An image processing apparatus stores model information representing a subject model belonging to a specific category, detects the subject from an input image by referring to the model information, determines a region for which an image correction is to be performed within a region occupied by the detected subject in the input image, stores, for a local region of the image, a plurality of correction data sets representing correspondence between a feature vector representing a feature before correction and a feature vector representing a feature after correction, selects at least one of the correction data sets to be used to correct a local region included in the region determined to undergo the image correction, and corrects the region determined to undergo the image correction using the selected correction data sets.

Image processing apparatus, method thereof, program, and image capturing apparatus

To provide a training data generating device capable of easily generating a large amount of training data used for machine-learning a dictionary of a discriminator for recognizing a crowd state. A person state determination unit 72 determines a person state of a crowd according to a people state control designation as designation information on a person state of people and an individual person state control designation as designation information on a state of an individual person in the people. A crowd state image synthesis unit 73 generates a crowd state image as an image in which a person image corresponding to the person state determined by the person state determination unit 72 is synthesized with an image at a predetermined size acquired by a background extraction unit 71 , and specifies a training label for the crowd state image.

Training data generating device, method, and program, and crowd state recognition device, method, and program

The invention provides a gesture recognizing method and a device of a ball game and a gesture auxiliary device. The method comprises: acquiring motion parameters of each sampling time corresponding to a segment of gestures; recognizing strategy extracting characteristic points according to the preset characteristic points by utilizing the acquired motion parameters, wherein the characteristic point recognition strategies at least comprise the following three types of recognition strategies of the characteristic points: the characteristic point corresponding with boosting tracks initially, thecharacteristic point corresponding with the highest point of the gestures, and the characteristic point corresponding with the ball hitting time; and determining whether the extracted characteristic points satisfy the characteristic point requirement of the preset ball game type, and recognizing that the segment of gestures belong to the preset ball game type if yes. According to the invention, the recognition gesture motions from the gesture parameters can be realized.

Gesture recognizing method and device of ball game and gesture auxiliary device

An image taking system including: a lens apparatus; an image pickup apparatus; an operation angle detection unit detecting an operation angle; a direction storage unit storing an object direction relative to the lens apparatus; an angle-of-field calculation unit calculating an image taking angle of field based on zoom and focus positions; a ranging area setting unit calculating a position of at least one object in a screen based on the operation angle detected by the operation angle detection unit, the object direction stored in the direction storage unit, and the image taking angle of field calculated by the angle-of-field calculation unit, to set a ranging area at the position of the at least one object; an object distance calculation unit calculating an object distance in the ranging area; and an output image generation unit generating an output image and information based on the object distance.

Image taking system and lens apparatus

An article pickup device configured so as to select a first and second three-dimensional points present in the vicinity of each other based on position information of the plurality of three-dimensional points acquired by a three-dimensional measurement instrument and image data acquired by a camera, acquire an image gradient information in a partial image region including points on an image corresponding to these three-dimensional points, judge whether the first and second three-dimensional points are present on the same article based on a position information of the three-dimensional points and the image gradient information, and add the first and second three-dimensional points to the same connected set when it is judged that the first and second three-dimensional points are present on the same article.

Apparatus and method for picking up article disposed in three-dimensional space using robot

PROBLEM TO BE SOLVED: To provide a personal action decision device, capable of deciding the action of a person included in a crowded scene by means of video processing only. SOLUTION: A personal action decision device 1 includes: a personal area detection means 10 for detecting one or more personal areas included in a video image at predetermined frame intervals by machine learning; a personal track generation means 20 for calculating a feature amount for each personal area, for deciding a personal area, having a resembling feature amount of the personal area in a plurality of frame images, to be the personal area of an identical person, and for generating a personal track by connecting the positions of the centers of gravity in the personal areas of the identical person; and a personal action decision means 30 for deciding that the person acts in conformity to an action condition, if the feature amount of the personal action satisfies the action condition by calculating the feature amount for each personal track and by deciding whether the feature amount of the personal track satisfies the action condition. COPYRIGHT: (C)2011,JPO&INPIT

Device and program for deciding personal action

PROBLEM TO BE SOLVED: To provide a person motion detection device that detects a motion of a person from video photographed by a camera.SOLUTION: A person motion detection device 1 includes: feature point track information generation means 10 of generating a track of feature points as feature point track information for each frame image of video; feature quantity extraction means 20 of generating a track feature quantity by accumulating a direction and a magnitude of a movement vector at a feature point for each range width obtained by dividing a possible range thereof by a predetermined number; learning data storage means 40 of clustering a plurality of track feature quantities into a predetermined number of clusters, and finding and storing, as learning data, a distribution obtained by accumulating a plurality of track feature quantities constituting a known motion by the clusters; and operation identification means 30 of generating a distribution obtained by accumulating clusters that the track feature quantities belong to from a plurality of track feature quantities within a predetermined time section, and comparing the distribution with the learning data to identify the motion of the person.

Person motion detection device and program thereof

PROBLEM TO BE SOLVED: To construct a discriminator for highly accurately detecting a detection target such as a specific object or event from video on the basis of learning using diverse learning data.SOLUTION: A learning device 1 extracts a video section corresponding to a keyword showing a detection target of a discriminator to be constructed or a keyword related to the keyword, by using a text showing voice of input video data; and constructs the discriminator by using the extracted video section as learning data of a positive sample. When the constructed discriminator has insufficient accuracy, the learning device 1 repeats processing of constructing the discriminator by adding and modifying learning data.In order to generate diverse learning data in adding learning data, the learning device 1 mixes a predetermined ratio of video data of a video section selected randomly, video section having high audio and visual similarity to the positive sample, and video section detected by a discriminator that has completed learning corresponding to a semantically similar keyword, of video sections in the input video data, with the present learning data as positive examples.

Learning device and program

PROBLEM TO BE SOLVED: To provide equipment for estimating a camera parameter which is capable of estimating the camera parameter by using an arbitrary fixed or moving object as a landmark. SOLUTION: The camera parameter estimating equipment 1 has a first landmark extracting means 10 which extracts the coordinates of the landmark as those of a reference image from a first image, a second landmark extracting means 11 which extracts the coordinates of the landmark as those of an observation image from a second image, a position estimating means 13 which estimates the three-dimensional coordinates of the landmark, based on a known camera parameter which is the camera parameter of a first camera, a landmark mapping means 12 which performs projection conversion of the three-dimensional coordinates into the second image so as to map the landmark thereon, and a parameter estimating means 14 which calculates the camera parameter of a second camera, based on the three-dimensional coordinates estimated by the position estimating means 13. COPYRIGHT: (C)2009,JPO&INPIT

Equipment and program for estimating camera parameter

PROBLEM TO BE SOLVED: To provide a camera controller and a camera control program for controlling the operation of a camera such that a plurality of photography purposes can be processed by a single camera. SOLUTION: The camera controller 1 for controlling the operation of a camera fixed to a drive mechanism using a measurement from a sensor 2 for detecting the photography state of the camera comprises a means 3 for setting a plurality of gaze regions and the importance of each gaze region, a means 5 for integrating gaze regions outputted from the gaze region setting means 3 and outputting an integrated gaze region, and a means 7 for controlling the camera to photograph the integrated gaze region. COPYRIGHT: (C)2007,JPO&INPIT

真人藤井

Papers

Device and program for deciding personal action

Person motion detection device and program thereof

Learning device and program

Equipment and program for estimating camera parameter

Camera controller and control program

真人 藤井

Papers

Device and program for deciding personal action

Person motion detection device and program thereof

Learning device and program

Equipment and program for estimating camera parameter

Camera controller and control program

真人藤井