Abstract: A passenger counter that counts the number of persons who get on/off a vehicle comprising an imaging unit 2 installed at an inside of a vehicle platform; a setting unit 31 configured to set an inner area I corresponding to a passage inside the vehicle, one outer areas B surrounding the inner area I and inside the vehicle and other outer area A surrounding the inner area I and outside the vehicle; and a count determination unit 35 configured to count the number of persons who move from one outer area A(B) to the other outer area B(A) through the inner area I while a door of the platform is opened, not to count the number of persons while the door is closed, and to perform processing of determining a person existing in the inner area I when the opened (closed) door is closed (opened) to be counted.

Abstract: The present invention relates to a moving-object height-determining apparatus which tracks and monitors a moving-object, such as a human, from a two-dimensional image captured from above by single image-capturing means to calculate a relative height of two moving objects existing relatively close to each other.

Abstract: The present invention realizes a moving-object height determining apparatus capable of easily and favorably determining a height of a moving-object using a single image-capturing device. In a two-dimensional image G captured by one camera 1, a height calculation unit 24 carries out the following processing. The height calculation unit 24 regards one of representative points P1 and P2 as a standard point A having a standard height, and regards the other representative point as an assumption point B having a virtual height. The height calculation unit 24 corrects the standard point A to a comparative point a corresponding to the virtual height along a vertical axis T of a moving-object M1. The height calculation unit 24 obtains a fluctuation amount q of a distance d between two points in a real space between the comparative point a and the assumption point B during a period of a plurality of clocks.

Abstract: The object of the present invention is to quickly and easily recognize the position, quantity, and kind of the object, which takes unspecified forms according to the angle in which the object is positioned. Points are arranged at regular intervals on an image. For each respective point, a fundamental wave Fourier transformation is calculated on the respective pixel values on the circumference of a circle whose center is at the point. The phase obtained by the fundamental wave Fourier transformation is a normal vector of the point. From the normal vector groups of every point arranged at regular intervals the object is recognized.

Abstract: A method for identifying the position, quantity, kind, etc. of an object. A Standard Object image is positioned on a picture so as to be around an arbitrary point (Arrangement Point), normal vector group is determined along the outline of the Standard Object image based upon the density difference in the background and the Standard Object, and an angle information and a position information are determined from the Arrangement Point to the normal vector group, so that such information are stored as standard data for the arrangement point. On the other hand, normal vector group is determined on the outline of an object image, which is to be recognized, based upon the density difference in the background and the object image so that, based on the standard data, a plurality of Answer points are determined. Lastly, a focus point region formed by the Answer points is evaluated.

Abstract: A method for identifying an object image shown in a picture using density differences between an object image and a background. A screen taken by a camera is first divided into blocks; for each block, a Standard Object image is positioned based upon an arbitrary point on each picture; from the density differences in the picture, a normal vector of the outline portion of the Standard Object image is determined; then related vector data, that includes a position information up to a normal vector group and an angle information, is determined; the related vector data is stored as standard data in a block from which the normal vector is detected; a normal vector for a picture that shows an object image to be recognized is determined; from the normal vector, Answer points are determined based on standard data of the Standard Object image; and a focus point region comprised of Answer points is evaluated.

Abstract: A method for identifying an object image shown in a picture using density differences between an object image and a background. A screen taken by a camera is first divided into blocks; for each block, a Standard Object image is positioned based upon an arbitrary point on each picture; from the density differences in the picture, a normal vector of the outline portion of the Standard Object image is determined; then related vector data, that includes a position information up to a normal vector group and an angle information, is determined; the related vector data is stored as standard data in a block from which the normal vector is detected; a normal vector for a picture that shows an object image to be recognized is determined; from the normal vector, Answer points are determined based on standard data of the Standard Object image; and a focus point region comprised of Answer points is evaluated.

Abstract: A method for identifying the position, quantity, kind, etc. of an object. A Standard Object image is positioned on a picture so as to be around an arbitrary point (Arrangement Point), normal vector group is determined along the outline of the Standard Object image based upon the density difference in the background and the Standard Object, and an angle information and a position information are determined from the Arrangement Point to the normal vector group, so that such information are stored as standard data for the arrangement point. On the other hand, normal vector group is determined on the outline of an object image, which is to be recognized, based upon the density difference in the background and the object image so that, based on the standard data, a plurality of Answer points are determined. Lastly, a focus point region formed by the Answer points is evaluated.

Abstract: The object of the present invention is to quickly and easily recognize the position, quantity, and kind of the object, which takes unspecified forms according to the angle in which the object is positioned. Points are arranged at regular intervals on an image. For each respective point, a fundamental wave Fourier transformation is calculated on the respective pixel values on the circumference of a circle whose center is at the point. The phase obtained by the fundamental wave Fourier transformation is a normal vector of the point. From the normal vector groups of every point arranged at regular intervals the object is recognized.

Abstract: A moving body detection method and apparatus which detects moving bodies by processing image data for said moving bodies, including a process in which spatial phases, which are obtained by the operational formula tan−1 (AS/AC) or cot−1 (AC/AS) (where AC is a Fourier cosine transformation and AS is a Fourier sine transformation) in a case where image signals obtained as aggregates of picture elements on the basis of picture element data constituting the image data are subjected to a spatial Fourier transformation in a direction which is not perpendicular to a direction of movement of the moving bodies, are calculated in terms of a time series; and then the moving bodies are detected on the basis of changes occurring in the calculated spatial phases.

Abstract: A device for measuring mean staying time of persons inside a building by processing signals from an entry/exit detector that outputs entry and exit signals when persons enter into and exit from the building. The device includes a staying measurer for determining the number of persons staying inside the building by subtracting the number of exit signals from the number of entry signals, an entry or exit measurer for determining the number of persons who have entered into or exited from the building by counting the entry or exit signals per predetermined period of time, and a calculating section for calculating the mean staying time of persons in the building during such a time period by dividing the number of persons staying inside at the time the unit time has expired by the number of persons who have exited.