Hitachi, Ltd.

Renesas Electronics Corporation

Iwatsu Electric Company Ltd.

Nippon Telegraph and Telephone Corporation

Renesas Technology Corp.

Sharp Kabushiki Kaisha Corporation

Sharp K.k.

Other

Hitachi Automotive Systems, Ltd.

Hitachi-kokusai Electric Inc.

Takashi Oshima

Taizo Yamawaki

Yuichi Okuda

Takaya Yamamoto

Keisuke Kimura

Hideo Nakane

Tatsuji Matsuura

Masaru Kokubo

Keiichi Hibi

Tomomi Takahashi

Osamu Nakamura

Hirotaka Nakano

Makoto Takahashi

Noriyuki Sakuma

Atsushi Isobe

Kenji Maio

Tadashi Uchiumi

Yohei Nakamura

Takashi Kawamoto

Yuudai Kamada

Keisuke Yamamoto

Masanao Yamaoka

Takahiro Miki

Daisuke Maeda

Akira Matsumoto

Naoki Mori

Masaki Fujiwara

Manabu Nakamura

Akira Kuriyama

Kenji Nozawa

Tatsuo Nakagawa

Yuki Furubayashi

Tsuneko Kura

Jiro Nakabayashi

Tsuneaki Iwano

Youji Kanada

Nobuyuki Ema

Tetsuo Matsui

Ryoji Yamaguchi

Masayuki Ikeda

Mitsuya Fukazawa

Atsutake Kosuge

Hiroshi Satoh

Osamu Hakamura

Masato Hayashi

Kazuo Ono

Goichi Ono

Chisaki Takubo

Tsukasa Fujimori

Masahiro Shioi

Yuki Okada

Tomohiko Yano

Takeshi Makiyama

Toshihiko Fukamachi

Takashi Shiota

Yoshiyuki Shibahara

Takeshi Doi

Tadashi Kishimoto

Kunihiko Usui

Noboru Mihara

Naoki Yada

Irei Kyu

Shuji Yamauchi

Kenzi Tamogami

Kiyoshi Hizume

Katsuki Tateyama

Yukinori Akamine

Viviana Crescitelli

Akihiro Kitagawa

Keijiro Mori

Tadashi Uchimi

An information processing device includes a parallel deep neural network configured to input a captured image of an article to deep neural network models respectively corresponding to a plurality of articles and perform inferences about the plurality of articles in parallel using the deep neural network models, a new article determination unit configured to determine whether an article included in the image is an unlearned article based on learned model information about the articles and the image, and a new article learning unit configured to learn a deep neural network model corresponding to the article determined to be unlearned based on the image and initial model configuration information about the deep neural network model when the article included in the image is determined to be an unlearned article. The new article learning unit adds the learned deep neural network model to the deep neural network models.

Information processing device and learning recognition system

An image processing device including a storage unit configured to store an object detection neural network trained using a first K-channel image generated from a first M-channel image and a first N-channel image generated from the first M-channel image, a reception unit configured to receive, from a sensor, a second M-channel image and a second N-channel image that include an identical subject, and an image analysis unit configured to generate, using the object detection neural network trained using the first K-channel image, object detection result information with respect to a second K-channel image generated from the second M-channel image and the second N-channel image, and output the object detection result information.

Image processing device, image processing method and image processing system

A three-dimensional position and posture recognition device speeds estimation of a position posture and a gripping coordinate posture of a gripping target product. The device includes: a sensor unit configured to measure a distance between an image of an object and the object; and a processing unit configured to calculate an object type included in the image, read model data of each object from the external memory, and create structured model data having a resolution set for each object from the model data, generate measurement point cloud data of a plurality of resolutions from information on a distance between an image of the object and the object, perform a K neighborhood point search using the structured model data and the measurement point cloud data, and perform three-dimensional position recognition processing of the object by rotation and translation estimation regarding a point obtained from the K neighborhood point search.

Three-dimensional position and posture recognition device and method

A MASH type sigma delta AD converter includes a modulator, an analog filter filtering an extraction signal obtained by extracting a probe signal and an quantization error generated in a quantizer within a sigma delta modulator, a low speed AD converter performing an AD conversion of an output signal of the analog filter, a first adaptive filter searching for a transfer function of the sigma delta modulator, a second adaptive filter searching for a transfer function from an output of the modulator to the low speed AD converter via the analog filter, and a noise cancellation circuit cancelling the probe signal and the quantization error included in an output signal of the quantizer using the search results by the first and second adaptive filters.

AD converter device and millimeter wave radar system

A neural network circuit having a plurality of analog-to-digital multipliers generates an analog product-sum voltage corresponding to the sum of charge signals of each of the analog-to-digital multipliers.

Neural network circuit

In a MEMS electrostatic capacitor type acceleration sensor, the manufacturing costs of MEMS elements are reduced, and at the same time, the variations of the electrical and mechanical characteristics of the MEMS elements are reduced. A detection circuit generates a voltage signal corresponding to the product of a difference between the two capacitance values of a pair of MEMS capacitors and a servo signal. A modulation circuit outputs a signal corresponding to the difference between the capacitance values using the servo signal. The control circuit outputs the servo signal on the basis of a signal corresponding to the difference between the capacitance values.

MEMS electrostatic capacitor type acceleration sensor

Provided is a sensor that is highly accurate while ensuring reduced power consumption. A sensor is an electronic circuit that includes a sensor element, an analog filter, an A/D converter, and first and second electronic circuit. The analog filter filters a waveform that includes a sensor signal from the sensor element and noise based on a servo signal. The A/D converter converts the waveform filtered by the analog filter into a first digital signal. The first electronic circuit includes a digital filter and acquires a second digital signal by performing signal processing including at least a filtering process on the servo signal by using the digital filter. The second electronic circuit acquires a third digital signal by subtracting the second digital signal from the first digital signal. A setting for the signal processing for acquiring the second digital signal is changed on the basis of the third digital signal.

Sensor with servo noise reduction

The present invention is directed to a CV conversion amplifier which is small in current consumption and capable of securing a sufficient capacitance-voltage conversion gain and a sufficient amplitude range of an output voltage and a capacitive sensor using the same which is low power consumption, low in noise, and wide in an input signal allowable range. A capacitive sensor includes first and second detection capacitors, a CV conversion circuit includes first and second feedback capacitors and obtains a voltage based on capacitance values of the first and second feedback capacitors, an AD converter performs analog digital conversion on an input voltage and obtains a digital signal, a digital control unit receives the digital signal as an input, and first and second digitally controlled variable capacitors have capacitance values that are controlled by the digital control unit.

Capacitive sensor

A modulator includes an analog integrator including an analog circuit and a quantizer quantizing its output signal. An external input signal is input thereto. A modulator is coupled to the latter stage of the modulator, and includes a quantizer. A probe signal generation circuit injects a probe signal to the modulator. An adaptive filter searches for a transfer function of the modulator by observing an output signal of the quantizer in accordance with a probe signal. Another adaptive filter searches for a transfer function of the modulator by observing an output signal of the quantizer in accordance with the probe signal. A noise cancel circuit cancels a quantization error generated by the quantizer using search results of the adaptive filters.

Analog/digital converter and milimeter wave radar system

A servo control signal is binarized using a digital delta-sigma modulator. The digital delta-sigma modulator forms a feedback loop including a digital adder/subtractor, a digital integrator, and a one-bit quantizer to perform pulse-density modulation of the input servo control signal and output the signal as a binary value of +1 or &#x2212;1.

Acceleration sensor

Provided is a wireless sensor node which includes a sensor to convert a physical quantity into an electric signal to measure the physical quantity, a filter to extract a signal containing a predetermined frequency from the electric signal, a transmitter to transmit data based on the frequency extracted by the filter, a receiver to receive a command to be transmitted from an outside in a wireless manner, and a control unit to control a frequency to be extracted by the filter based on the command.

Wireless sensor terminal, wireless sensor system, and sensor data collection method

Provided is an acceleration sensor capable of realizing a simultaneous operation method of signal detection and servo control in place of a time-division processing method, by an MEMS process in which a manufacturing variation is large. The acceleration sensor is an MEMS capacitive acceleration sensor and has capacitive elements for signal detection and capacitive elements for servo control different from the capacitive elements for the signal detection. A voltage to generate force in a direction reverse to a detection signal of acceleration by the capacitive elements for the signal detection is applied to the capacitive elements for the servo control. Further, the acceleration sensor includes a variable capacity unit compensating for a mismatch of capacity values of the capacitive elements for the servo control at an ASIC side, detects a leak signal due to the mismatch of the capacity values in an ASIC, controls a capacity value of the variable capacity unit, on the basis of a detection result, compensates for an influence of the mismatch of the capacity values, and executes a normal signal detection/servo control simultaneous operation.

There is provided an inertia sensor with low noise and high sensitivity. The inertia sensor captures a physical quantity as a change of electrostatic capacitance and detects the physical quantity based on a servo voltage generating electrostatic force that cancels the change of the electrostatic capacitance. The inertia sensor includes a detection capacitor unit that captures the physical quantity as the change of the electrostatic capacitance and a servo capacitor unit to which the servo voltage is applied. Here, the detection capacitor unit and the servo capacitor unit are connected mechanically through an insulation material.

Inertia sensor with improved detection sensitivity using servo voltage to detect a physical quantity

In a capacitance detection type sensor system, a sensitivity of the sensor system deteriorates because a low frequency noise typified by a 1/f noise cannot be separated in frequency from a signal band. A carrier wave used for capacity detection is modulated with two kinds of frequencies, sampled at a first modulation frequency, subjected to a C/V conversion, and synchronously detected at a second modulation frequency to obtain a signal.

Signal detection method for capacitance detection type sensor, MEMS sensor, and system

A successive approximation type AD converter includes an in-phase voltage detection and supply circuit that supplies an in-phase voltage obtained by impedance voltage division of a first input analog signal and a second input analog signal to a first capacitance DA converter and a second capacitance DA converter. The first capacitance DA converter samples the first input analog signal with reference to the in-phase voltage, and the second capacitance DA converter samples the second input analog signal with reference to the in-phase voltage. After the sampling period ends, a comparator compares the output of the first capacitance DA converter and the output of the second capacitance DA converter, output voltages of the first capacitance DA converter and the second capacitance DA converter are changed by the control signal of a successive approximation logic unit on the basis of a comparison result, and comparison processing is repeated.

Successive approximation type AD converter and sensor device

Growing community of inventors

Tokyo, Japan

Takashi Oshima