Abstract: An object recognition system having at least two image sensors and a controller that is adapted for measuring the distance from the system to a physical object with respect to respective windows of a n image captured by the sensors. The controller is further programmed to form clusters by uniting adjacent windows that have similar measure distances. The controller is programmed to judge whether each of the clusters is valid or invalid based on the attributes of the cluster and to recognize an object based on the clusters judged to be valid.

Abstract: An object detecting apparatus including an imaging section, an extracting section for extracting edge images from image signals supplied from the imaging section, a forming section for forming a differential image between a first edge image extracted from an image signal that has been picked up for an object at a certain time and a second edge image extracted from an image signal that has been picked up for the same object at a later time, and a detecting section for detecting the object on the basis of the differential image. With the object detecting apparatus, portions of a background without motion that are contained in the edge images are eliminated to produce edge images that only relate to the object that is substantially in motion. As a result, information can be efficiently obtained that relates to the state, position and otherwise of the object in motion.

Abstract: An object recognition system comprises at least two image sensors and a controller that is adapted for measuring the distance from the system to a physical object with respect to respective windows of an image captured by the sensors. The controller is further programmed to form clusters by uniting adjacent windows that have similar measured distances. The controller is programmed to judge whether each of the clusters is valid or invalid based on the attributes of the cluster, and to recognize an object based on the clusters judged to be valid. In one embodiment, the attributes of the cluster is an area of the cluster. The controller calculates the area of the cluster based on the number of windows contained in the cluster and measured distance of each of the windows, and judges that the cluster is valid if the area is larger than a predetermined threshold value. The controller detects any failed state of the captured image based on the number of clusters judged to be invalid.

Abstract: A motor vehicle is controlled with a neural network which has a data learning capability. A present value of the throttle valve opening of the engine on the motor vehicle and a rate of change of the present value of the throttle valve opening are periodically supplied to the neural network. The neural network is controlled to learn the present value of the throttle valve opening when the rate of change of the present value of the throttle valve opening becomes zero so that a predicted value of the throttle valve opening approaches the actual value of the throttle valve opening at the time the rate of change thereof becomes zero. An operating condition of the motor vehicle is controlled based on the predicted value of the throttle valve opening, which is represented by a periodically produced output signal from the neural network.