Kyushu Institute of Technology

Equos Research Co., Ltd.

Aisin Corporation

Caterpillar Japan Ltd.

Mitsubishi Gas Chemical Company, Inc.

Nihon Matai Co., Ltd.

Nippon Yusen Kaisha

Mitsubishi Denki Kabushiki Kaisha

Agency of Industrial Science and Technology

Caterpillar Sarl

Takenaka Corporation

Sokkia Company Limited

Kogyo Gijutsuin

Kyoritsu Co., Ltd.

Hideo Yamada

Shuichi Enokida

Kazuhiro Kuno

Masatoshi Shibata

Satoshi Fujii

Tomoaki Ono

Hakaru Tamukoh

Shoei Kataoka

Isao Murota

Yuzuru Takahashi

Michael Jones

Yasuo Komamiya

Susumu Tsunoda

Ryuya Muramatsu

Kunio Nakajima

Kenji Kadokura

Susumu Uchida

Hisamoto Naniwa

Shigemi Ichiki

Yoshinobu Sugiyama

Kiyoshi Shimizu

Mitsuo Kawashima

Hiroshi Tateno

Hisatoshi Kishi

Kazutaka Onozuka

Toshio Kuno

Yukio Kuno

Eiji Iwata

Hiroyuki Fujisada

Masatoshi Yoshimura

Shiryu Ooe

Masaharu Kamagata

Hiromichi Ohtsuka

Tatsuya Hashimoto

Yuta Yamasaki

Masashi Usuda

Hideo Kuno

Tatsuya Shimasaki

Isamu Makita

Toshio Tsurushima

Hisao Tanoue

Yasuaki Kakizawa

An image recognition device includes: an image processing device that acquires a feature amount from an image; and an identification device that determines whether a prescribed identification object is present in the image, and identifies the identification object. The identification device includes a BNN that has learned the identification object in advance, and performs identification processing by performing a binary calculation with the BNN on the feature amount acquired by the image processing device. Then, the identification device selects a portion effective for identification from among high-dimensional feature amounts output by the image processing device to reduce the dimensions used in identification processing, and copies low-dimensional feature amounts output by the image processing device to increase dimensions.

Information processing device

An image processing device has a function for plotting a luminance gradient co-occurrence pair of an image on a feature plane and applying an EM algorithm to form a GMM. The device learns a pedestrian image and creates a GMM, subsequently learns a background image and creates a GMM, and calculates a difference between the two and generates a GMM for relearning based on the calculation. The device plots a sample that conforms to the GMM for relearning on the feature plane by applying an inverse function theorem. The device forms a GMM that represents the distribution of samples at a designated mixed number and thereby forms a standard GMM that serves as a standard for image recognition. When this mixed number is set to less than a mixed number designated earlier, the dimensions with which an image is analyzed are reduced, making it possible to reduce calculation costs.

Image processing device, image recognition device, image processing program, and image recognition program

An image processing device converts an image that is a recognition object image to high-resolution, medium-resolution, and low-resolution images. The device sets the pixel of interest of the high-resolution image, and votes the co-occurrence in a gradient direction with offset pixels, the co-occurrence in the gradient direction pixels in the medium-resolution image, and the co-occurrence in the gradient direction pixels in the low-resolution image, to a co-occurrence matrix. The device creates such a co-occurrence matrix for each pixel combination and for each resolution. The device executes the process on each of the pixels of the high-resolution image, and creates a co-occurrence histogram wherein the elements of a plurality of co-occurrence matrices are arranged in a line. The device normalizes the co-occurrence histogram and extracts, as a feature quantity of the image, a vector quantity having as a component a frequency resulting from the normalization.

Image feature amount output device, image recognition device, the image feature amount output program, and image recognition program

An image recognition device executes a Hilbert scan of frame image data constituting moving-image data to generate one-dimensional spatial image data, and further arrays the one-dimensional spatial image data in a time direction to generate two-dimensional spatio-temporal image data that holds spatial information and temporal information. The image recognition device converts the moving-image data into the two-dimensional spatio-temporal image data while holding the spatial and temporal information. By means of a CNN unit, the image recognition device executes a convolution process wherein a two-dimensional filter is used on the spatio-temporal image data to image-recognize a behavior of a pedestrian who is a recognition object. The image recognition device executes behavioral recognition of the pedestrian that requires a three-dimensional analysis consisting of two dimensions for space and one dimension for time by the image recognition process of the two-dimensional image by the CNN, and estimates a state of the pedestrian.

Image data generation device, image recognition device, image data generation program, and image recognition program

A hardware configuration is constructed for calculating at high speed the co-occurrence of luminance gradient directions between differing resolutions for a subject image. In an image processing device, a processing line for high-resolution images, a processing line for medium-resolution images, and a processing line for low-resolution images are arranged in parallel, and the luminance gradient directions are extracted for each pixel simultaneously in parallel from images having the three resolutions. Co-occurrence matrix preparation units prepare co-occurrence matrices by using the luminance gradient directions extracted from these images having the three resolutions, and a histogram preparation unit outputs a histogram as an MRCoHOG feature amount by using these matrices. To concurrently processing the images having the three resolutions, high-speed processing can be performed, and moving pictures output from a camera can be processed in real time.

Method and device to determine image features using multi-resolution gradient analysis

Lens holder for magnifying glass with lamp

An image recognition device sets an overall observation region which surrounds a whole body of an object and partial observation regions which surround characteristic parts of the object respectively to locations in an image which are estimated to include captured images of the object. The device clips images in the overall observation region and the partial observation regions, and calculates similarity degrees between them and previously learned images on the basis of a combination of two image feature amounts. The device calculates an optimum ratio in combining the HOG feature amount and the color distribution feature amount individually for the regions. This ratio is determined by setting a weight parameter &#x3b1;i for setting a weight used for combining the HOG feature amount and the color distribution feature amount to be included in a state vector and subjecting the result to complete search by a particle filter.

Image recognition by setting a ratio of combining the feature correlation coefficients for the respective acquired image feature amounts

An image recognition device adds a margin region filled with predetermined image data to a periphery of a captured image captured by a camera to create an expanded image larger than the captured image. When a person is too close to the camera, a part of a person image protrudes from the captured image, but a large detection window which also includes the margin region is set, whereby a window image including a protruding region is taken out of the expanded image. The window image lacks a protruding part of the person image, but it is an image showing an entire body of the person image. The image recognition device stores many reference images assuming various states of a person. The image recognition device extracts features from the window image, and compares them with a feature of the reference image, thereby recognizing the person image.

Image recognition device and image recognition program

Method for controlling input to a touch panel includes a monitor screen display displaying a rear camera image screen, a measurement screen at the touch panel, and an input operation screen display in which an input operation can be performed. When the machine is operable, a monitor screen can be displayed in an input lock state in which the input operation is inhibited by turning off a hydraulic lock switch and releasing a hydraulic lock state. A specific input lock releasing operation on the touch panel releases the lock and the monitor screen display is switched to the input operation screen display.

Input control method of touch panel monitor for working machine

A pulse wave detection device color converts a frame image of a moving image from RBG components to YIQ components, and identifies an eye section using the eye color of a user prepared in advance with a Q component. Next, the pulse wave detection device uses the Y values of the eye section to detect the brightness of the imaging environment. Then, the pulse wave detection device detects a pulse wave signal Qm on the basis of the average of the Q-values of a skin section in the frame image, corrects a change in the brightness by subtracting from Qm the average value Ye of the Y values of the eye section, and thereby outputs a post-brightness-correction Qm. As a result, a pulse wave can be successfully detected even if the brightness is changing because the user is moving in a vehicle or the like.

Pulse wave detection device and pulse wave detection program

A pulse wave detection device color converts a frame image of a moving image from RBG to HSV components, and identifies a skin section using the skin color of a user prepared in advance with an H component. The device converts the skin section of the image to YIQ components, and takes Qm as a pulse wave signal, Qm being obtained by averaging the Q values of the pixels. The device then obtains a chronological change in the pulse wave signal Qm and outputs the change as a pulse wave. Accordingly, it is possible to exclude disturbance factors from the pulse wave detection target, and successfully detect a pulse wave. The identification of the skin section is performed using the H component to identify candidate pixels, and using the S component to narrow down the candidate pixels to the target, so high-precision identification of the skin section is possible.

An indicator control system for switching from a measurement value display mode to a camera display mode and vice versa in order to display a selected mode on a monitor section of an indicator and for generating an alarm from an alarm section. The measurement value display mode shows the measurement data of an object to be monitored such as a construction machine. The camera display mode being for a camera section that is mounted on the construction machine.

Indicator control system for constrution machine

An indicator control system with a camera section provided with a switch for switching from a measurement value display mode to a camera display mode and vice versa to display a selected mode on a monitor section of an indicator. The measurement value display mode shows the measurement data of an object to be monitored on a construction machine, and the camera display mode is for the camera section mounted on the construction machine.

Indicator control system with camera section

A remote management system including a work machine side dynamic state data management device, and a management section side management device for causing a communication unit capable of data transmission and reception to and from a communication unit on the work machine side to receive dynamic state data transmitted from at least the work machine side and at the same time, causing a control section to run a Web site capable of providing data only to a user permitted to access and reflecting arbitrary data out of the received dynamic state data in the Web site.

Remote management system of dynamic state data of work machine

A method for fabricating a flat, light-emitting display panel includes the steps of applying frit seal to the pin electrodes in a state of pressing the rear panel against the front panel to keep them in contact with one another using a flat plate having an opening formed at a position corresponding to each of the pin electrodes; drying the frit seal to fix provisionally the rear panel to the front panel; detaching the flat plate from the both panels; applying frit seal to an end of the front panel and a side face of the rear panel; and burning the whole of components. The sequence of the application of the frit seal to the pin electrode and the application of the frit seal to the end of the front panel and the side face of the rear panel may be altered. The frit seal having flowability less than the frit seal applied to the pin electrode is applied to the end of the front panel and the side face of the rear panel.

Method for fabricating a flat, light-emitting display panel

Growing community of inventors

Tokyo, Japan

Hideo Yamada