Sanyo Electric Co., Ltd.

Panasonic Intellectual Property Management Co., Ltd.

Hitoshi Hongo

Yohei Ishii

Kozo Okuda

Changhui Yang

Hideto Fujita

Akihiko Yamada

Mamoru Yasumoto

A drive assistance device has an imaging device () mounted on a vehicle body and imaging a region surrounding the vehicle body, lens distortion correction means () for performing lens distortion correction for an inputted image taken by the imaging device (), and a display () for displaying the image obtained by the lens distortion correcting means (). The lens distortion correction means () divides the inputted image into multiple regions and performs lens distortion correction for each of the regions with different distortion correction level.

Drive assistance device

A driving assistance system that projects images imaged by multiple vehicle cameras onto a plane, and synthesizes projection images from images obtained at different times to accurately determine whether the vehicle cameras have moved out of their proper positions or imaging directions. The system includes: first and second in-vehicle cameras that capture first and second images, respectively. The cameras capture overlapping regions respectively in different directions. An image converter converts the first and second images into first and second projection images projected onto a plane. A solid object detection unit determines whether a solid object exists in the overlapping region. When no solid object exists, the images of the overlapping regions within the first and second projection images are compared to generate a comparison value. The comparison value is in turn compared with a threshold value for the determination of vehicle camera movement out of its proper position.

Image processor, driving assistance system, and out-of-position detecting method

One camera having a horizontally wide view angle is installed at each of the left and right rear ends of a tractor. The visual field of the left camera includes the road surface located to the left side of the tractor and a trailer, and the like. The visual field of the right camera includes the road surface located to the right side of the tractor and the trailer, and the like. The left and right cameras have a common visual field at the rear side of the trailer. A panorama image obtained by synthesizing images respectively obtained by the left and right cameras is displayed on a display device located in the interior of the tractor.

Image processor and vehicle surrounding visual field support device

An object detection apparatus for detecting a specific object in an input image includes a specific object detection module for performing a specific object detecting process of setting the input image or a reduced image of the input image as a target image, and of determining whether or not the specific object exists in a determination region while scanning the determination region in an edge feature image of the target image. The specific object detection module includes a determination module for determining whether the specific object exists in the determination region, based on an edge feature amount of the edge feature image corresponding to the determination region, and a previously determined relationship between an edge feature amount and a weight indicating object likelihood for each predetermined feature pixel in an image having the same size as the determination region.

Object detection apparatus for detecting a specific object in an input image

A driving support system includes a rotation amount setting means and a bird's eye view image generating means. The rotation amount setting means sets a previously-set inclination angle of the image pickup device to a horizontal plane at a rotation angle during coordinate transformation for the image within a range where a distance from the vehicle is not more than a predetermined threshold in the taken image, while computing and setting the rotation angle during the coordinate transformation based on the previously-set inclination angle of the image pickup device to the horizontal plane and the distance from the vehicle for the image within a range where the distance from the vehicle is more than the predetermined threshold in the taken image. The bird's eye view image generating means generates an extension bird's eye view image by transforming a coordinate of the taken image into a coordinate of a bird's eye view using the rotation angle set by the rotation amount setting means for the image corresponding to the coordinate.

Driving support system

There is provided a recognition system capable of correctly recognizing nodding action of a user and controlling interaction reflecting the user's intention. The instruction recognition system includes a gesture recognition section for recognizing the user's nodding action on the basis of a photographed image of the user's head; a line-of-sight detection section for detecting the line of the user's sight; a display section for indicating image data; and a controller which determines the candidate for selection, toward which the line of sight is directed, to be selected and which performs predetermined processing when the nodding action recognition section detects nodding action and when the line of sight detected by the line-of-sight detection section is oriented toward any one of the candidates for selection during the nodding action, while the system awaits the user's instruction and one or a plurality of candidates for selection are displayed on the display section.

Instruction recognition system having gesture recognition function

By a first camera fastened to the head of a worker at a remote working environment, an image of an object to be worked on is shot within a range including at least the worker's field of view. This image is transmitted to the work instructor side and displayed on a display device. The work instructor carries out a pointing indication movement with respect to the image of the object displayed on the display device. That movement is shot by a second camera and applied to an instruction information determination unit as video information. The instruction information determination unit generates pointing position information by the well-known gesture recognition process and transmits the information to the worker side. A marker according to the pointing position information transmitted from the work instructor side is overlapped on the image of the object shot by the first camera and displayed on the display of a head mount type display device fastened to the head of the worker. A particular region on the object is indicated by pointing to the worker. At the same time, the work procedure is explained by voice transmission from the work instructor.

Growing community of inventors

Shijonawate, Japan

Hitoshi Hongo