Abstract: A movement vector calculation unit calculates movement vectors between frames of a video image of an area ahead of a vehicle. The video image is input as a moving image. An area inference unit infers an area indicating a movable object included in the video image of the area ahead of the vehicle. A vector excluding unit excludes, from among the calculated movement vectors, movement vectors in an area inferred as being the area indicating the movable object. A behavior inference unit infers behavior of the vehicle based on the movement vectors from which those in the area inferred as being the area indicating the movable object have been excluded.

Abstract: An object recognition system 80 includes: a recognition device 30 that recognizes an object in an image; and a server 40 that generates a learning model. The recognition device 30 includes: a first object recognition unit 310 that determines a type of the object in the image using the learning model; and an image transmission unit 320 that transmits a type-indeterminable image, which is an image in which the type has not been determined, to the server 40 when an object included in the type-indeterminable image is an object detected as a three-dimensional object. The server 40 includes: a learning device 410 that generates the learning model based on training data in which a teacher label is assigned to the type-indeterminable image; and a learning model transmission unit 420 that transmits the generated learning model to the recognition device 30. The first object recognition unit 310 determines the type of the object in the image using the transmitted learning model.

Abstract: A position detection unit detects positions of right and left shoulders of a driver, and positions of at least two body parts of the driver from a driver image obtained by capturing an image of the driver. A shoulder width calculation unit calculate a width of shoulders of the driver based on the detected positions of the right and left shoulders. A threshold determination unit determines at least one determination threshold based on the calculated width of shoulders. A determination unit determines a driving state of the driver by using the positions of the at least two detected body parts detected by the position detection unit and the at least one determination threshold determined by the threshold determination unit.

Abstract: An image generation apparatus (20) includes an acquisition unit (210) and a data processing unit (220). The acquisition unit (210) repeatedly acquires analysis data from at least one sending apparatus (10). The analysis data include at least type data and relative position data. The data processing unit (220) generates, each time analysis data are acquired, a reconfigured image by using the analysis data, and causes a display (230) to display the reconfigured image. Further, the data processing unit (220) requests the sending apparatus (10) for a captured image, when a criterion is satisfied.

Abstract: An object recognition unit recognizes an object included in an image captured by a camera mounted on a vehicle. A first distance estimation unit estimates a distance between the vehicle and the recognized object based on the image. A second distance estimation unit estimates the distance between the vehicle and the recognized object based on the image by using an estimation method different from that of the first distance estimation unit. A combining unit combines a result of estimating the distance obtained by the first distance estimation unit and a result of estimating the distance obtained by the second distance estimation unit based on at least one of an amount of change in the distance estimated by the second distance estimation unit, a steering wheel angle of the vehicle, and information about an acceleration in an up-down direction, and outputs a result of the combination as a ranging result.

Abstract: An object recognition device 80 includes a scene determination unit 81, a learning-model selection unit 82, and an object recognition unit 83. The scene determination unit 81 determines, based on information obtained during driving of a vehicle, a scene of the vehicle. The learning-model selection unit 82 selects, in accordance with the determined scene, a learning model to be used for object recognition from two or more learning models. The object recognition unit 83 recognizes, using the selected learning model, an object in an image to be photographed during driving of the vehicle.

Abstract: It is difficult in related communication apparatuses to avoid degradation of communication quality due to fading and achieve sufficient throughput performance; therefore, a communication apparatus according to an exemplary aspect of the present invention includes fade avoidance rate calculation means for calculating, from a time variation in communication quality information and a transmission pattern in transmitting a communication packet repeatedly, a fade avoidance rate of a probability that the communication packet lies outside a fade duration, with respect to each transmission pattern; throughput calculation means for calculating, from the transmission pattern and the fade avoidance rate, a throughput of the communication packet with respect to each transmission pattern; and transmission pattern determination means for determining an optimum transmission pattern, of the transmission pattern, by which the throughput is maximized.

Abstract: A dangerous scene prediction device 80 for predicting a dangerous scene occurring during driving of a vehicle includes a learning model selection/synthesis unit 81 and a dangerous scene prediction unit 82. The learning model selection/synthesis unit 81 selects, from two or more learning models, a learning model used for predicting the dangerous scene, depending on a scene determined based on information obtained during the driving of the vehicle. The dangerous scene prediction unit 82 predicts the dangerous scene occurring during the driving of the vehicle, using the selected learning model.

Abstract: An object recognition system 80 includes: a recognition device 30 that recognizes an object in an image; and a server 40 that generates a learning model. The recognition device 30 includes: a first object recognition unit 310 that determines a type of the object in the image using the learning model; and an image transmission unit 320 that transmits a type-indeterminable image, which is an image in which the type has not been determined, to the server 40 when an object included in the type-indeterminable image is an object detected as a three-dimensional object. The server 40 includes: a learning device 410 that generates the learning model based on training data in which a teacher label is assigned to the type-indeterminable image; and a learning model transmission unit 420 that transmits the generated learning model to the recognition device 30. The first object recognition unit 310 determines the type of the object in the image using the transmitted learning model.

Abstract: An object recognition device 80 includes a scene determination unit 81, a learning-model selection unit 82, and an object recognition unit 83. The scene determination unit 81 determines, based on information obtained during driving of a vehicle, a scene of the vehicle. The learning-model selection unit 82 selects, in accordance with the determined scene, a learning model to be used for object recognition from two or more learning models. The object recognition unit 83 recognizes, using the selected learning model, an object in an image to be photographed during driving of the vehicle.

Abstract: A signal processing device combines a plurality of received signals, and includes: a phase reference signal selection means for selecting a signal serving as a phase reference from among the plurality of received signals on the basis of the quality of the plurality of received signals; a relative phase calculation means for obtaining information about the relative phases of the plurality of received signals before the combining; a phase compensation means for performing relative phase compensation on each of the plurality of received signals on the basis of the relative phases; and a phase correction means for calculating a phase correction amount based on the relative phase information and performing phase correction on the received signals, wherein when switching occurs in the selected phase reference signal, the phase correction amount is changed by as much as the relative phase difference between the phase reference signals before and after the switching.

Abstract: A signal processing device combines a plurality of received signals, and includes: a phase reference signal selection means for selecting a signal serving as a phase reference from among the plurality of received signals on the basis of the quality of the plurality of received signals; a relative phase calculation means for obtaining information about the relative phases of the plurality of received signals before the combining; a phase compensation means for performing relative phase compensation on each of the plurality of received signals on the basis of the relative phases; and a phase correction means for calculating a phase correction amount based on the relative phase information and performing phase correction on the received signals, wherein when switching occurs in the selected phase reference signal, the phase correction amount is changed by as much as the relative phase difference between the phase reference signals before and after the switching.

Abstract: The present invention improves reception characteristics of a receiving apparatus based on OFDM. The receiving apparatus includes: a window timing selection unit that determines Fourier transform window start and end timings for a received signal(s) based on OFDM, based on a signal-to-interference power ratio and signal power in a Fourier transform window; and a Fourier transform unit that performs Fourier transform on the received signal(s) in accordance with the Fourier transform window start and end timings outputted by the window timing selection unit.

Abstract: It is difficult in related communication apparatuses to avoid degradation of communication quality due to fading and achieve sufficient throughput performance; therefore, a communication apparatus according to an exemplary aspect of the present invention includes fade avoidance rate calculation means for calculating, from a time variation in communication quality information and a transmission pattern in transmitting a communication packet repeatedly, a fade avoidance rate of a probability that the communication packet lies outside a fade duration, with respect to each transmission pattern; throughput calculation means for calculating, from the transmission pattern and the fade avoidance rate, a throughput of the communication packet with respect to each transmission pattern; and transmission pattern determination means for determining an optimum transmission pattern, of the transmission pattern, by which the throughput is maximized.

Abstract: The object of the present invention is to reduce the number of complex multiplications in an ICI reduction processing and to reduce the influence of characteristic degradation due to a quantization bit limitation of a digital signal processing. A receiver includes an extended CP addition unit (102) that receives radio signals through a plurality of paths and compensates for a symbol lost within a Fourier transform window to received signals received through the plurality of paths; and FFTs (104-1 and 104-2) each of which performs, in a range of the Fourier transform window, Fourier transform on the received signal with a lost symbol added.

Abstract: The present invention improves reception characteristics of a receiving apparatus based on OFDM. The receiving apparatus includes: a window timing selection unit that determines Fourier transform window start and end timings for a received signal(s) based on OFDM, based on a signal-to-interference power ratio and signal power in a Fourier transform window; and a Fourier transform unit that performs Fourier transform on the received signal(s) in accordance with the Fourier transform window start and end timings outputted by the window timing selection unit.

Abstract: The object of the present invention is to reduce the number of complex multiplications in an ICI reduction processing and to reduce the influence of characteristic degradation due to a quantization bit limitation of a digital signal processing. A receiver includes an extended CP addition unit (102) that receives radio signals through a plurality of paths and compensates for a symbol lost within a Fourier transform window to received signals received through the plurality of paths; and FFTs (104-1 and 104-2) each of which performs, in a range of the Fourier transform window, Fourier transform on the received signal with a lost symbol added.

Abstract: A radio reception device and a radio receiving method are provided that, when a frequency band assigned to a different radio system is shared, can effectively suppress the influence of interfering waves from this different radio system.

Abstract: A wireless transmission device is characterized by including: first interference suppression processing means 71 for generating an interference suppression transmission signal for partially suppressing leakage power of a signal to an interference avoidance band by frequency-domain processing for the signal in a partial frequency band of transmission signals; and second interference suppression processing means 72 for generating an interference suppression transmission signal for suppressing leakage power of a signal to the interference avoidance band by time-domain processing for the signal in a partial or entire frequency band of transmission signals.

Abstract: A wireless sending apparatus with a change judging means to judge whether changing an interference causing avoiding transmission means on the basis of predetermined change judging information, and to output the judgment as a change judgment result; a signal separating means to separate the sending signal into each the group on the basis of the change judgment result; a first interference causing avoiding transmission means to input the sending signal which is separated into each the group, and to reduce leak power by a time-domain process; a second interference causing avoiding transmission means to input the sending signal which is separated into each the group, and to reduce the leak power by a frequency-domain process; and a synthesizing means to synthesize the sending signals which the first interference causing avoiding transmission means and the second interference causing avoiding transmission means carry out the interference causing avoiding process.