Nec Corporation

Gaku Nakano

Asuka Ishii

Katsuhiko Takahashi

Tetsuo Inoshita

Yuichi Nakatani

Masahiko Ohta

Yuzo Senda

Jun Takada

Kazuhito Murata

Kenichi Ishii

Shoji Nishimura

Shinya Yamasaki

Shin Tominaga

Shigeki Shinoda

Masumi Ishikawa

Shota Yamamoto

Kana Takizawa

Narumitsu Notomi

Aki Nakamura

Eishi Arita

Yoshiyuki Satou

Youtarou Noda

Yoshitaka Higeta

Takashi Shibata

Masato Tsukada

Hiroshi Imai

Yoshiaki Sato

Eiji Kaneko

Atsushi Hatabu

Daisuke Ikefuji

Yosuke Kimura

Nana Jumonji

Noriyoshi Hiroi

Chisato Sugawara

Zhen Wang

Subhajit Chaudhury

Daisuke Iketuji

In an object detection device, the plurality of object detection units output a score indicating a probability that a predetermined object exists for each partial region set with respect to inputted image data. The weight computation unit uses weight computation parameters to compute a weight for each of the plurality of object detection units on a basis of the image data and outputs of the plurality of object detection units, the weight being used when the scores outputted by the plurality of object detection units are merged. The merging unit merges the scores outputted by the plurality of object detection units for each partial region according to the weights computed by the weight computation unit. The first loss computation unit computes a difference between a ground truth label of the image data and the score merged by the merging unit as a first loss. Then, the first parameter correction unit corrects the weight computation parameters so as to reduce the first loss.

Object detection device, learned model generation method, and recording medium

An image processing apparatus () includes an image processing unit () and a risk information generation unit (). The image processing unit () acquires and processes an image generated by an image capture apparatus (), that is, an image including a plurality of persons. As an example, the image processing unit () sets a person being at least part of the plurality of persons as a reference person and computes a distance (first distance) between the reference person and the closest person to the reference person. By using the first distance, the risk information generation unit () generates infection risk information in a target region being an image capture target of the image capture apparatus ().

Image processing apparatus, image processing method, and non-transitory computer-readable medium

A projection transformation parameter for guaranteeing a deformation to a convex quadrilateral can be calculated even when one or more of correspondence points are errors. A projection transformation parameter estimation device according to an embodiment includes a correspondence point detection unit () configured to detect information about a correspondence between two pieces of input data, a quadratic surface calculation unit () configured to fit a quadratic surface to the information about the correspondence for one or both of the two pieces of the input data, and a projection transformation matrix calculation unit () configured to calculate a projection transformation parameter between the two pieces of the input data by using the information about the correspondence with a constraint condition specifying that a property of the quadratic surface is maintained even after projection transformation.

Projection transformation parameter estimation device, projection transformation parameter estimation method, and computer readable medium storing program thereof

A state determination device according to the present invention includes: a memory; and at least one processor coupled to the memory. The processor performs operations. The operations including: combining output from a plurality of determination models for an input image of a road, the plurality of determination models each learned using training data in which at least one of a state of a moving object mounting an imaging device that acquires an image of the road, a state of the road, and an external environment is different.

State determination device, state determination method and recording medium

The information processing device performs distillation learning of a student model using unknown data which a teacher model has not learned. The label distribution determination unit outputs an arbitrary label for the unknown data. The data generation unit outputs new generated data using an arbitrary label and unknown data as inputs. The distillation learning part performs distillation learning of the student model using the teacher model and using the generated data as an input.

Information processing device, learning method, and recording medium

A photographing guide device includes a detection means and an output means. The detection means compares a candidate image of a structure captured from a capturing candidate position in a capturing candidate direction with a registered image of the structure captured from a given capturing position in a given capturing direction and stored in advance, thereby detecting a positional difference between the capturing candidate position and the given capturing position. The output means outputs information indicating the detected positional difference.

Photographing guide device

In an object detection device, a plurality of object detection units output a score indicating probability that a predetermined object exists, for each partial region set to image data inputted. The weight computation unit computes weights for merging the scores outputted by the plurality of object detection units, using weight calculation parameters, based on the image data. The merging unit merges the scores outputted by the plurality of object detection units, for each partial region, with the weights computed by the weight computation unit. The target model object detection unit configured to output a score indicating probability that the predetermined object exists, for each partial region set to the image data. The first loss computation unit computes a first loss indicating a difference of the score of the target model object detection unit from a ground truth label of the image data and the score merged by the merging unit. The first parameter correction unit corrects parameters of the target model object detection unit to reduce the first loss.

Object detection device, learning method, and recording medium

An image processing apparatus includes at least one memory configured to store instructions, and at least one processor configured to execute the instructions to process an image of a target region, and thereby compute a proximity index being an index relating to a proximity state of a plurality of persons captured in the image, and cause a predetermined apparatus to execute predetermined control, when the proximity index satisfies a criterion.

Image processing apparatus, image processing method, and non-transitory computer-readable storage medium

An apparatus includes an acquisition means for acquiring the displacement quantity in a time-series manner, the displacement quantity being generated at a measurement part of a structure by the weight of a vehicle that travels on the structure, a detection means for detecting the position and the clock time of the vehicle that travels a pre-passage area of the measurement part, an estimation means for estimating the arrival time that the vehicle arrives at the measurement part, from the position of the measurement part and the position and the clock time of the vehicle, and a control means for controlling the acquisition means on the basis of the estimated arrival time.

Displacement measurement apparatus for structure

In the object detection device, the plurality of object detection units output a score indicating a probability that a predetermined object exists, for each partial region set with respect to image data inputted. The weight computation unit computes a weight for each of the plurality of object detection units by using weight computation parameters and based on the image data. The weights are used when the scores outputted by the plurality of object detection units are merged. The weight redistribution unit changes the weight for a predetermined object detection unit, among the weights computed by the weight computation unit, to 0 and output the weights. The merging unit merges the scores outputted by the plurality of object detection units for each of the partial regions, by using the weights computed by the weight computation unit and including the weight changed by the weight redistribution unit. The loss computation unit computes a difference between a ground truth label of the image data and the merged score merged by the merging unit as a loss. Then, the parameter correction unit corrects the weight computation parameters so as to reduce the loss.

In a camera calibration apparatus (), an external parameter calculation unit () calculates a rotation vector and a rotation matrix using the normalized start point coordinates, the normalized end point coordinates, and an 'evaluation function' obtained by the normalized coordinate transformation unit () for each normal vector in the image plane and then outputs the calculated translation vector and rotation matrix. The normal vectors in the image plane respectively correspond to a plurality of normal vectors in a world coordinate space with respect to a reference plane in the world coordinate space. The evaluation function is for overdetermining a rotation parameter around a normal line with respect to the above reference plane in the world coordinate space.

Camera parameter calculation apparatus, camera parameter calculation method, and non-transitory computer readable medium storing program

A camera parameter estimation apparatus: takes three sets of three-dimensional coordinates pertaining to an object and two-dimensional coordinates corresponding to the three-dimensional coordinates, and transforms a coordinate system of the three-dimensional coordinates from a world coordinate system to a local coordinate system; calculates a linear transformation matrix based on a projection transformation expression from the transformed three-dimensional coordinates to the two-dimensional coordinates, calculates a coefficient of a quartic equation pertaining to any one of depths from a camera center to each three-dimensional coordinate, and calculates each depth; calculates the rotation matrix in the local coordinate system using each depth and the linear transformation matrix; calculates a translation vector in the local coordinate system from each depth based on the projection transformation expression; and calculates a rotation matrix and a translation vector in the world coordinate system by performing an inverse transform of the rotation matrix and the translation vector.

Camera parameter estimation apparatus, camera parameter estimation method, and computer-readable recording medium

A camera parameter estimation apparatusfor estimating geometric parameters of a camera that has shot an image of an object and a lens distortion parameter of a lens distortion model represented by a single unknown. The camera parameter estimation apparatusincludes: a data obtaining unitthat obtains image corresponding points relating to the object and an approximation order for polynomial approximation of the lens distortion model; and a parameter estimation unitthat estimates, based on the image corresponding points and the approximation order, the geometric parameter and the lens distortion parameter that minimize an error function representing a specific transformation of the image corresponding points.

In a camera calibration apparatus (), an acquisition unit () acquires a first normal vector in an image plane and a second normal vector in the image plane respectively corresponding to a first normal vector in a world coordinate space and a second normal vector in the world coordinate space which are normal vectors with respect to a reference plane in the world coordinate space and have the same length. A projective depth calculation unit () calculates a projective depth vector having, as vector elements, four projective depths respectively corresponding to a start point and an end point of the first normal vector in the image plane and a start point and a end point of the second normal vector in the image plane.

Camera calibration apparatus, camera calibration method, and nontransitory computer readable medium storing program

An apparatus includes an acquisition means for acquiring displacement quantity in a time-series manner, the displacement quantity being generated at a measurement part of a structure by the weight of a vehicle that travels on the structure, a detection means for detecting the size of the vehicle that passes through the structure and detecting the type of the vehicle from the size, and a control means for controlling the acquisition means on the basis of the detected type of the vehicle.

Growing community of inventors

Tokyo, Japan

Gaku Nakano