Denso Corporation

Denso It Laboratory, Inc.

Tokyo Institute of Technology

Ikuro Sato

Yukimasa Tamatsu

Kunihiro Goto

Akihiro Nomura

Hiroshi Doi

Nobuhiro Mizuno

Satoshi Matsuoka

Mitsuru Ambai

Masahiro Iida

Kensuke Yokoi

Ryo Fujisaki

Yosuke Oyama

Kohta Ishikawa

According to one embodiment of the present disclosure, provided is a learning system that updates a parameter for a neural network, the learning system including: a plurality of differential value calculators; and a parameter update module.

Learning system and learning method

A recognition system includes: a sensor processing unit (SPU) that performs sensing to output a sensor value; a task-specific unit (TSU) including an object detection part that performs an object detection task based on the sensor value and a semantic segmentation part that performs a semantic segmentation task based on the sensor value; and a generic-feature extraction part (GEU) including a generic neural network disposed between the sensor processing unit and the task-specific unit, the generic neural network being configured to receive the sensor value as an input to extract a generic feature to be input in common into the object detection part and the semantic segmentation part.

Recognition system, generic-feature extraction unit, and recognition system configuration method

A learning apparatus performs a learning process for a feed-forward multilayer neural network with supervised learning. The network includes an input layer, an output layer, and at least one hidden layer having at least one probing neuron that does not transfer an output to an uppermost layer side of the network. The learning apparatus includes a learning unit and a layer quantity adjusting unit. The learning unit performs a learning process by calculation of a cost derived by a cost function defined in the multilayer neural network using a training data set for supervised learning. The layer quantity adjusting unit removes at least one uppermost layer from the network based on the cost derived by the output from the probing neuron, and sets, as the output layer, the probing neuron in the uppermost layer of the remaining layers.

Learning apparatus, learning program, and learning method

A vehicle detection apparatus detects an object based on an image captured from a vehicle. In the vehicle detection apparatus, a camera is mounted in the vehicle. A search region determining unit determines a region including a road surface in the image to be a search region. A cost minimizing unit divides the search region into two, an upper region and a lower region, by a boundary line, determines corresponding points in a plurality of images captured by the camera at different time points by applying an optical flow model having a fixed magnification factor to the upper region and an optical flow model having a planar constraint condition to the lower region, and determines a boundary line that minimizes cost related to a difference between pixel values of the corresponding points. A vehicle presence determining unit determines presence of a forward vehicle based on the boundary line.

Object detection apparatus, object detection method, and program

An apparatus for detecting a moving object is provided. In the apparels, a moving object, such as a pedestrian, is imaged repeatedly. As a dictionary, image patterns indicative of features of the moving object are stored in a storage in advance. Feature points indicating a position of an object in the images are extracted based on the images. An optical flow of the feature points is calculated based on the features points. The feature points are grouped and a reference rectangle encompassing the grouped feature points is set, based on the optical flow. An identification region encompassing a region showing the moving object is set, the identification region encompassing the reference rectangle. The moving object is identified in the identification region, using the dictionaries. The region of the moving object is specified, based on identified results and an image region having the highest degree of match with the dictionaries.

Method and apparatus for detecting moving objects

The moving object recognition system includes: a camera that is installed in a vehicle and captures continuous single-view images; a moving object detecting unit that detects a moving object from the images captured by the camera; a relative approach angle estimating unit that estimates the relative approach angle of the moving object detected by the moving object detecting unit with respect to the camera; a collision risk calculating unit that calculates the risk of the moving object colliding with the vehicle, based on the relationship between the relative approach angle and the moving object direction from the camera toward the moving object; and a reporting unit that reports a danger to the driver of the vehicle in accordance with the risk calculated by the collision risk calculating unit.

Moving object recognition systems, moving object recognition programs, and moving object recognition methods

A travel trace storage apparatus includes a location detection device, a positioning trace generation device, a movement distance detection device, a travel direction detection device, a dead reckoning trace generation device for generating a dead reckoning trace, in which each vector determined by a vehicle movement distance and a vehicle travel direction is chronologically arranged, a correction positioning trace generation device for generating a correction positioning trace obtained by removing a location distant from the dead reckoning trace by a predetermined distance or more, a correction dead reckoning trace generation device for generating a correction dead reckoning trace obtained by correcting the dead reckoning trace, an absolute trace generation device for generating an absolute trace obtained by synthesizing the correction positioning trace and the correction dead reckoning trace, an absolute trace memory for storing the absolute trace.

Growing community of inventors

Yokohama, Japan

Ikuro Sato