Mitsubishi Electric Corporation

Mitsubishi Denki Kabushiki Kaisha

Hideaki Maehara

Kenji Taira

Momoyo Hino

Yoshimi Moriya

Akira Minezawa

Kazuyuki Miyazawa

Hidetoshi Mishima

Sumio Kato

Tomoya Sawada

Mengxiong Wang

Momoyo Nagase

Shunichi Sekiguchi

Takashi Sato

Satoshi Tanaka

Ryoji Hattori

Hironobu Abe

Koichi Takeuchi

Tetsuro Wada

Eiji Ueda

Yosuke Ishiwatari

Naohiro Shibuya

Ryoga Suzuki

An object of the present invention is to provide a water level measurement device and a shoreline extraction method each of which is capable of stably measuring the water level. A pixel selection unit () selects a pixel of interest () from a designated area () designated from a captured image (), and an identification image extraction unit () extracts identification images (), () each coming in contact with the pixel of interest (). The identification unit () calculates an identification strength indicating a degree to which an area corresponding to each of the identification images (), () is a water area, on a basis of the result of machine learning related to identification between the water area and a non-water area. The shoreline extraction unit () extracts a shoreline in the captured image from the identification strength of the area corresponding to each of the identification images (), (), on a basis of the result of machine learning related to the identification between the water area and the non-water area by the learning unit ().

Water level measurement device and shoreline extraction method

An attitude estimation apparatus () includes: a data acquiring unit () for acquiring observation data; a range-measurement point coordinate calculator (A) for calculating geodetic coordinates of a range-measurement point in a geodetic coordinate system using positioning data, ranging data, actual attitude data, and an estimated value of an unknown parameter representing an attitude of a flying object; an image coordinate calculator (B) for calculating coordinates of a projected point by performing projection transformation from the geodetic coordinate system to an image coordinate system on the geodetic coordinates; an image matching processor () for detecting image coordinates of the range-measurement point appearing in a first captured image by executing image matching between the first captured image and a second captured image selected from captured images; and an attitude estimator () for correcting the estimated value such that a magnitude of a difference between the coordinates of the projected point and the image coordinates decreases.

Attitude estimation apparatus, attitude estimation method, and observation system

An image feature map generating unit () generates, on the basis of feature amounts extracted from a plurality of images successively captured by a camera (), an image feature map which is an estimated distribution of the object likelihood on each of the images. An object detecting unit () detects an object on the basis of the image feature map generated by the image feature map generating unit ().

Object detection device and object detection method

An object detection device includes: an optical flow calculator to calculate an optical flow between images captured by the image capturer at different times; an evaluation value calculator to divide the image captured by the image capturer into areas, and calculate, for each divided area, an evaluation value by using the optical flows of pixels belonging to the divided area, the evaluation value indicating a measure of a possibility that the divided area is an object area representing part or whole of the object to be detected; and an area determinator to determine an area in an image, in which the object to be detected exists, by comparing the evaluation value of each divided area calculated by the evaluation value calculator with a threshold value.

Image matching on a pair of image data about images which are shot at different shooting positions is performed, and a point corresponding to the coordinates of a distance measurement point on the image shown by one image data of the pair is searched through the image shown by the other image data of the pair. The value of a parameter showing the attitude of an airplane () is corrected in such a way that the difference between the coordinates of the distance measurement point on the image shown by the other image data of the pair and the coordinates of the corresponding point which is searched for via the image matching becomes small, to estimate the attitude of the airplane ().

Navigation system and survey system

It is an object to obtain a high-resolution image generation apparatus that can generate a high-quality image by sorting out good portions from faulty portions in optical flow. The present invention includes: a hard disk that stores multi-viewpoint image information and parameter information of a base image and a plurality of reference images; an optical flow computation unit that extracts a plurality of pairs of the base image and a reference image, the plurality of pairs each including a different reference image, and computes optical flow for each pair; a depth information computation unit that computes depth information which indicates depth of each pixel of the base image for each pair, based on optical flow and the parameter information; and an optical flow sorting unit that determines whether or not each piece of pixel-based correspondence information included in the optical flow of each pair is to be used for improving a resolution of the base image, based on two pieces of the depth information.

High-resolution image generation apparatus, high-resolution image generation method, and high-resolution image generation program

An image generation system which comprises an image generation apparatus having viewpoint definition means for defining a virtual viewpoint placed in virtual three dimensions, virtual panel definition means for defining a virtual object displayed in the virtual three dimensions and defining a virtual panel being placed in the virtual three dimensions, the virtual panel onto which a moving image is projected, based on the virtual viewpoint and the virtual object, moving image selection means for selecting a moving image to be projected onto the virtual panel from among a plurality of moving images based on the virtual viewpoint defined in the viewpoint definition means, and virtual three-dimensional image generation means for placing the virtual panel defined in the virtual panel definition means in the virtual three dimensions, projecting the moving image selected by the moving image selection means onto the virtual panel, and generating an image from the virtual viewpoint defined in the viewpoint definition means, and a moving image output apparatus for outputting the plurality of moving images to the image generation apparatus.

Image generation system, image display system, computer-readable record medium recording image generation program, and image generation method

A drawing recognition system is disclosed which recognizes even a complex low-quality drawing containing overlapping charts, or many blurs or discontinuations with less operations. The system includes both a program for approximating a graphical object to be recognized and a program for approximating positions on the approximated graphical object. The system further includes a means for creating a chart model according to the designation, and a chart recognition means for matching the chart model and the chart to be recognized in the drawing.

Growing community of inventors

Tokyo, Japan

Hideaki Maehara