Matsushita Electric Industrial Co., Ltd.

Panasonic Corporation

Panasonic Intellectual Property Corporation of America

Panasonic Intellectual Property Management Co., Ltd.

Matsushita Electrical Industrial Co., Ltd.

Panasonic Corporation of North America

Luca Rigazio

Jean-Claude Junqua

David Kryze

Philippe Rene Morin

Patrick Nguyen

Sotaro Tsukizawa

Robert C Boman

Takahiro Nishi

Tadamasa Toma

Kiyofumi Abe

Ryuichi Kanoh

Alec Hodgkinson

Tiffany Yun

Min Young Kim

Masaki Yamauchi

Kazuki Kozuka

Nobuyuki Kunieda

Peter Veprek

Denis A Gudovskiy

Keiko Morii

Junnosuke Kurihara

Stefano Alletto

Zia Syed

Younes Souilmi

Christophe Cerisara

Jae Jung

Yasunori Ishii

Ryota Fujimura

Ted H Applebaum

Stephen Reiger Myers

Brian A Hanson

Michael Galler

Ganymed Stanek

Rathinavelu Chengalvarayan

Casey Joseph Carlin

Alexander Joseph Romelfanger

Brice Tsakam

Gregory Senay

Chaojun Liu

Ambroise Mutel

A learning method includes an input process to input, to a neural network, a first image and a second image that constitute a moving image and that are temporally adjacent to each other, where the second image is an image subsequent to the first image with a predetermined time interval therebetween, a learning process to cause the neural network to use the first image and the second image and learn to output a transformation matrix applied to all pixels of the first image and used to convert the first image into the second image, and an output process to output, as a result of estimation of motion between the first image and the second image, a motion amount image generated from the transformation matrix and representing an amount of motion of each of the pixels of the first image that continues until the predetermined time interval elapses.

Learning method and recording medium

Executing a deep neural network by obtaining, during deep neural network inference, a binary intermediate feature map in binary representation by converting a floating-point or fixed-point intermediate feature map into a binary vector using a first transformation module; generating a compressed feature map by compressing the binary intermediate feature map using a nonlinear dimensionality reduction layer; storing the compressed feature map into memory; reconstructing the binary intermediate feature map by decompressing the compressed feature map read from the memory using a reconstruction layer corresponding to the nonlinear dimensionality reduction layer; and converting the reconstructed binary intermediate feature map into a floating-point or fixed-point intermediate feature map using a second transformation module.

Execution method, execution device, learning method, learning device, and recording medium for deep neural network

The encoder includes processing circuitry, and memory. Using the memory, the processing circuitry: generates a predicted image of an input image that is a current image to be encoded, based on generated data output from a generator network in response to a reference image being input to the generator network, the generator network being a neural network; calculates a prediction error by subtracting the predicted image from the input image; and generates an encoded image by at least transforming the prediction error.

Encoder, decoder, encoding method, and decoding method

An encoder includes circuitry and memory. Using the memory, the circuitry: encodes an original image and decodes the original image encoded, to generate a first bitstream and a local decoded image; encodes supplemental information and decodes the encoded supplemental information, to generate a second bitstream and local decoded supplemental information; inputs data based on the local decoded image and the local decoded supplemental information to a post processing network which is a neural network, to cause a reconstructed image to be output from the post processing network, the reconstructed image corresponding to the original image and being to be used to encode a following original image which follows the original image; and concatenates the first bitstream and the second bitstream to generate a concatenated bitstream.

An information processing method performed using a computer includes: obtaining first sensor data (SD) that is SD of a scene and includes noise; inputting the first SD to a single converter, and obtaining second SD outputted from the single converter as a result of denoising performed on the first SD by the single converter; obtaining third SD that is SD of a scene identical or corresponding to the scene, does not include the noise, and is different from the second SD; obtaining feature information of the second SD and feature information of the third SD, based on the second SD and the third SD, respectively; and training the single converter by machine learning using the second SD and the feature information of the second SD as converted data, and using the third SD and the feature information of the third SD as reference data corresponding to the converted data.

Information processing method, information processing apparatus, and recording medium

An image processor includes memory and circuitry. The circuitry performs processing of approximating a decompressed image to an original image by using a neural network model trained to approximate the decompressed image to the original image. The decompressed image is obtained as a result of compression of the original image and decompression of the compressed image. The neural network model includes one or more convolutional blocks, and includes one or more residual blocks. Each of the one or more convolutional blocks is a processing block including a convolutional layer. Each of the one or more residual blocks includes a convolutional group including at least one of the one or more convolutional blocks, inputs data which is input to the residual block to the convolutional group included in the residual block, and adds the data input to the residual block to data to be output from the convolutional group.

Image processor and image processing method

An information processing method includes: inputting an input tensor indicating data to a processor having a memory; causing the processor to perform, after elements of the input tensor are subjected to precomputation for conversion into a power-of-two format and are stored in the memory, convolution operation processing with only addition and shift operations by using the precomputed elements of the input tensor stored in the memory and weight tensors that are pre-converted into the power-of-two format in accordance with a predetermined algorithm, that are stored in the memory, and that indicate weights having a possibility of being used for a convolution operation; and outputting, as an output tensor, the elements of the input tensor on which the convolution operation processing is performed.

Information processing method, information processing apparatus, and computer-readable recording medium

Inputting an image to a neural network, performing convolution on a current frame included in the image to calculate a current feature map, which is a feature map at a present time, combining a past feature map, which is obtained by performing convolution on a past frame included in the image, and the current feature map, estimating an object candidate area using the combined past feature map and current feature map, estimating positional information and identification information regarding the one or more objects included in the current frame using the combined past feature map and current feature map and the estimated object candidate area, and outputting the positional information and the identification information regarding the one or more objects included in the current frame of the image estimated in the estimating as object detection results are included.

Method for processing information, information processing apparatus, and non-transitory computer-readable recording medium

A determination method for determining the structure of a convolutional neural network includes acquiring N filters having the weights trained using a training image group as the initial values, where N is a natural number greater than or equal to 1, and increasing the number of the filters from N to M, where M is a natural number greater than or equal to 2 and is greater than N, by adding a filter obtained by performing a transformation used in image processing fields on at least one of the N filters.

Determination method and recording medium

In an image recognition method executed by a computer of an image recognizer using a convolutional neural network, the convolutional neural network is a first convolutional neural network in which a fully connected layer is changed to a convolutional layer, and the method includes controlling a first convolutional neural network to acquire an input image, controlling the first convolutional neural network to estimate a center area of a recognition target in the acquired input image and to output a value indicating the estimated center area as a location of the recognition target in the input image.

Image recognition method

An aircraft having a fixed wing is operative to perform vertical takeoff and landing while positioned in a nose-down orientation. The aircraft has a fixed wing having a leading edge and a trailing edge; a propulsion system operative to selectively provide forward propulsion and rearward propulsion; and a controller operative to control operation of the propulsion system. The propulsion system provides rearward propulsion during takeoff of the aircraft to move the aircraft in a direction of the trailing edge of the fixed wing, and provides forward propulsion during flight of the aircraft to move the aircraft in a direction of the leading edge of the fixed wing. The aircraft maintains the wing substantially vertical with the trailing edge facing upwards during takeoff, and transitions to having the wing substantially horizontal during flight. A vertical landing procedure is also provided.

Aircraft system and method for vertical takeoff and landing

A method for remote control wherein a first mobile device is remotely controls a second mobile device connected to the first mobile device via an audio/data transmission network. The method includes receiving a request from an user of the first mobile device on the first mobile device, performing audio transmission from the first mobile device to the second mobile device, and transmitting data for a displayed screen from the first device to the second device via the data transmission network. The received data for the displayed screen is displayed on the second mobile device, operation content is received from an user operating the displayed screen on the second device, and the operation content is transmitted from the second device to the first device via the data transmission network, so that a terminal feature on the first device is operable based on the operation content received from the second device.

Mobile device remotely controlled by other mobile device through a network

A non-contact gesture sensor is mounted within a vehicle for vehicle occupants to enter control commands by using hand gestures. The effects of vehicle motion and vibration are stabilized by an electronic circuit that includes an inertial motion sensor (IMU) in rigidly fixed relation to the gesture sensor. An adaptive filter processes the gesture sensor signal and the IMU sensor signal by modeling the arm and hand as a semi-rigid articulated body using a transfer function that relates accelerations measured by the IMU with vehicle motion-induced accelerations of the hand. The filter calculates a noise-reduced gesture signal by subtracting out the motion-induced accelerations and measurement noise. The filter also outputs a confidence measure that controls a threshold circuit that inhibits use of the filtered gesture signal when confidence in the filter's system estimation is low.

3D gesture stabilization for robust input control in mobile environments

An apparatus for communicating with a target device includes: a sensing portion for sensing points of user contact with the apparatus and user gestures; a transmitting device for sending signals representative of user commands to the target device; a controller; and a memory including instructions for configuring the controller to perform a self-orientation process to determine a forward direction of a plane of operation for defining the user gestures.

Apparatus for remotely controlling another apparatus and having self-orientating capability

Growing community of inventors

San Jose, CA, United States of America

Luca Rigazio