摘要:
An object is to provide a face pose estimating device, a face pose estimating method, and a face pose estimating program that allow high accuracy estimation of a face pose even if a face organ cannot be detected from an image. A face organ detector 11 of the face pose estimating device 10 detects a face organ from an image frame. A face pose candidate set generator 16 generates a face pose candidate set. A first similarity estimator 12 computes 3D-model-based similarities. A second similarity estimator 13 computes appearance-based similarities. A first likelihood estimator 141 computes a first likelihood corresponding to the 3D-model-based similarity. A second likelihood estimator 142 computes a second likelihood corresponding to the appearance-based similarities. An integrated likelihood estimator 143 computes an integrated likelihood by using the first and second likelihoods. A face pose estimator 15 estimates the face pose by using the integrated likelihood.
摘要:
An IP communication apparatus has a file transferer that transfers a media data file to a destination apparatus, when determining that the destination apparatus has the file transfer function, based on transmission and reception of SIP messages to and from a call controller, which transmits and receives SIP messages to and from the destination apparatus via a call connection server. Thereby, the IP communication apparatus allows an easy transfer of the media data file.
摘要:
According to the data amount stored in a jitter buffer, which temporarily stores obtained data from a received voice packet, an operation timing of an output process of the jitter buffer and a data process of a codec and a modem is adjusted, the codec and the modem processing data that is sequentially output from the jitter buffer.
摘要:
A vehicle floor structure having a noise insulation structure with a two-way freedom system is provided. The two-way freedom system noise insulation structure is comprised of a lower mass layer and a urethane layer beneath the same, and an upper mass layer and a low resilient material layer beneath the same and made of fibrous material layer or low resilient urethane layer.
摘要:
A knowledge provider system is configured as a plurality of data servers connected via a data communication network, which function as respective knowledge provider agents in response to information request messages sent from users of the network. Each agent holds a script which contains a knowledge base, and data defining predetermined message formats for respective types of messages and predetermined content formats for respective types of message contents which can be handled by that agent. A message received by an agent is pattern-matched against the message formats, if it is thereby found to be an information request message the message content portion is pattern-matched against the predetermined content formats, and if that matching is successful, the subject for which information is requested is pattern-matched against the contents of the knowledge base, to find a set of information corresponding to that subject. If any of the pattern matching operations is not successful, the agent originates messages for successively propagating the content portion of that information request message to other agents via the network. Obtained information is then sent back to the originating agent and hence to the user.
摘要:
A propylene resin composition containing a propylene-ethylene block copolymer containing (a) a crystalline polypropylene moiety (constituent A) and an ethylene-propylene random copolymer moiety (constituent B), (b) a styrene-ethylene-butylene-styrene block copolymer which contains 10% to 25% of bound styrene, and (c) at least one filler selected from talc and inorganic whiskers and wherein the surface of the filler is treated with one of the organic compounds (I), (II) and (III) having the formulas, ##STR1## in which the various substituents and R groups are as defined in the specification and claims. The composition of the present invention has excellent mechanical strength, moldability and is capable of producing molded products having an excellent appearance.
摘要:
A blower comprises an impeller which can function to raise the pressure of a fluid and delivers it; a driving device for driving the impeller; and a fan casing which includes a fluid path to inspire the fluid from the outside and deliver it to the outside through the impeller; wherein the fan casing is at least partly formed by a hard porous structural unit whose specific gravity is continuously changed in at least one of the direction of thickness and a direction of surface.
摘要:
A floor detector for a power brush of a vacuum cleaner comprises a lift sensor S1 and a floor sensor S2. The lift sensor S1 has a movable member which yieldably displaces when the power brush is placed on a relatively soft floor while the floor sensor S2 has a movable member which yieldably displaces when the power brush is placed on a relatively hard floor. Each of movable members is detected its movement by a corresponding light sensor which provides a signal representative of the movements. The signals from the light sensors are sent to a control circuit which controls a drive source for driving the brush member of the power brush. In this manner, the brush member is rotated when the power brush is placed on a relatively soft floor such as a carpeted floor and is not rotated when the power brush is placed on a relatively hard, flat, smooth floor.
摘要:
There is provided an arousal state classification model generating device for generating a blink waveform pattern model and an arousal state pattern model based on data on a blink waveform, which are preferably used for accurately estimating an arousal level with respect to unspecified object persons, an arousal state classifying device for classifying the arousal state of an object person, and a warning device. In the arousal state classification model generating device, a first pattern model is generated by learning a statistical model by using as learning data first feature data extracted from the blink data of at least one of the eyes of each object person at the time of blinking and blink waveform identification information. A second pattern model is generated by learning a statistical model by using as learning data second feature data including data on the occurrence ratio of each specific type of blink waveform in the sequence of analysis intervals and arousal state information data in which arousal state information indicating the arousal state of each object person is provided to each sequence of analysis intervals.