Denso Corporation

Nippondenso Co., Ltd.

Mikio Sasaki

Katsushi Asami

Fumihiko Murase

Kazuoki Matsugatani

Kenzo Ito

Satoshi Hirose

Hideaki Namba

Ryuichi Suzuki

Tetsuya Kominami

Yukihiro Kanayama

Hideki Saitou

Noriaki Takemoto

An estimation apparatus of an object appearance frequency is provided. The apparatus estimates an appearance frequency of objects, such as pedestrians, in a predetermined estimation area. The apparatus calculates a matrix Fby searching an appearance frequency data in the past. In detail, an estimated result that is an output of an estimating module is expressed as a vector. Objects to be estimated are classified into a total of 12 kinds, such as a 'man, woman, child, bike, unknown, dog' and a 'right, left'. Feature vector of appearance frequency of pedestrians, i.e., objective variables of estimation, is expressed by 12th dimension vector space. Moreover, status information is used as explaining variables, which explain the feature vectors when a feature vector occurs. The regression relationship of the feature vector with respect to the status information vector expressed in 28th dimension is solved by the linear least squares method.

Object appearance frequency estimating apparatus

A moving object detection apparatus generates frame difference image data each time a frame data is captured, based on the captured frame data and previous frame data, and such frame difference image data is divided into pixel blocks. Subsequently, for each of the pixel blocks a discrete cosine transformation (DCT), a two-dimensional DCT coefficient is calculated, and such two-dimensional DCT coefficients are accumulated and stored. The value of each element of the two-dimensional DCT coefficient is arranged to form a characteristic vector, and, for each of the pixel blocks at the same position of the frame difference image data, the characteristic vector is generated and then such characteristic vector is arranged to form a time-series vector. The time-series vector derived from moving-object-capturing pixel blocks is used to calculate a principal component vector and a principal component score.

Moving object detection apparatus

An image recognition apparatus includes an image recognition unit, an evaluation value calculation unit, and a motion extraction unit. The image recognition unit uses motion vectors that are generated in the course of coding image data into MPEG format data or in the course of decoding the MPEG coded data by the evaluation value calculation unit and the motion extraction unit as well as two dimensional DCT coefficients and encode information such as picture types and block types for generating the evaluation values that represent feature of the image. The apparatus further includes an update unit for recognizing the object in the image based on the determination rules for a unit of macro block. The apparatus can thus accurately detect the motion of the object based on the evaluation values derived from DCT coefficients even when generation of the motion vectors is difficult.

Apparatus for image recognition

A color information creating part calculates the average color of captured image data in units of macro blocks, and determines to which color index the average color of each macro block corresponds. Color arrangement information formed by associating color information with the macro blocks is stored in a color index memory. A histogram creating part creates color histograms representative of the distribution of macro blocks added with color information corresponding to aimed color indexes. Based on the color arrangement information and the color histograms, a color application execution part recognizes objects, surroundings, or the situation of a driver's own vehicle without performing area splitting (shape acquisition) of an image.

Environment recognition device

When a start key is operated, an inferring process of estimating a demand of a user is executed on the basis of preset situation data, a user profile, and situation data manually input via a situation setting key. Based on the inference result, a genre list and a contents list are reconstructed so that genres and contents items are arranged in order of the degree of a demand of the user. The top three genres extracted from the reconstructed genre list are associated with three selection keys, and the names of the associated genres or labels of the genres are displayed in genre name display parts. It enables the user to easily and instantaneously select one of contents items to be processed.

Interface device, inferring system, and visual expression method

The system for performing interactive dialog of the present invention recognizes a question from a user and outputs an answer by a synthesized voice. The system includes; a selection unit for selecting the answer from a database; an evaluation unit for evaluating a dialog between the user and computer and determining whether or not to continue the dialog. The evaluation unit may evaluate a dialog consistency, or dialog circumstance. Further, the selection unit selects and combines on the basis of the determination result the answer with one of a plurality of dialog sentences. The system may further comprises a learning unit for storing a novel answer unknown to the computer, by interrogating the user about the novel answer and further storing the interrogation scenario.

System for performing interactive dialog

A vector retrieval/generation/correction unit of a user terminal generates, corrects, and optimizes an inquiry vector on the basis of a vector profile, an inquiry history, a user model, and a user profile. On the other hand, a vector retrieval/generation/correction unit in an information center generates/corrects/optimizes a feature vector on the basis of a vector table, a search history, and a contents description database. In the information center, when an inquiry profile including an inquiry vector is transmitted from the user terminal, an adaptive searching process is executed. According to evaluation made by a contents evaluating unit, proper contents are retrieved from a contents database.

Adaptive information-retrieval system

An information service system having user terminals and a center in which information according to a request for retrieval is provided to users at a low cost while simplifying setting of conditions for retrieval at the user terminals is simplified and maintaining real-time properties. A profile database at a center is updated using profile information transmitted by user terminals to construct an information database. Further, profile information used for retrieval is generated such that it includes information on the environment and situation around a user and information of requests and status of the user to allow proper retrieval in addition to verbal information from the user. The center searches the information database based on such profile information to provide information to the user terminal.

Information service system for providing terminal users with terminal user specific information

A user information inferring system defines user information according to five categories, that is, user environment, circumstance, condition, request, and action, and further defines a sixth category, that is, situation data encompassing these other five categories. User information in each of the defined categories, that is, environment, circumstance, condition, request, action, and situation, is then described using item values, and operating units infer the item values. The inference operation uses temporal-spatial characteristics indicative of the effect of temporal-spatial elements on the item values, information about inferred situations, a rule database containing rules describing the relationships between items, and an optimization process for the defined categories using vector expressions.

User information inferring system

First, in a microcomputer of a communication terminal, data communication request is carried out. Next, a profile corresponding to contents of requested data is received from a communication control device. The microcomputer then selects one of communication systems based on the profile. The result of the selection is notified to the communication control device. Then, a transmission request signal is transmitted from the microcomputer. Thereafter, the data is received from the communication control device through the selected communication system. Thus, the download through the selected communication system is completed.

Adaptive communication system, communication control device, communication terminal, computer program and communication method

A control information output apparatus has a memory unit, an extraction unit and an output unit. The memory unit stores a dependence relationship between each application and a predetermined dependency factor. The memory unit also stores dependency table indicating dependence on the dependence factor of each application. Using the dependency factor value determined with data extracted by the extracting unit, an application list indicating the application having a higher execution request, dependency factor list indicating effective dependency factor and control information comprising a dependence vector and dependence characteristic are outputted from the output unit based on the dependency table and dependence characteristic information of the memory unit.

Control information output apparatus and information system

An interactive-type user interface device for a navigation system or the like in a car enables switching of application programs (APs) in the course of a single interaction with simple scenario descriptions for realizing interactive processing. A scenario for realizing interactive processing by a controller includes a root scenario and a plurality of AP scenario groups, each corresponding to a different AP. In each AP scenario group, only information for acquiring information needed by the respective AP is described. Processing for starting the APs and processing for loading the respective AP scenario groups are described together in the root scenario. Each AP scenario group includes an AP root scenario and multiple AP scenarios. Dialogue information relating to a predetermined topic for realizing interactive processing is described in each AP scenario, while information for branching to the AP scenarios is described in the AP root scenario.

Interactive-type user interface device having root scenario

In a multi-module system, information required for linked operation of a plurality of modules is stored in a communication manager as profiles written in a specific format. The modules operate by referring to these profiles, and update the profiles as appropriate. The modules thereafter operate based on the updated profiles, and appropriately updates the profiles. The communication manager thus enables the linked operation among the modules based on continuously updated profiles.

INTERACTIVE MULTI-MODULE SYSTEM HAVING A COMMUNICATION MANAGER FOR ACHIEVING LINKED OPERATION OF PLURALITY OF MODULES AND FOR DEFINING WHETHER AND HOW AN INDIVIDUAL MODULE CAN ACCESS A PARTICULAR FUNCTION

An apparatus includes a device for generating plural recognition candidates from a user's utterance including a series of words and a device for screening the candidates to select a few appropriate series of words from the candidates. In selecting the appropriate series of words, various factors are taken into consideration. Those factors include evaluation of sentence structures, grammar, relation among words and dialogue topics, and situations surrounding the user. For example, a dialogue topic is first determined, and then a recognition dictionary that only includes words relating to the determined topic is dynamically restructured in the system. Words included in the series of words are recognized and determined with reference to the restructured dictionary. Thus, recognition errors are minimized and determination of a correct series of words is effectively performed.

Apparatus for determining appropriate series of words carrying information to be recognized

A picture signal encoding system capable of transmitting a motion picture at an extremely low rate while sufficiently controlling the occurrence of a retransmission mode and the occurrence of a picture freeze. The encoding system comprises an encoding control section, an attribute memory, an attribute prediction section and an area extraction and recognition processing section. For realizing the extremely low rate transmission, the encoder system integrally performs the alteration of the syntax, the substitute of the code word, the adaptive control for the prediction of the current frame encoding attribute based on the past encoding attribute and the attribute decision, the object area extraction based on the motion and a model, the area-separated quantization control, and the control of the necessary number of transformation coefficients according to the use mode, the transmission rate and the motion occurrence quantity. A protocol transformer is provided to match the current picture compression standard (H.261), so that the encoding system can be made with a simple arrangement.

Growing community of inventors

Kariya, Japan

Mikio Sasaki