Abstract: An information processing apparatus includes: model learning means for self-organizing, on the basis of a state transition model having a state and state transition to be learned by using time series data as data in time series, an internal state from an observation signal obtained by a sensor; and controller learning means for performing learning for allocating a controller, which outputs an action, to each of transitions of a state or each of transition destination states in the state transition model indicating the internal state self-organized by the model learning means.

Abstract: A facial expression recognition system that uses a face detection apparatus realizing efficient learning and high-speed detection processing based on ensemble learning when detecting an area representing a detection target and that is robust against shifts of face position included in images and capable of highly accurate expression recognition, and a learning method for the system, are provided. When learning data to be used by the face detection apparatus by Adaboost, processing to select high-performance weak hypotheses from all weak hypotheses, then generate new weak hypotheses from these high-performance weak hypotheses on the basis of statistical characteristics, and select one weak hypothesis having the highest discrimination performance from these weak hypotheses, is repeated to sequentially generate a weak hypothesis, and a final hypothesis is thus acquired.

Abstract: An object detecting device for detecting an object in a given gradation image. A scaling section generates scaled images by scaling down a gradation image input from an image output section. A scanning section sequentially manipulates the scaled images and cutting out window images from them and a discriminator judges if each window image is an object or not. The discriminator includes a plurality of weak discriminators that are learned in a group by boosting and an adder for making a weighted majority decision from the outputs of the weak discriminators. Each of the weak discriminators outputs an estimate of the likelihood of a window image to be an object or not by using the difference of the luminance values between two pixels. The discriminator suspends the operation of computing estimates for a window image that is judged to be a non-object, using a threshold value that is learned in advance.

Abstract: In an information processing apparatus, such as a robot that discriminates human faces, nodes are hierarchically arranged in a tree structure. Each of the nodes has a number of weak classifiers. Each terminal node learns face images associated with one label. An upper node learns learning samples of all labels learned by lower nodes. When a window image to be classified is input, discrimination is performed sequentially from upper nodes to lower nodes. When it is determined that the window image does not correspond to a human face, discrimination by lower nodes is not performed, and discrimination proceeds to sibling nodes.

Abstract: A learning control apparatus for an autonomous agent including a functional module having a function of multiple inputs and multiple outputs, the function receiving at least one variable and outputting at least one value, includes an estimating unit for estimating a causal relationship of at least one variable, a grouping unit for grouping at least one variable into a variable group in accordance with the estimated causal relationship, a determining for determining a behavior variable corresponding to each of the variable groups, and a layering unit for layering, in accordance with the variable group and the behavior variable, the function corresponding to each variable group, the function receiving the variable grouped into the variable group and outputting the behavior variable.

Abstract: A face image processing apparatus selects feature points and feature for identifying a person through statistical learning. The apparatus includes input means for inputting a face image detected by arbitrary face detection means, face parts detection means for detecting the positions of face parts in several locations from the input face image, face pose estimation means for estimating face pose based on the detected positions of face parts, feature point position correcting means for correcting the position of each feature point used for identifying the person based on the result of estimation of face pose by the face pose estimation means, and face identifying means for identifying the person by calculating a feature of the input face image at each feature point after position correction is performed by the feature point position correcting means and checking the feature against a feature of a registered face.

Abstract: The present invention relates to an image processing system, a learning device and method, and a program which enable easy extraction of feature amounts to be used in a recognition process. Feature points are extracted from a learning-use model image, feature amounts are extracted based on the feature points, and the feature amounts are registered in a learning-use model dictionary registration section 23. Similarly, feature points are extracted from a learning-use input image containing a model object contained in the learning-use model image, feature amounts are extracted based on these feature points, and these feature amounts are compared with the feature amounts registered in a learning-use model registration section 23. A feature amount that has formed a pair the greatest number of times as a result of the comparison is registered in the model dictionary registration section 12 as the feature amount to be used in the recognition process. The present invention is applicable to a robot.

Abstract: A legged mobile robot can calculate the movement amount between a portion of the robot apparatus that had been in contact with a floor up to now and a next portion of the robot apparatus in contact with the floor using kinematics and to switch transformation to a coordinate system serving as an observation reference as a result of the switching between the floor contact portions.

Abstract: A facial expression recognition system that uses a face detection apparatus realizing efficient learning and high-speed detection processing based on ensemble learning when detecting an area representing a detection target and that is robust against shifts of face position included in images and capable of highly accurate expression recognition, and a learning method for the system, are provided. When learning data to be used by the face detection apparatus by Adaboost, processing to select high-performance weak hypotheses from all weak hypotheses, then generate new weak hypotheses from these high-performance weak hypotheses on the basis of statistical characteristics, and select one weak hypothesis having the highest discrimination performance from these weak hypotheses, is repeated to sequentially generate a weak hypothesis, and a final hypothesis is thus acquired.

Abstract: A facial expression recognition system that uses a face detection apparatus realizing efficient learning and high-speed detection processing based on ensemble learning when detecting an area representing a detection target and that is robust against shifts of face position included in images and capable of highly accurate expression recognition, and a learning method for the system, are provided. When learning data to be used by the face detection apparatus by Adaboost, processing to select high-performance weak hypotheses from all weak hypotheses, then generate new weak hypotheses from these high-performance weak hypotheses on the basis of statistical characteristics, and select one weak hypothesis having the highest discrimination performance from these weak hypotheses, is repeated to sequentially generate a weak hypothesis, and a final hypothesis is thus acquired.

Abstract: An object of the present invention is to provide a robot apparatus and a walking control method thereof capable of changing walking control modes in accordance with floor surfaces by discriminating states of the floor surfaces for walking without modifying a step-based walking schedule and capable of providing stable walking even if floor surface states change greatly. A robot apparatus comprises: an action control section 11 to output a walking start instruction; a floor surface discrimination section 12 to discriminate a category for a current floor surface; and a walking control section 13 to compute an adaptive operation amount. The walking control section 13 obtains sensor values of a foot sole sensor and the like from the current floor surface by means of an in-place stepping motion and the like. Based on the sensor value, the walking control section 13 computes the adaptive operation amount as a correction amount from a standard gait model.

Abstract: A gateway object (48) for transmitting and receiving data to and from an object of a robot apparatus (1) is allocated to a radio LAN PC card (41) of the robot apparatus (1), and a gateway object (52) for transmitting and receiving data to and from an object on a personal computer (32) is allocated to a network adapter (31) of a remote system (30). When the radio LAN PC card (41) and the network adapter (31) are connected with each other by radio or wired connection, inter-object communication is carried out between the gateway object (48) of the radio LAN PC card (41) and the gateway object (52) of the network adapter (31), thereby carrying out inter-object communication between the object of the robot apparatus (1) and the object of the personal computer (32). Thus, preparation of a program is facilitated.

Abstract: An obstacle recognition apparatus is provided which can recognize an obstacle by accurately extracting a floor surface. It includes a distance image generator (222) to produce a distance image using a disparity image and homogeneous transform matrix, a plane detector (223) to detect plane parameters on the basis of the distance image from the distance image generator (222), a coordinate transformer (224) to transform the homogeneous transform matrix into a coordinate of a ground-contact plane of a robot apparatus (1), and a floor surface detector (225) to detect a floor surface using the plane parameters from the plane detector (223) and result of coordinate transformation from the coordinate transformer (224) and supply the plane parameters to an obstacle recognition block (226).

Abstract: A facial expression recognition system that uses a face detection apparatus realizing efficient learning and high-speed detection processing based on ensemble learning when detecting an area representing a detection target and that is robust against shifts of face position included in images and capable of highly accurate expression recognition, and a learning method for the system, are provided. When learning data to be used by the face detection apparatus by Adaboost, processing to select high-performance weak hypotheses from all weak hypotheses, then generate new weak hypotheses from these high-performance weak hypotheses on the basis of statistical characteristics, and select one weak hypothesis having the highest discrimination performance from these weak hypotheses, is repeated to sequentially generate a weak hypothesis, and a final hypothesis is thus acquired.

Abstract: A robot includes a face extracting section for extracting features of a face included in an image captured by a CCD camera, and a face recognition section for recognizing the face based on a result of face extraction by the face extracting section. The face extracting section is implemented by Gabor filters that filter images using a plurality of filters that have orientation selectivity and that are associated with different frequency components. The face recognition section is implemented by a support vector machine that maps the result of face recognition to a non-linear space and that obtains a hyperplane that separates in that space to discriminate a face from a non-face. The robot is allowed to recognize a face of a user within a predetermined time under a dynamically changing environment.

Abstract: An image transmission device and method, a transmitting device and method, a receiving device and method, and robot apparatus are capable of effectively transmitting the image data of multiple channels by using the existing systems which are formed on the premise of transmitting and receiving of the image data through single transmission line. At a transmitting side, the image data of multiple channels to be input is multiplexed with switching the channels by frame, and prescribed image information is added to each of the multiplexed image data of each frame. At a receiving side, the image information added to each of the image data for each frame respectively transmitted from the transmitting device are analyzed, and dividing device for dividing for each frame and outputting the multiplexed image data transmitted from the transmitting device to the corresponding channels is provided based on the analysis result.

Abstract: A robot apparatus includes face includes a face tracking module (M2) for tracking a face in an image photographed by a CCD camera, a face detecting module (M1) for detecting face data of the face in the image photographed by the image pickup device, based on the face tracking information by the face tracking module (M2) and a face identification module (M3) for identifying a specified face based on the face data as detected by the face data detecting module (M1).

Abstract: A data processing device for processing time-sequence data includes a data extracting unit operable to extract time-sequence data for a predetermined time unit from time-sequence data; and a processing unit operable to obtain scores for nodes of an SOM configured from multiple nodes provided with a spatial array configuration, the scores showing applicability to time-sequence data for a predetermined time unit thereof, wherein the node with the best score thereof is determined to be the winning node which is the node most applicable; wherein the processing unit obtains scores as to the time-sequence data for one predetermined time unit, regarding a distance-restricted node wherein distance from the winning node as to the time-sequence for a predetermined time unit immediately preceding the time-sequence data of one predetermined time unit is within a predetermined distance; and wherein the distance-restricted node with the best the score is determined to be the winning node thereof.

Abstract: A data processing device for processing time-sequence data includes a learning unit for performing self-organizing learning of a SOM (self-organization map) making up a hierarchical SOM in which a plurality of SOMs are connected so as to construct a hierarchical structure, using, as SOM input data which is input to the SOM, a time-sequence of node information representing a winning node of a lower-order SOM which is at a lower hierarchical level from the SOM.

Abstract: The present invention provides an image processing apparatus to recognize a predetermined model whose surface has a plurality of colors from an input color image that is obtained by capturing an image of a color object whose surface has a plurality of colors. The image processing apparatus includes a detecting unit configured to detect color areas from the input color image, each color area including adjoining pixels of the same color; and a recognizing unit configured to determine whether the color areas on the input color image detected by the detecting unit correspond to parts of the model to which color areas on a reference color image obtained by capturing an image of the model correspond, and determine whether the color object in the input color image is the model on the basis of the determination result.