Abstract: An object detection system, comprising an unit for calculating relationship information between a position on an image of an object existing on a road surface and a size of an image picked up by one camera, using an actual size of a target object and camera parameter, a unit for evaluating an existence possibility of a symmetry axis in a specific pixel incase of an interval determined on the basis of geometric information, a unit for evaluating density and continuity in the vicinity of the center axis of a rectangular area of a pixel whose symmetry value is equal to or more than a specific threshold and detecting the lowest end point of the symmetric object and a unit for outputting a position and size of a candidate area of the symmetric object on the basis of the lowest end point.

Abstract: A recording medium, a parking support apparatus and a parking support screen for displaying an image allow the driver of a vehicle to easily grasp the situation while maneuvering the vehicle for parking.

Abstract: A recording medium, a parking support apparatus and a parking support screen for displaying an image allow the driver of a vehicle to easily grasp the situation while maneuvering the vehicle for parking.

Abstract: A character recognition method is provided, in which the method includes the steps of: picking up images in a motion picture by changing brightness for each image; extracting a character area from each image; recognizing at least one character in the character area by performing a matching process between the character area and dictionary images for each image, and determining a character recognition result for each image; and selecting a final character recognition result of which the matching degree is the highest from the character recognition results of the images. Accordingly, even when a character is too dark to recognize due to shadows in the daytime or a character is too bright to recognize due to irradiation in the nighttime, the character can be recognized by using images having differing brightness.

Abstract: There is provided an image control apparatus which incorporates an automatic configuration mechanism for setting parameters used in event detection, to thereby perform efficient event detection, and improve quality and reliability of image monitoring control. An encoding section encodes an image from a monitoring camera. A reduced image generation section performs simplified decoding of an encoded image to generate a reduced image. A feature amount extraction section detects an image event from the reduced image and extracts feature amounts therefrom. A screen display control section performs screen display control such that a listing of static images of the reduced image is displayed on a display, and a detection event can be set which is an event to be detected. A detection dictionary-preparing section measures variance values from the feature amounts of the detection event to thereby prepare a detection dictionary containing detection parameters which are feature amounts having small variance values.

Abstract: A monitoring system using an imaging device like a TV camera, etc. enhances a monitoring accuracy without involving manual operations and increasing costs for installing the monitoring system. Two lengths of linear components parallel to each other are extracted from data of an image taken by the imaging device. A rotational angle and an elevation angle of the imaging device are calculated from a positional relationship between those two lengths of linear components and a view point of the imaging device. Obtained is a ratio of a line-to-line distance between the two lengths of linear components when transforming coordinates of the two lengths of linear components on an image plane into coordinates on an imaginary plane to a line-to-line distance between the two lengths of linear components in a real space. A height of position from the plane for installing the imaging device is obtained from this ratio.

Abstract: A traffic monitoring apparatus that is used to reliably detect the occurrence of an abnormal situation, such as a traffic accident. An imaging device produces and outputs images of a point to be monitored at predetermined intervals. Image inputting unit of the traffic monitoring apparatus inputs images output from the imaging device. Move vector extracting unit first generates a background image from a plurality of images input, then specifies areas where a moving object exists by calculating the difference between the background image and a newly input image, and then extracts move vectors from the specified areas. Parameter calculating unit calculates the slope and intercept, being parameters, of a move vector by considering the move vector as a segment. Plotting unit plots parameters for each move vector in a two-dimensional coordinate system with slope and intercept as its bases.

Abstract: A method for measuring the speed of a vehicle which enables measurement of the speed of a vehicle with a high accuracy by an image pickup camera mounted to a single simple supporting pole installed at the side of a field, including capturing a vehicle in motion by an image pickup unit mounted on a support provided at the side of a field, calculating an amount of movement in the vertical direction by an image of the vehicle captured by the image pickup unit on a display screen displaying the image, calculating an amount of movement in the horizontal direction by the image of the vehicle captured by the image pickup unit on the display screen displaying the image, converting the calculated amount of vertical movement and amount of horizontal movement based on information of the capture location of the image pickup unit in the real space of the vehicle and information of the attitude of the image pickup camera to an amount of vertical movement and amount of horizontal movement in that real space, and computing t

Abstract: A character recognition method is provided, in which the method includes the steps of: picking up images in a motion picture by changing brightness for each image; extracting a character area from each image; recognizing at least one character in the character area by performing a matching process between the character area and dictionary images for each image, and determining a character recognition result for each image; and selecting a final character recognition result of which the matching degree is the highest from the character recognition results of the images. Accordingly, even when a character is too dark to recognize due to shadows in the daytime or a character is too bright to recognize due to irradiation in the nighttime, the character can be recognized by using images having differing brightness.

Abstract: A first camera 12 having a fish-eye lens 13 and a second camera 14 having a fish-eye lens 15 are disposed with the respective fish-eye lenses faced with each other. An image pick-up range of the first camera 12 and an image pick-up range of the second camera 14 are partially overlapped, and only a relatively narrow area at the backside of each camera becomes a blind area. A processor 30 sets a frame F in the image pick-up area of the first camera 12 and the image pick-up area of the second camera 14 respectively corresponding to a set monitoring range. The image data within these frames F are taken out and distortions of the image due to the characteristics of the fish-eye lenses 13 and 15 are eliminated to obtain first and second transformed frame data. These transformed frame data are combined by an image combining unit 25, to obtain image data corresponding the monitoring range free from any gap. The combined image data is displayed in a monitor 8 through a PC 7.

Abstract: There is provided an image control apparatus which incorporates an automatic configuration mechanism for setting parameters used in event detection, to thereby perform efficient event detection, and improve quality and reliability of image monitoring control. An encoding section encodes an image from a monitoring camera. A reduced image generation section performs simplified decoding of an encoded image to generate a reduced image. A feature amount extraction section detects an image event from the reduced image and extracts feature amounts therefrom. A screen display control section performs screen display control such that a listing of static images of the reduced image is displayed on a display, and a detection event can be set which is an event to be detected. A detection dictionary-preparing section measures variance values from the feature amounts of the detection event to thereby prepare a detection dictionary containing detection parameters which are feature amounts having small variance values.

Abstract: A first camera 12 having a fish-eye lens 13 and a second camera 14 having a fish-eye lens 15 are disposed with the respective fish-eye lenses faced with each other. An image pick-up range of the first camera 12 and an image pick-up range of the second camera 14 are partially overlapped, and only a relatively narrow area at the backside of each camera becomes a blind area. A processor 30 sets a frame F in the image pick-up area of the first camera 12 and the image pick-up area of the second camera 14 respectively corresponding to a set monitoring range. The image data within these frames F are taken out and distortions of the image due to the characteristics of the fish-eye lenses 13 and 15 are eliminated to obtain first and second transformed frame data. These transformed frame data are combined by an image combining unit 25, to obtain image data corresponding the monitoring range free from any gap. The combined image data is displayed in a monitor 8 through a PC 7.

Abstract: A display control system for a videoconference terminal capable of displaying proper images of participants. A video camera captures wide-angle source pictures including the images of participants. The source pictures are sent to a participant position detector and image clipping unit. The participant position detector detects a participant position by examining the source pictures. Depending on the on-screen movement observed in the participant position detected by the participant position detector, the image clipping unit determines an appropriate clipping window. It clips the desired image out of the source pictures as defined by the clipping window. A screen adjustment unit adjusts the image size so that it will fit to the actual screen size.

Abstract: An automatic monitoring apparatus for automatically detecting an object to be detected, such as a suspicious person, based on the picture obtained from an image pickup device. Moving object detecting unit detects information about a moving object in the picture, based on the picture signal input from the image pickup device. Characteristic quantity calculating unit calculates a characteristic quantity of the moving object based on the information detected by the moving object detecting unit. Characteristic quantity storing unit stores at least a characteristic quantity relating to a non-detection object that should not be detected. Determining unit compares the characteristic quantity of the moving object, calculated by the characteristic quantity calculating unit, with the characteristic quantity stored in the characteristic quantity storing unit, to determine whether or not the moving object is an object to be detected.

Abstract: An image processing apparatus with interframe interpolation capabilities for reproducing a sequence of video frames by performing a frame interpolation between two given video frame images to compensate for dropped frames. The image processing system comprises an outline detection unit to detect the outline of each moving object contained in a frame image and an affine parameter calculation unit to calculate first affine parameters based on the geometrical relationship between one outline image at a first point in time and another outline image at a second point in time. Based on the first affine parameters, an affine parameter interpolation unit performs a linear interpolation to produce second affine parameters corresponding to a third point in time between the first and second points in time.

Abstract: A character recognition apparatus for detecting a character which is represented by an image data, by extracting a characteristic quantity of the character from the image data of the character, and comparing the characteristic quantity with characteristic quantities of characters which are memorized in a dictionary. Before the above comparison, a modification of the above characteristic quantity which is extracted from the image data is carried out, where the modification corresponds to a magnification or reduction of the scale of the above image data to equalize the scale of of the above image data of the character with the scales of the characters of which the characteristic quantities are memorized in the above dictionary. Further, a magnification or reduction of the width of the character image to equalize the width of of the character image with the width of the characters of which the characteristic quantities are memorized in the above dictionary.

Abstract: A character recognition apparatus for detecting a character which is represented by an image data, by extracting a characteristic quantity of the character from the image data of the character, and comparing the characteristic quantity with characteristic quantities of characters which are memorized in a dictionary. Before the above comparison, a modification of the above characteristic quantity which is extracted from the image data is carried out, where the modification corresponds to a magnification or reduction of the scale of the above image data to equalize the scale of the above image data of the character with the scales of the characters of which the characteristic quantities are memorized in the above dictionary. Further, a magnification or reduction of the width of the character image to equalize the width of the character image with the width of the characters of which the characteristic quantities are memorized in the above dictionary.