Abstract: A vehicle includes a first actuating system having an automatic steering actuator to bring the front wheel steer angle to a calculated target front wheel steer angle for lane keeping, and a second actuating system such as a front and rear roll stiffness distribution control system, a front and rear driving force distribution control system, a rear wheel steering system, and a differential limiting force control system. By controlling the second actuating system in accordance with the automatic steering operation, a control unit adjusts the steering characteristic of the vehicle in a direction to improve the yawing response or in a direction to improve the running stability.

Abstract: An unmanned vehicle running system, capable of reducing a stop time of a vehicle by immediately judging whether or not an obstacle blocks the passage when detecting the obstacle. For this purpose, the unmanned vehicle running system has a plurality of vehicles (1) running without a driver in a predetermined course (3) while detecting the current position and a central monitor station (2) for monitoring operations of the plurality of vehicles, wherein each of said vehicles is provided with a phototaking device (24) for taking a photo of the course, with a vehicle communication unit (23) for transmitting the taken image to the central monitor station, and with an obstacle detecting unit (5) for detecting an obstacle (4) which blocks the passage, wherein the central monitor station is provided with a central communication unit (8) for receiving the image and with a monitor (9) for displaying the image, and wherein the phototaking device takes a photo when the obstacle detecting unit detects an obstacle.

Abstract: The video-assisted remote control device disclosed comprises a remote control station and a station on board the machine to be remote controlled. The latter comprises a real-time mixing unit, a video and audio transmitter and a remote control receiver. The control station comprises several monitors, a video and audio receiver and a remote control transmitter. Application to the remote control of public works machines.

Abstract: A plurality of cameras respectively input an image from different camera positions. The plurality of cameras is on a moving object. An image memory stores a plurality of images input by the plurality of cameras. An image transformation unit transforms one image input by a first camera using each of a plurality of transformation parameters each representing a geometrical relationship among a predetermined plane, the first camera, and a second camera, and generates a plurality of transformed images from a view position of the second camera. A matching processing unit compares each of the plurality of transformed images with another image input by the second camera for each area consisting of pixels, and calculates a coincidence degree of each area between each transformed image and another image. An obstacle detection unit detects an obstacle area consisting of areas each having a coincidence degree below a threshold from another image.

Abstract: An object recognition apparatus that can recognize an object in an image acquired by an on-vehicle camera mounted on a vehicle with high efficiency and accuracy. A recognition processing is carried out in a cut off range, which is cut off from the image, and in which an object to be recognized is supposed to be present. The cut off range is obtained using support information supplied from a position detection device and/or an anti-lock brake device of the vehicle. Since the object in the image changes its position as the vehicle moves, the displacement must be estimated during the object recognition. The estimation requires camera attitude parameters of the on-vehicle camera with respect to the road, and the estimation is performed using support information supplied from the position detection device and/of the anti-lock brake device. This will improve the efficiency and accuracy of obtaining the camera attitude parameters.

Abstract: An image processing apparatus for extracting a floor region and an obstacle region from an image formed by pixels taken by a camera, includes an image dividing unit to divide the image into a plurality of regions; an arithmetic unit to calculate the absolute value of the difference between the density of each pixel of each region and a set density and to accumulate the absolute value for each region; a floor/obstacle judging portion to judge whether a target region is a floor region or an obstacle region on the basis of the result of comparison between a set value and the accumulated value of the absolute values for all the pixels within the target region or the average value of the accumulated value obtained by dividing the accumulated value by the number of pixels; and a storage portion to store the result of the floor/obstacle judging portion.

Abstract: An image sensor attached to an aircraft generates an image. The image includes a runway and other objects. The edges within the image are detected and Nav Data is used to predict the coordinates defining the runway. The predicted coordinates and the detected edges are correlated to determine the location of the runway within the image. The location of the runway within the image is then used to determine the lateral and vertical deviation of the aircraft relative to the runway.

Abstract: An automatic travel controlling device capable of reliably guiding a vehicle along a lane even if the white lane lines cannot be detected. A laser radar device for detecting the distance to a side wall of the lane is provided to the left and right in addition to a CCD camera for detecting the white lane lines. An image from the CCD camera is supplied to a image processor ECU, and an extracted white line is supplied to a vehicle controlling ECU. A vehicle controlling ECU drives a steering actuator to perform steering control based on two white lines of the lane when detected. However, when the white lines cannot be detected, steering control based on the distances to the side walls is performed. If an obstacle is detected ahead by the laser radar device, the vehicle position is detected based on the distances to the side walls and a lane change is performed to evade the obstacle.

Abstract: A synchronized target subsystem for use in an automated docking or station keeping system for docking a chase vehicle with a target vehicle wherein the chase vehicle is provided with a video camera which provides adjacent frames each having a predetermined time duration. A light source mounted on the target vehicle flashes at a frequency which has a time duration which is a multiple of the duration time of the frames, the light being on for at least one frame duration and being off for the remainder of the cycle. An image processing unit is connected to the camera for receiving signals from the camera and subtracting one of the adjacent frames from the other to detect whether the light appears in one frame, both frames or neither frame. If the target light appears in both frames or neither frame, the image processing unit feeds a signal to a timing circuit to advance the video camera one frame.

Abstract: The driverless vehicle system and method of control therefor includes a fixed camera fixedly mounted to a vehicle and a movable camera movably mounted to the vehicle. A control unit selectively inputs an image from one of the fixed camera and the movable camera, determines a trace angle based on the input image, and controls a steering angle of the vehicle based on the trace angle. The control unit also compares the trace angle to a first reference angle when the control unit inputs images from the fixed camera, and if the trace angle is greater than the first reference angle, the control means generates a desired angular position for the movable camera. A camera moving mechanism moves the movable camera to the desired angular position. Thereafter, the control means selects the movable camera from which to input images.

Abstract: A road lane recognizing apparatus can accurately recognize a road lane position from an image shown by an actual road surface image signal obtained by picturing a road surface in front of a vehicle by means of picturing means such as a television camera or the like mounted on the vehicle. Whether the vehicle exists on a straight part of road or not is discriminated in accordance with a vehicle-self position detected by vehicle detecting means. When the vehicle exists on the straight part, an attitude angle showing the direction of the vehicle for the road direction at the vehicle-self position is detected. When the attitude angle is detected, a predetermined ideal road surface image is inclined by only the attitude angle, thereby obtaining the corrected road surface image. The actual road surface image signal from the picturing means is compared with a signal of the corrected road surface image. An image difference is used as an offset amount.

Abstract: The invention is directed to a method and apparatus for detecting a lane on a road, the latter of which includes an edge sensor (ED) for detecting edges indicative of boundaries of opposite sides of each lane, an edge memory (EM) for storing the edges to form a couple of continuous lines of edge groups indicative of the opposite boundaries of the lane, and an image processor (DP) for defining the opposite boundaries of the lane on a plane in a three-dimensional geometry. A center of curvature defining device (RC) defines a center of curvature to the opposite boundaries of the lane. An edge line extracting device (ES) divides the edge groups stored in the edge memory into a plurality of continuous regions each having a predetermined length along a concentric circle arc having the same center as the center of curvature, and extracts a pair of edge lines from each region.

Abstract: A navigation system for an autonomous mobile robot within an environment which comprises coded signs at predetermined points comprising means for storing data regarding said environment, including data regarding the positions of said coded signs relative to the environment, passive vision systems for the image acquisition and automatic recognition of said coded signs, a computer for estimating its own position and orientation relative to one of said coded signs and to the environment, means for acquiring the location of target positions, means for planning a path to be covered within said environment to reach target positions, and means for controlling the robot motion based on the stored path data.

Abstract: An onboard forward monitoring system is disclosed in which three television cameras, each supported by a steering mechanism, take picture of a road surface located forward of a vehicle at near distance, a medium distance and a far distance zone to detect white lines which partition a lane on the road surface, thus detecting a vehicle running ahead on the lane which is defined by the white lines. To enable a reliable detection and tracking of the vehicle running ahead in any zone of the road surface even when the road is curved, the individual television cameras are steered so that a vehicle running ahead is positioned at the center of the screen whenever such vehicle is present and so that a center across the width of the lane is positioned at the center of screen when a vehicle running ahead is not detected.

Abstract: A video camera or equivalent sensor is mounted on a vehicle and used to detect the lane markings on the road (usually the white painted lines). An associated signal processor (11) estimates the vehicle's lateral position in relation to the lane markings. An electric motor (4) coupled to the steering mechanism (1) is used to provide a torque input to the steering which may either assist or oppose the steering torque from the driver. The processor (11) is designed to assist the driver to maintain the vehicle's lane position by holding the vehicle at a set-point using a biasing torque. This simulates the effect of the lane being cambered upwards towards the lane edges. However the driver is able to override or cancel the effect if the driver applied steering torque exceeds a prescribed torque threshold.

Abstract: An object recognition apparatus that can recognize an object in an image acquired by an on-vehicle camera mounted on a vehicle with high efficiency and accuracy. A recognition processing is carried out in a cut off range, which is cut off from the image, and in which an object to be recognized is supposed to be present. The cut off range is obtained using support information supplied from a position detection device and/or an anti-lock brake device of the vehicle. Since the object in the image changes its position as the vehicle moves, the displacement must be estimated during the object recognition. The estimation requires camera attitude parameters of the on-vehicle camera with respect to the road, and the estimation is performed using support information supplied from the position detection device and/of the anti-lock brake device. This will improve the efficiency and accuracy of obtaining the camera attitude parameters.

Abstract: A warning system for a vehicle comprises a pair of stereoscopic cameras, image recognizing means for processing images, two warning devices disposed on the left and right side of a driver, the deviation judging means for judging a possibility of deviation from the lane where the vehicle runs or a possibility of collision to obstacles and warning control means for determining the warning device to be operated. When the vehicle has a possibility of deviation from the lane or a possibility of collision to obstacles, either left or right side of the warning device inform the driver of the possibility of deviation or collision, whereby the driver can take a quick action for avoiding hazard. Further, when the vehicle runs on a narrow load, the driver can know an inability of passing through the road by the left and right warning devices operated simultaneously.

Abstract: A laser-directed ranging system for use in telerobotics applications and other applications involving physically handicapped individuals. The ranging system includes a left and right video camera mounted on a camera platform, and a remotely positioned operator. The position of the camera platform is controlled by three servo motors to orient the roll axis, pitch axis and yaw axis of the video cameras, based upon an operator input such as head motion. A laser is provided between the left and right video camera and is directed by the user to point to a target device. The images produced by the left and right video cameras are processed to eliminate all background images except for the spot created by the laser. This processing is performed by creating a digital image of the target prior to illumination by the laser, and then eliminating common pixels from the subsequent digital image which includes the laser spot.

Abstract: The present invention features a method of identifying and/or extracting an object from multiple fused information sources, such as maps and images. The system allows a user to integrate information freely from multiple sources, such as maps, socio-economic data and various types of images. Data is first retrieved and then processed to transform its pixel representation to a region representation. The region representation is then refined by merging mechanisms, such as segmentation. The identified and/or extracted object can then be visualized by the user. Features or objects can then be extracted using the user's expert rules and confidence levels, which confidence levels may be derived by fuzzy logic.

Abstract: The present invention relates to an automatic system for controlling the steering of a non-railed transfer crane travelling along a lane indicant. The system comprises a vision sensor for continuously photographing the condition of a crane's actual travelling direction with respect to lanes represented by the lane indicant, and outputting predetermined deviations (distance as well as angle) showing off-centered degrees between the crane's actual travelling direction and the lanes based on the photographed image signal, and a deviation processor for outputting a control signal to a motor driver so that the crane can travel toward removing the deviation distance. By properly changing a rotative velocity of the crane's wheels, the present invention prevents the crane's travelling direction from being off-centered from the lanes.

Abstract: An automatic steering device is presented for controlling the direction of travel of an asphalt finisher during a paving operation. The device is provided with a laser generator (18) which projects a laser beam of a slit shape on a series of objects along the roadside which is selected to served as a reference line (A). An image recording device (17), a CCD camera, is disposed on the vehicle member (2), which records the projected laser light illuminating the objects and outputs a generated image (Ba) to a master controller (22). The master controller (22) determines the current deviation of the vehicle member (2) from the reference line (A) by the changes in the position of the generated image (Ba), and operates the automatic control device so as to steer the vehicle member (2) in the correct direction to permit the asphalt finisher to follow the reference line (A).

Abstract: Disclosed is an automatic travelling apparatus which is capable of taking an image of an area ahead of a vehicle by an image pick-up means attached to the vehicle; sampling and processing the image data to extract therefrom continuous line segments; determining a permissible travelling area ahead of the vehicle on the basis of the continuous line segments extracted; setting a target course in the permissible travelling area thus determined; detecting the instantaneous running condition of the vehicle; estimating, on the basis of the instantaneous running condition, a steering amount to permit the vehicle to follow the target course; and steering the vehicle with reference to the steering amount, and furthermore of renewing, on the basis of the instantaneous running condition during a period of image sampling, the preceding position of the vehicle in the permissible travelling area and reset a target course in the permissible travelling area in relation to the renewed position.

Abstract: A device and a process for judging the contour of a road by processing data from an image taken of the road by a camera. In the data processing, Hough transform is used to obtain a plurality of straight lines approximate to the edges of the road. In order to recognize the contour of a road, it is most important to recognize the edges of the road. For the recognition of a road, for example, an image taken of the road is divided into upper and lower regions. In the lower region, two straight lines are given approximate to the right and the left edges of the road. In the upper region as well, two straight lines are given approximate to the right and the left edges of the road. Then, positional relationships between the intersection of the former two straight lines and that of the latter two straight lines are compared. Based on positional relationships, it can be judged very easily whether the road is straight, curves, inclines or declines.

Abstract: A system and method for using a camera and an associated display means for facilitating the loading of the distinguishing characteristics of a workpiece into the control system for a machining system to allow machining of workpieces in accordance with a stored program.

Abstract: A movable security camera apparatus for providing visual security with minimal human effort, error and equipment expense, includes a MICOM, a path input section, a sensing section, a sensor detecting section, a camera video tape recording section, and a main driving section. The MICOM controls the whole system, including the motion of a watch camera on the basis of control programs in accordance with inputted path information. The sensing section provides the data for the moving direction of the camera, the data being obtained when sensors of a rail are controlled by the path commands of the MICOM.

Abstract: A control device of an autonomously moving body according to the present invention comprises at least one image pickup unit which picks up the image of a moving road of an automatically moving body; an image processing unit which processes a plurality of image data outputted from the image pickup unit and detects and outputs the condition of said moving read, or an outside information obtaining unit which obtains environmental information other than image; a storage means which stores data outputted from said image processing unit or said outside information obtaining means; a data control section which corrects said data stored in said storage means to data of an arbitrary time and position; a data evaluating section which integrates a plurality of data outputted from said data control section into one moving road data; and a control section which controls the movement of the autonomously moving body according to the moving road data outputted from said data evaluating section.