Yuji Otsuka has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
Abstract: The invention provides an image processing system capable of precisely locating the positions of the light spots covering near headlights through far tail lamps by using one camera. The invention, discriminating the headlights and tail lamps from noise lights such as a traffic light, streetlight, and vending machine, enhances the vehicle detection performance at night. The system includes an image input means that inputs images in front of a vehicle, an image analysis means that analyzes the images inputted by the image input means. The image input means has a means of photographing more than two images with different exposures. The image analysis means analyzes the images photographed by the image input means to transform them into the position information of the vehicles traveling in front.
Abstract: An image processing system which detects foreign matter on window of a vehicle with high reliability. The system includes an image processor, a first lamp, and a second lamp and when to turn on the first and second lamps is controlled by the image processor. Light from the first lamp passes through the glass. If there are raindrops on the outer surface of the glass, light is reflected by raindrops and light from the second lamp is reflected by a surface of the glass and such reflected light goes through a lens and an optical filter with prescribed optical characteristics to an imaging device.
Abstract: In a lane marker recognition method comprising the steps of inputting an image including a lane marker, extracting a luminance change point in the image input in the image inputting step, and estimating the position of the lane marker using the edge points extracted in the edge extracting step, the edge extracting step calculates an angle of orientation of each of the edges and the lane marker position estimating step extracts edge points that are oriented toward a vanishing point of a road from among the edge points extracted in the edge extracting step.
Abstract: A traffic environment recognition system includes an image-processing unit, an information-merging unit, a radar unit, and a network connected to the image-processing unit, the radar unit, the information-merging unit and a vehicle control unit capable of controlling the traveling operation of a host vehicle. The image-processing unit recognizes headway distance, the azimuth, relative speed and width of the preceding vehicle, and the position of the host vehicle in a lane. The radar unit recognizes headway distance, the azimuth and relative speed of the preceding vehicle. The information-merging unit receives recognition results provided by the image-processing unit and the radar unit through the network, merges the recognition results, identifies recognition objects relating to the recognition results.
Abstract: A driving lane recognition system which can improve the lane recognition accuracy by stably detecting the various kinds of lane markers is disclosed. An image processing means 6 for image-processing a road image taken by a camera 5 has a plurality of different kinds of image processing algorithms 9 to 11. A driving lane is detected by selecting an image processing algorithm suitable for the driving lane out of the plurality of different kinds of image processing algorithms 9 to 11 corresponding to a road on which a vehicle is running.
Abstract: Information of light from a subject is converted into information of the electric charges to generate image data for one screen in an image pickup device, the image data is outputted to an image processing LSI, only the image data belonging to a plurality of areas is selected by a processing amount reduction unit, the selected image data is transferred to a RAM in a single chop by a data transfer unit, and the processing of recognizing a white line is executed by a CPU on the basis of the image data stored in the RAM.
Abstract: An enteric-soluble composition for coating drugs and the like comprises a conventional enteric-soluble polymer in admixture with a polyanionic polymer which is soluble at low pH values. By altering proportions and types of both polymer, it is possible to alter the pH value at which the composition will disintegrate to release the drug or the like.