 12d that extracts a direction value of a moving edge portion in the moving region F based on the moving region F of the moving object detected by the moving region extraction unit 12b and creates an edge direction value distribution thereof. The human body detection means 12e is configured to detect a human body based on the edge direction value distribution obtained from the region feature quantity detection means 12d. The human body edge has a curved portion more complicated than a straight portion. Since the shape is a shape and the edge direction is distributed in all directions, it is determined whether or not the moving region F is a human body. Therefore, a moving body other than the human body is erroneously detected as a human body. It can further be suppressed.

  In addition, the image pickup apparatus A includes a human body detector 2 using infrared rays having the predetermined area as a detection range. When the human body detector 2 detects a human body, each human body detection unit 12e includes a human body detection determination. Since the determination is performed, when the human body is not detected by the human body detector 2, that is, when only the moving region F having no probability of being a human body is obtained, the human body detection means 12e includes the human body detection determination. Since determination is not performed, it is possible to further suppress erroneous detection of a moving body other than a human body as a human body.

  By the way, the moving area F extracted by the moving area extracting unit 12d may be divided into a plurality of parts due to various causes such as disturbance even if the moving area F is originally a single moving body. Therefore, when the moving region group having the distance between the moving regions F equal to or less than a predetermined value in the extracted moving region group exists in the moving region extracting unit 12d, the moving region extracting unit 12d has a rectangular shape with a minimum range including these moving region groups. A function of creating an integrated movement area composed of areas may be provided.

  For example, as shown in FIG. 4 (a), two moving areas F (hereinafter, the upper moving area F in FIG. 4 (a) is indicated by reference numeral F10 as needed and moved downward by the moving area extracting means 12d. If the distance between the moving areas F10 and F11 is equal to or smaller than the predetermined value when the area F is extracted), the rectangular rectangle of the minimum range including the moving area group including the moving areas F10 and F11 is extracted. An integrated movement area G composed of shape areas is created.

  If the movement area F is tracked by using the integrated movement area G in the human body detection means 12e, the movement area F can be tracked even when the movement area F is divided into a plurality of areas. Can improve tracking accuracy.

  By the way, in the next image (next in time series) of the image shown in FIG. 4A, when only the movement area F11 is extracted as shown in FIG. No creation is done. In such a case, the actual movement distance between the movement areas F10 is between the position P1 of the movement area F10 indicated by a broken line in FIG. 4B and the position P2 of the movement area F10 indicated by a solid line in FIG. When the human body detection determination is performed using the integrated moving area G, the moving distance between the moving areas F10 is between the position P3 of the integrated moving area G and the position P2 of the moving area F10 indicated by the solid line. Will be given as a distance. That is, since the center of gravity position differs between the movement area F10 and the integrated movement area G including the movement area F10, when the movement distance between the integration movement area G and the movement area F10 is calculated, There is a risk that the correct travel distance cannot be obtained due to the difference.

  Therefore, it is preferable to use the integrated moving area G when tracking the moving area F, and to use the moving area F when calculating the moving distance. In this way, the tracking accuracy of the moving area F can be improved, It is possible to prevent a correct moving distance from being obtained.

  Note that the method of creating the integrated moving area in the moving area extracting unit 12c is not limited to the above-described one. For example, when a moving area having a moving outline having an end point is detected, a vertically long shape including the moving area having the end point is detected. A moving area having another end point may be searched in the rectangular area, and the moving area having the end point may be combined in the rectangular area to form an integrated moving area.

  Further, an anemometer (not shown) for detecting the wind speed in the predetermined area is provided in the imaging device A, and when the output of the anemometer is equal to or higher than a predetermined value, the human body detection means 12e performs human body detection determination. It may be. In this way, when the output of the anemometer is less than a predetermined value, for example, when there is a low probability that a plant or the like will not be shaken by the wind and erroneously detect the plant or the like as a human body, the human body detection means 12e does not perform human body detection determination. (In other words, only the first determination and the third determination are performed), and the human body detection unit 12e performs the human body detection determination only when the output of the anemometer is equal to or higher than a predetermined value and there is a high probability that a plant or the like is erroneously detected as a human body. The processing speed can be improved.

  By the way, when performing the human body detection determination, if the moving area F has not moved out of the predetermined range between a plurality of images, the predetermined distance is set to a value larger than the maximum moving distance of the moving area. May be. In this way, the moving area F that remains within the predetermined range is less likely to be a moving body such as an intruder or the like, and the predetermined moving distance F is larger than the maximum moving distance of the moving area F. Since the distance is set to a large value and the moving distance is not determined as a human body, it is possible to further suppress erroneous detection of a moving body other than a human body as a human body. Note that the size of the predetermined range may be appropriately set according to the size of the moving area.

  Further, depending on the position of the moving area F on the image, the moving distance value of the moving area F changes from the actual value due to the distortion of the lens of the imaging means 10 or the influence of the peripheral light amount ratio. The value may not be obtained. Therefore, when performing human body detection determination in the human body detection means 12e, the value of the predetermined distance may be changed to a value that takes into account the influence of lens distortion and the like according to the position of the moving region F on the image. Good. In this way, the influence of lens distortion and the like can be corrected, and the reliability can be further improved.

  For example, even when the lens of the imaging means 10 is distorted and the moving body moves the same distance, the distance moved on the image differs between the vicinity of the center of the image and the vicinity of the periphery (the movement distance in the vicinity of the periphery is different). In this case, the predetermined distance value may be reduced as the position of the moving region F on the image moves away from the center of the image in consideration of lens distortion. . Here, in reducing the value of the predetermined distance, only the distance in the horizontal direction (horizontal direction) between the position of the moving region F on the image and the center of the image may be referred to, or the vertical direction ( Only the distance in the (vertical direction) may be referred to. In addition, various methods such as a method of changing the value of the predetermined distance in a quadratic function according to the distance between the moving area F on the image and the center of the image may be appropriately used depending on the situation.

(Embodiment 2)
The imaging apparatus A of the present embodiment is configured such that the human body detection unit 12e gives weight to the moving distance of the moving area F in the moving direction according to the moving direction of the moving area F in the human body detection determination. This is different from the first embodiment. Since other configurations are the same as those in the first embodiment, the description thereof is omitted.

  In the human body detection means 12e in the present embodiment, when performing the human body detection determination, the calculated motion vector of the moving region F is classified into eight directions of Va to Vh in 45 degree increments as shown in FIG. A process of multiplying the weighting coefficients Wa to Wh set for each direction by the magnitude of the motion vector in the direction is performed. In addition, as an example of the setting method of the weighting factor, Vb, Vc, Vd, Vf, Vg, and Vh, which are directions other than the weighting factors Wa and We corresponding to Va and Ve, which are directions in which the plant sways in the wind, are set. There is a method of setting the corresponding weighting factors Wb, Wc, Wd, Wf, Wg, Wh so as to increase.

For example, in the case of the moving region F shown in FIG. 3A, the direction of the motion vectors V1 to V6 is Vb, and the directions of the motion vectors V7 and V8 are Vd, so the moving distance from the moving region F1 to the moving region F9 is , Wb · {(x1 ² + y1 ² ) ^1/2 + (x2 ² + y2 ² ) ^1/2 + (x3 ² + y3 ² ) ^1/2 + (x4 ² + y4 ² ) ^1/2 + (x5 ² + y5 ² ) ^1/2 + (x6 ² + y6 ² ) ^1/2 } + Wd · {(x7 ² + y7 ² ) ^1/2 + (x8 ² + y8 ² ) ^1/2 }

In the case of the moving area F shown in FIG. 3B, the direction of the motion vectors V1 to V4 is Ve, and the direction of the motion vectors V5 to V8 is Va. Therefore, the moving distance from the moving area F1 to the moving area F9 is , We · {(x1 ² + y1 ² ) ^1/2 + (x2 ² + y2 ² ) ^1/2 + (x3 ² + y3 ² ) ^1/2 + (x4 ² + y4 ² ) ^1/2 } + Wa · {(x5 ² + Y5 ² ) ^1/2 + (x6 ² + y6 ² ) ^1/2 + (x7 ² + y7 ² ) ^1/2 + (x8 ² + y8 ² ) ^1/2 }.

  According to the imaging apparatus A of the present embodiment described above, when the moving direction of the human body is likely to be biased, for example, the moving distance in the moving direction that is highly likely to be the moving direction of the human body is given a weight. If the moving distance is made larger than the moving direction, it becomes easy to distinguish a human body from other moving bodies, and it is possible to further suppress erroneous detection of a moving body other than the human body as a human body.

  By the way, in correcting the influence such as the distortion of the lens described above, the weight as in the present embodiment may be used. For example, even when the lens of the imaging means 10 is distorted and the moving body moves the same distance, the distance moved on the image differs between the vicinity of the center of the image and the vicinity of the periphery (the movement distance in the vicinity of the periphery is different). In this case, the weight may be changed as the position of the moving region F on the image moves away from the center of the image in consideration of lens distortion.

(Embodiment 3)
The imaging apparatus A according to the present embodiment is configured in such a manner that when the moving direction of the moving area F continues in the same direction in the human body detection determination, the human body detecting unit 12e gives weight to the moving direction. Different from Form 1. Since other configurations are the same as those in the first embodiment, the description thereof is omitted.

  In the human body detection means 12e in the present embodiment, when performing human body detection determination, the motion vectors of the moving region F are classified into eight directions Va to Vh in the present embodiment as in the second embodiment, and continuously in the same direction. When moving to, a process of multiplying weight coefficients Wa to Wh set for each direction by the magnitude of the motion vector in the direction is performed. Here, the weighting factors Wa to Wh are set to the same values as in the second embodiment.

For example, in the case of the moving region F shown in FIG. 3A, the direction of the motion vectors V1 to V6 is Vb, and the directions of the motion vectors V7 and V8 are Vd, so the moving distance from the moving region F1 to the moving region F9 is , (X1 ² + y1 ² ) ^1/2 + Wb · {(x2 ² + y2 ² ) ^1/2 + (x3 ² + y3 ² ) ^1/2 + (x4 ² + y4 ² ) ^1/2 + (x5 ² + y5 ² ) ^{1 / 2} + (x6 ² + y6 ² ) ^1/2 } + (x7 ² + y7 ² ) ^1/2 + Wd · (x8 ² + y8 ² ) ^1/2

  According to the imaging apparatus A of the present embodiment described above, when the moving direction of the moving region F continues in the same direction, the moving direction is weighted. For example, the moving region F is a human body in order to advance in the same direction. Although it is highly probable, the moving speed is extremely slow, so even if it is a moving area where the moving distance does not exceed the predetermined distance and is not determined as a human body, it can be determined as a human body, so human body detection reliability Can be increased.

(Embodiment 4)
The imaging apparatus A of the present embodiment is different from that of the first embodiment in the calculation method of the movement distance in the human body detection determination performed by the human body detection unit 12e. Since other configurations are the same as those in the first embodiment, the description thereof is omitted.

  When performing human body detection determination, the human body detection unit 12e in the present embodiment calculates motion vectors between adjacent images in time series in the plurality of images for the tracked movement region F, and synthesizes the calculated motion vectors. The magnitude of the vector is used as the movement distance of the tracked movement area.

For example, as shown in FIGS. 3A and 3B, if the motion vector when moving from the movement area Fn to the movement area Fn + 1 (n = 1 to 8) is Vn = (xn, yn), the movement The moving distance of the region F can be represented by {(x1 + x2 + x3 + x4 + x5 + x6 + x7 + x8) ² + (y1 + y2 + y3 + y4 + y5 + y6 + y7 + y8) ² } ^1/2 . That is, the motion vector when moving linearly from the position of the moving area F of the first image in time series in the plurality of images arranged in time series to the position of the moving area F of the last image in time series. The size is the moving distance.

  Therefore, according to the imaging apparatus A of the present embodiment, in addition to the same effects as those of the first embodiment, a moving region F that moves in a predetermined direction as shown in FIG. As shown in 3 (b), it becomes easy to distinguish the moving area F that moves back and forth, and it is possible to further prevent erroneous detection of a moving body other than a human body as a human body, thereby improving the reliability of human body detection. Can be planned.

  In addition to the above method, the movement distance may be evaluated using the total value of each component of the motion vector. In such a case, the X-axis direction component of the movement distance (the horizontal direction of the image) If the component) is equal to or greater than the predetermined distance for the X-axis direction and the Y-axis direction component (the vertical component of the image) is equal to or greater than the predetermined distance for the Y-axis direction, the moving region F is determined to be due to the human body. To do. For example, in the motion vectors V1 to V8 described above, the X-axis direction component of the movement distance is given by x1 + x2 + x3 + x4 + x5 + x6 + x7 + x8, and the Y-axis direction component is given by y1 + y2 + y3 + y4 + y5 + y6 + y7 + y8. In this way, it is possible to reduce the amount of calculation for calculating the movement distance and improve the processing speed.

(Embodiment 5)
The imaging apparatus A according to the present embodiment is different from the first embodiment in the human body detection determination method performed by the human body detection unit 12e. Since other configurations are the same as those in the first embodiment, the description thereof is omitted.

  The human body detection means 12e in the present embodiment tracks the movement area F between a plurality of images arranged in time series order, and the motion vector between adjacent images in the plurality of images in the plurality of images for the tracked movement area F is obtained. And calculating a ratio with respect to the total number of motion vectors for each direction of the calculated motion vector, and performing a human body detection determination that determines that the moving region is a human body if the ratio of the motion vectors in a predetermined direction is equal to or greater than the predetermined ratio. It is configured as follows.

  The human body detection determination in the present embodiment will be described below with reference to FIGS. 3 (a) and 3 (b) and FIGS. 6 (a) and 6 (b). As a method for tracking a moving area between images, a conventionally known method such as calculating the similarity of moving areas can be used. Therefore, detailed description is omitted, and only the method for calculating the ratio is described. To do.

  In calculating the ratio in the human body detection determination, first, a motion vector between adjacent images in time series for the tracked moving region F is calculated. The motion vector can be calculated by calculating a difference in coordinates of the center of gravity position of the moving area F.

  After calculating the motion vectors, the motion vectors are classified into eight directions Va to Vh shown in FIG. 5 as in the second embodiment, and the ratio to the total number of motion vectors is calculated for each of the directions Va to Vh. For example, in the example shown in FIG. 3A, the total number of motion vectors is 8, whereas Va: Vb: Vc: Vd: Ve: Vf: Vg: Vh = 0: 6: 0: 2: 0 : 0: 0: 0, Vb is 75%, Vd is 25%, Va, Vc, Ve, Vf, Vg, and Vh are 0%, and the bar graph is shown in FIG. 6 (a). A graph like this is obtained.

  On the other hand, in the example shown in FIG. 3B, the total number of motion vectors is 8, whereas Va: Vb: Vc: Vd: Ve: Vf: Vg: Vh = 4: 0: 0: 0: 4: Since 0: 0: 0, Va and Ve are 50%, Vb, Vc, Vd, Vf, Vg, and Vh are 0%, and a graph as shown in FIG. can get.

  Using the ratio for each direction with respect to the total number of motion vectors obtained in this way, it is determined whether or not the moving area F is a human body. In this embodiment, the ratio of motion vectors in a predetermined direction is predetermined. If it is equal to or greater than the ratio, it is determined that the moving area F is caused by a human body. For example, as the predetermined direction, Vb, Vc, Vd, which has a high probability of moving a human body (particularly an intruder), is used, and the ratio of any of Vb, Vc, Vd is a predetermined ratio (for example, 70%) or more. If there is, it is determined that the moving area F is due to a human body. In the example shown in FIG. 3A and FIG. 6A, since Vb is 75%, it is determined that the above condition is satisfied and the moving region F is due to the human body, and FIG. In the example shown in FIG. 6B, since Vb, Vc, and Vd are all 0%, the above condition is not satisfied, and it is not determined that the moving region F is due to a human body.

  According to the imaging apparatus A of the present embodiment described above, while the movement region F by the human body often exhibits a behavior that moves in a predetermined direction, movement other than the human body such as a plant swaying in the wind. Focusing on the fact that the movement region F by the body often exhibits a behavior such as reciprocating movement, a motion vector between images adjacent in time series in a plurality of images arranged in time series is calculated, For each motion vector direction, the ratio to the total number of motion vectors is calculated. If the ratio of motion vectors in a predetermined direction is equal to or greater than the predetermined ratio, the moving region F is determined to be a human body. It is possible to suppress erroneous detection as a human body and improve the reliability of human body detection. Further, since only the arithmetic processing in the human body detecting means 12e needs to be added, it is not necessary to add a new device or the like, and the cost can be reduced.

  In this embodiment, if the ratio of the motion vector in the predetermined direction is equal to or greater than the predetermined ratio, it is determined that the moving area is due to the human body, but the moving direction of the plant swaying in the wind is specified. In consideration of the possibility that the human body may move in all directions, while it is likely to be biased in the direction of Good.

  By the way, the human body detection determination method described in the present embodiment may be performed in each of the first to fourth embodiments. When the human body detection unit 12e performs the human body detection determination, the moving distance is equal to or greater than a predetermined value. In addition, if the ratio of motion vectors in a predetermined direction or the ratio of motion vectors in all directions is equal to or greater than a predetermined ratio, it may be determined that the moving area F is due to a human body.

  In this way, in performing the human body detection determination, not only the moving distance of the moving area F but also the direction of the motion vector of the moving area F is taken into account, so that a moving body other than the human body is erroneously detected as a human body. Can be further suppressed, and the reliability of human body detection can be further improved.

It is explanatory drawing of the door phone system containing the imaging device of Embodiment 1. FIG. It is a schematic explanatory drawing which shows the installation condition of an imaging device same as the above. It is explanatory drawing of the human body detection determination in an imaging device same as the above. It is operation | movement explanatory drawing in an imaging device same as the above. 10 is an explanatory diagram of human body detection determination in the imaging apparatus of Embodiment 2. FIG. FIG. 10 is an explanatory diagram of human body detection determination in the imaging apparatus according to the fifth embodiment.

Explanation of symbols

A imaging device B door phone master unit 2 human body detector 10 imaging means 12a contour extracting means 12b moving contour extracting means 12c moving area extracting means 12d area feature quantity detecting means 12e human body detecting means 15 transmitting means

Claims (12)

An imaging device connected to a door phone master unit for a door phone system that enables a telephone call between a house and an outside, an imaging unit that images a predetermined area, and a contour extraction unit that extracts a contour from an image captured by the imaging unit A moving contour detecting unit that extracts a contour of the moving object from the contour extracted by the contour extracting unit; and a moving region that detects a moving region including a rectangular region circumscribing the contour of the moving object extracted by the moving contour extracting unit. An extraction means, a human body detection means for detecting a human body based on the moving area, and a transmission means for transmitting an image captured by the imaging means to the door phone master unit,
The human body detection means tracks a moving area between a plurality of images arranged in time series order, calculates a motion vector between adjacent images in time series in the plurality of images for the tracked moving area, and calculates the calculated motion vector A human body detection determination that calculates a ratio to the total number of motion vectors for each direction and determines that the moving region is due to a human body if the ratio of motion vectors in a predetermined direction or the ratio of motion vectors in all directions is equal to or greater than a predetermined ratio An image pickup apparatus configured to perform the above. An imaging device connected to a door phone master unit for a door phone system that enables a telephone call between a house and an outside, an imaging unit that images a predetermined area, and a contour extraction unit that extracts a contour from an image captured by the imaging unit A moving contour detecting unit that extracts a contour of the moving object from the contour extracted by the contour extracting unit; and a moving region that detects a moving region including a rectangular region circumscribing the contour of the moving object extracted by the moving contour extracting unit. An extraction means, a human body detection means for detecting a human body based on the moving area, and a transmission means for transmitting an image captured by the imaging means to the door phone master unit,
The human body detecting means is configured to detect a motion vector when moving linearly from the position of the moving area of the first image in time series to the position of the moving area of the last image in time series in a plurality of images arranged in time series. The size is calculated as the moving distance of the moving region to be tracked , and the motion vector between the images adjacent in time series in the plurality of images is calculated for the tracked moving region , and the motion is calculated for each direction of the calculated motion vector. If the moving distance is equal to or greater than a predetermined value and the ratio of motion vectors in a predetermined direction or the ratio of motion vectors in all directions is equal to or greater than a predetermined ratio, the movement area is determined to be a human body. An imaging apparatus configured to perform human body detection determination. An imaging device connected to a door phone master unit for a door phone system that enables a telephone call between a house and an outside, an imaging unit that images a predetermined area, and a contour extraction unit that extracts a contour from an image captured by the imaging unit A moving contour detecting unit that extracts a contour of the moving object from the contour extracted by the contour extracting unit; and a moving region that detects a moving region including a rectangular region circumscribing the contour of the moving object extracted by the moving contour extracting unit. An extraction means, a human body detection means for detecting a human body based on the moving area, and a transmission means for transmitting an image captured by the imaging means to the door phone master unit,
The moving area extracting means is an integrated unit composed of a rectangular area having a minimum range that includes the moving area group when the moving area group having a distance between the moving areas of a predetermined value or less exists in the extracted moving area group. Configured to create a moving area,
The human body detecting means is configured to detect a motion vector when moving linearly from the position of the moving area of the first image in time series to the position of the moving area of the last image in time series in a plurality of images arranged in time series. The size is calculated as the moving distance of the moving area to be tracked. If the moving distance is equal to or greater than the predetermined distance, human body detection determination is performed to determine that the moving area is due to a human body, and integrated movement is performed when tracking the moving area. using an area, features and to that imaging device that is configured to use a moving region when calculating the moving distance. An imaging device connected to a door phone master unit for a door phone system that enables a telephone call between a house and an outside, an imaging unit that images a predetermined area, and a contour extraction unit that extracts a contour from an image captured by the imaging unit A moving contour detecting unit that extracts a contour of the moving object from the contour extracted by the contour extracting unit; and a moving region that detects a moving region including a rectangular region circumscribing the contour of the moving object extracted by the moving contour extracting unit. An extraction means, a human body detection means for detecting a human body based on the moving area, and a transmission means for transmitting an image captured by the imaging means to the door phone master unit,
The human body detecting means is configured to detect a motion vector when moving linearly from the position of the moving area of the first image in time series to the position of the moving area of the last image in time series in a plurality of images arranged in time series. The size is calculated as the movement distance of the moving area to be tracked, and is configured to perform human body detection determination that determines that the moving area is due to a human body if the moving distance is equal to or greater than a predetermined distance. features and to that imaging device to be provided with a weight to the movement distance of the moving area in the moving direction depending on the direction of movement. An imaging device connected to a door phone master unit for a door phone system that enables a telephone call between a house and an outside, an imaging unit that images a predetermined area, and a contour extraction unit that extracts a contour from an image captured by the imaging unit A moving contour detecting unit that extracts a contour of the moving object from the contour extracted by the contour extracting unit; and a moving region that detects a moving region including a rectangular region circumscribing the contour of the moving object extracted by the moving contour extracting unit. An extraction means, a human body detection means for detecting a human body based on the moving area, and a transmission means for transmitting an image captured by the imaging means to the door phone master unit,
The human body detecting means is configured to detect a motion vector when moving linearly from the position of the moving area of the first image in time series to the position of the moving area of the last image in time series in a plurality of images arranged in time series. The size is calculated as the movement distance of the moving area to be tracked, and is configured to perform human body detection determination that determines that the moving area is due to a human body if the moving distance is equal to or greater than a predetermined distance. when the movement direction is continuously in the same direction, it characterized imaging device to be provided with a weight to the movement direction. An imaging device connected to a door phone master unit for a door phone system that enables a telephone call between a house and an outside, an imaging unit that images a predetermined area, and a contour extraction unit that extracts a contour from an image captured by the imaging unit A moving contour detecting unit that extracts a contour of the moving object from the contour extracted by the contour extracting unit; and a moving region that detects a moving region including a rectangular region circumscribing the contour of the moving object extracted by the moving contour extracting unit. An extraction means; a human body detection means for detecting a human body based on a moving area; a transmission means for transmitting an image captured by the imaging means to the intercom base unit; and an anemometer for detecting the wind speed in the predetermined area;
When the output of the anemometer is equal to or greater than a predetermined value , the human body detecting means detects the moving area of the last image in time series from the position of the moving area of the first image in time series in a plurality of images arranged in time series. The human body detection that calculates the size of the motion vector when moving linearly to the position of as a moving distance of the moving area to be tracked and determines that the moving area is due to a human body if the moving distance is equal to or greater than a predetermined distance it characterized in that it is configured to perform determination imaging device. An imaging device connected to a door phone master unit for a door phone system that enables a telephone call between a house and an outside, an imaging unit that images a predetermined area, and a contour extraction unit that extracts a contour from an image captured by the imaging unit A moving contour detecting unit that extracts a contour of the moving object from the contour extracted by the contour extracting unit; and a moving region that detects a moving region including a rectangular region circumscribing the contour of the moving object extracted by the moving contour extracting unit. An extraction means, a human body detection means for detecting a human body based on the moving area, and a transmission means for transmitting an image captured by the imaging means to the door phone master unit,
The human body detecting means is configured to detect a motion vector when moving linearly from the position of the moving area of the first image in time series to the position of the moving area of the last image in time series in a plurality of images arranged in time series. The size is calculated as a moving distance of the moving area to be tracked, and is configured to perform human body detection determination that determines that the moving area is caused by a human body if the moving distance is a predetermined distance or more. If the movement area is not moved out of the predetermined range in between images, the predetermined distance up to the moving distance settings that said imaging device to a larger value of the moving region. An imaging device connected to a door phone master unit for a door phone system that enables a telephone call between a house and an outside, an imaging unit that images a predetermined area, and a contour extraction unit that extracts a contour from an image captured by the imaging unit A moving contour detecting unit that extracts a contour of the moving object from the contour extracted by the contour extracting unit; and a moving region that detects a moving region including a rectangular region circumscribing the contour of the moving object extracted by the moving contour extracting unit. Extraction means, human body detection means for detecting a human body based on the movement area, transmission means for transmitting an image captured by the imaging means to the intercom base unit, and the movement area after the movement area is extracted by the movement area extraction means Area information storage means for storing the position of the moving area and moving area information having the moving distance until the image disappears from the image,
The human body detecting means is configured to detect a motion vector when moving linearly from the position of the moving area of the first image in time series to the position of the moving area of the last image in time series in a plurality of images arranged in time series. The size is calculated as the moving distance of the moving area to be tracked. If the moving distance is equal to or greater than the predetermined distance, human body detection determination is performed to determine that the moving area is due to a human body, and the movement stored in the area information storage unit If the moving area represented by the area information is not a human body, the moving area represented by the moving area information similar to the moving area information is determined not to be a human body. It shall be the imaging device. The imaging apparatus according to claim 2, wherein the human body detection unit is configured to change the value of the predetermined distance according to a position of a moving region on the image. The human body detection means is configured to determine whether or not the moving area is based on a human body based on the size of the moving area . Imaging device. Based on the moving area of the moving object detected by the moving area extracting means, the area feature quantity detecting means for extracting the direction value of the moving edge portion in the moving area and creating the edge direction value distribution, the human body detecting means, The imaging apparatus according to claim 1, wherein the imaging apparatus is configured to detect a human body based on an edge direction value distribution obtained from a region feature amount detection unit . A human body detector using infrared rays having the predetermined area as a detection range is provided, and the human body detection unit is configured to perform the human body detection determination when the human body is detected by the human body detector. imaging equipment of any one of claims 1 to 11 to.

Images