Nec Corporation

Nec Solution Innovators, Ltd.

Tetsuaki Suzuki

Hiroyoshi Miyano

Ryoma Oami

Akira Inoue

Yusuke Takahashi

Takashi Shibata

Takuya Ogawa

Kenshirou Katsura

Taizou Matsunaga

A learning device makes an object detection device learn how to detect an object from an input image. A feature extraction unit performs feature extraction from input images including real images and pseudo images to generate feature maps, and the object detection unit detects objects included in the input images based on the feature maps. The domain identification unit identifies the domains forming the input images and generates domain identifiability information. Then, the feature extraction unit and the object detection unit learn common features that do not depend on the difference in domains, based on the domain identifiability information.

Learning device, object detection device, learning method, and recording medium

An information processing apparatus () generates likelihood data for each of a plurality of partial regions () in image data (). The likelihood data are data being associated with a position and a size on the image data () and indicating a likelihood that a target object exists in an image region at the position with the size. The information processing apparatus () computes a distribution (probability hypothesis density: PHD) of an existence likelihood of a target object with respect to a position and a size by computing the total sum of likelihood data each piece of which is generated for each partial region (). The information processing apparatus () extracts, from the PHD, partial distributions each of which relates to one target object. For each extracted partial distribution, the information processing apparatus () outputs a position and a size of a target object represented by the partial distribution, based on a statistic of the partial distribution.

Information processing device, control method, and program

An information processing apparatus () detects a left-behind object from video data (). In addition, the information processing apparatus () estimates a time-point at which the left-behind object is left behind. Furthermore, the information processing apparatus () acquires video data near an estimated left-behind time-point (estimated left-behind time-point), controls the acquired video data based on the estimated left-behind time-point, and then presents at least a part of the acquired video data to a user.

Information processing apparatus, control method, and program

A detection system which detects a mobile object includes: an image input unit for receiving an input of a plurality of image frames having different capturing times; an inter-background model distance calculation unit for calculating differences between a first background model generated based on an image frame at the time of processing, a second background model in which an influence of an image frame at the time of processing is smaller than that of the first background model, and a third background model in which an influence of an image frame at the time of processing is smaller than that of the second background model; and a mobile object detection unit for detecting a first region in an image frame.

Detection system, detection method, and program storage medium

Provided is a technology for sensing anomalous tide level fluctuations to be used to monitor a tsunami, in which an estimated value of a sea surface fluctuation is obtained by conducting statistical processing or testing processing for a physical phenomenon of the tsunami displayed in image information. An anomalous tide level fluctuation sensing device according to this invention is configured to: detect a position of an object or a horizon, which fluctuates in association with a tide level, from within a video; and detect that the position fluctuates in a time cycle different from a time cycle of a tide or an ocean wave.

Anomalous tide level fluctuation sensing device, anomalous tide level fluctuation sensing method, and anomalous tide level fluctuation sensing program

A masquerading detection system includes: an imaging unit () that obtains a first image by imaging an inspection object () from a first angle, and a second image by imaging the inspection object from a second angle which is different from the first angle; a unit () that detects first feature points from the first image, obtains first feature point coordinates of the detected feature points, detects second feature points from the second image, and obtains second feature point coordinates of the detected feature points; a unit () that obtains transformed coordinates by performing a plane projective transformation for the second feature point coordinates from the second image to the first image; and a unit () that determines that masquerading has been attempted when the difference between the transformed coordinates and the corresponding first feature point coordinates is equal to or smaller than a predetermined value.

Masquerading detection system, masquerading detection method, and computer-readable storage medium

An image processing system includes a local area selecting section configured to select a local area as at least one correction target from an input image, the local area including at least one pixel; a correction amount calculating section configured to calculate a gradation correction amount for the local area as the correction target; and a local gradation correcting section configured to perform a gradation correction to correct a gradation value of the local area based on the gradation correction amount to generate an image with a local gradation correction. Also, the correction amount calculating section includes a peripheral area gradation value calculating section configured to calculate a gradation value of a peripheral area of the local area; and a local area correction amount converting section configured to calculate the gradation correction amount by using the calculated gradation value of the peripheral area.

Image correction processing system and image correction processing method

In the video processing device, a correction amount update determining unit determines whether to update a correction amount based on an input image obtained from an image input unit and when a cut point is detected or when the number of frames in a number of frames storing unit exceeds a fixed value, determines that update is required, and at this time, a correction amount obtaining unit obtains a new correction amount based on the input image. Then, if no cut point is detected, an amount of change of a correction amount in time is limited and the obtained result is recorded in a correction amount storing unit, and an image correcting unit conducts quality improving correction processing with respect to the input image based on a correction amount recorded in the correction amount storing unit and the image corrected is sent to an image output unit.

Growing community of inventors

Tokyo, Japan

Tetsuaki Suzuki