Abstract: A machine learning system includes first and second information processing devices. The first-information-processing device includes a first-evaluation unit, a first-selection unit, and a candidate-data-transmission unit. The first-evaluation unit calculates a first evaluation value for each of candidate data pieces based on a first evaluation standard. The first-selection unit selects whether each input data is included in the candidate data pieces based on the first evaluation value. The candidate-data-transmission unit transmits the candidate data. The second-information-processing device includes a candidate-data-reception unit, a second-evaluation unit, and a second-selection unit. The candidate-data-reception unit receives the candidate data. The second-evaluation unit calculates a second evaluation value for each candidate data based on a second evaluation standard different from the first evaluation standard.

Abstract: According to one embodiment, a learning apparatus includes a processor. The processor performs, on a neural network model, an adaptation processing that includes at least either insertion of an activation function, or correction of the activation function. The processor generates a trained model by training the neural network model on which the adaptation processing has been performed. The processor performs pruning on the trained model to generate a reconstructed model from which a parameter has been reduced.

Abstract: A position and attitude estimation apparatus includes sub-sensor input accepters, a speed sensor state determiner, a scale estimator, and a position and attitude information corrector. The sub-sensor input accepter accepts an output of a sub-sensor which acquires information regarding a movement amount based on information other than an output value of a speed sensor. The speed sensor state determiner determines whether the output value of the speed sensor is reliable. The scale estimator estimates a size of the movement amount based on at least one of the output value of the speed sensor and an output value of the sub-sensor. The position and attitude information corrector corrects position and attitude information based on the size of the movement amount estimated by the scale estimator.

Abstract: According to one embodiment, a three-dimensional map estimation apparatus includes a processor that selects an imaging apparatus from a plurality of imaging apparatuses and then estimates a position and orientation for a moving object on which the selected imaging apparatus is mounted based on images captured by the selected imaging apparatus. The processor outputs a first position and orientation estimation result for the moving object based on images from selected imaging apparatuses. The processor calculates a second position and orientation estimation result indicating an estimated position and orientation for the moving object using the first position and orientation estimation result. The processor estimates a three-dimensional map for the surroundings of the moving object based on the second position and orientation estimation result.

Abstract: A location estimation apparatus includes a reliability calculation circuit, a selection circuit, and a self-location estimation circuit. The reliability calculation circuit calculates a reliability with respect to location estimation for a plurality of devices capturing a plurality of input images. The selection circuit selects one of the devices based on the reliability. The self-location estimation circuit performs self-location estimation based on the image captured by the selected device.

Abstract: According to one embodiment, a motion estimation device includes a first receiving circuit that receives a first input frame and a calculation circuit that performs motion estimation processing on the first input frame. The calculation circuit estimates a distance for each pixel of the first input frame and estimates a reliability of the distance for each pixel of the first input frame based on pixel information of the first input frame.

Abstract: According to one embodiment, a distance estimation device comprises a first distance estimation unit based on a first estimation method, and a second distance estimation unit based on a second estimation method different from the first estimation method. The second distance estimation unit is configured to change a part of the second estimation method according to an output of the first distance estimation unit.

Abstract: An information processing apparatus according to one embodiment includes a processing circuit. The processing circuit calculates a first presence probability of an object present around a moving body with positional information measured by each of a plurality of sensors having different characteristics, acquires non-measurement information indicating that the positional information on the object has not been obtained for each of the sensors, and determines a second presence probability of the object based on the first presence probability and the non-measurement information.

Abstract: An information processing apparatus according to one embodiment includes a memory having computer executable components stored therein; and processing circuitry communicatively coupled to the memory. The processing circuitry is configured to: acquire, for each of a plurality of sensors installed in a vehicle, positional information of an object present around the vehicle measured by the sensor; calculate a probability that the object is present for each of a plurality of areas obtained by dividing surroundings of the vehicle based on the positional information measured by the sensors; record non-measurement information indicating that the positional information was not obtained for an area corresponding to a direction in which the positional information was not obtained for each of the sensors; and determine a final probability that the object is present based on the probability calculated for each of the sensors and the non-measurement information.

Abstract: According to one or more embodiments, an information processing device includes a processor to receive input signals from a plurality of external devices and to receive a plurality of sensor signals from a plurality of sensors. The processor selects a processing mode for each input signal from the plurality of external devices based at least in part on the plurality of sensor signals. The processing mode is selected from available processing modes which include a normal mode and a low load mode. The low load mode has a lower processing load than the normal mode. The processor processes a first input signal in the low load mode and a second input signal in the normal mode.

Abstract: An information processing apparatus according to an embodiment includes a determination unit and an output control unit. The determination unit determines whether a particular part related to a type of an object is included in a blind spot of an object of interest. The output control unit outputs output information when it is determined that the part is included in the blind spot.

Abstract: According to an embodiment, a device includes processing circuitry. The processing circuitry performs three-dimensional measurement of surroundings of a mobile object to obtain a three-dimensional point group. The processing circuitry calculates movement information. The processing circuitry makes a threshold value based on time series differences in the movement information. The processing circuitry extracts, from the three-dimensional group, three-dimensional points having distance to the mobile object in a moving direction of the mobile object to be equal to or smaller than the threshold value. The processing circuitry divides space, in which the three-dimensional points are present, into divided spaces in the moving direction. The processing circuitry selects a representative point for the divided space from among three-dimensional points included in the divided space.

Abstract: A location estimation apparatus includes a reliability calculation circuit, a selection circuit, and a self-location estimation circuit. The reliability calculation circuit calculates a reliability with respect to location estimation for a plurality of devices capturing a plurality of input images. The selection circuit selects one of the devices based on the reliability. The self-location estimation circuit performs self-location estimation based on the image captured by the selected device.

Abstract: A position attitude estimation apparatus includes sub-sensor input accepters, a speed sensor state determiner, a scale estimator, and a position attitude information corrector. The sub-sensor input accepter accepts an output of a sub-sensor which acquires information regarding a movement amount based on information other than an output value of a speed sensor. The speed sensor state determiner determines whether the output value of the speed sensor is reliable. The scale estimator estimates a size of the movement amount based on at least one of the output value of the speed sensor and an output value of the sub-sensor. The position attitude information corrector corrects position attitude information based on the size of the movement amount estimated by the scale estimator.

Abstract: An example image processing device obtains first images capturing a street, on which a target vehicle is running, from a plurality of directions, and position information indicating positions at which the first images are taken, and associates a background object in a second image with a background object in a third image. The second image is an image which the target object is detected from and the third image is an image which is taken by an imaging device having a common imaging range with the second image among imaging devices mounted on the target vehicle. An output image is generated to include the position information indicating a position at which the second image is taken, the image of the detection rectangle which is clipped from the second image and includes the target object and the background object, and the first image of surroundings of the target vehicle.

Abstract: According to an embodiment, a detection device includes a camera, a memory, and processor circuitry. The camera is connected to an internal bus and configured to acquire an image including an area in which a mobile body is movable. The memory is connected to the internal bus and configured to store data and a program. The processor circuitry is connected to the internal bus and configured to detect at least the area, a mark on the area, and a person, from the image, calculate a first distance between the person and a position of the device when the person is in the area, and set a range according to a result of the detection and the first distance.

Abstract: According to an embodiment, an image processing apparatus includes a characteristic point detecting unit configured to detect a plurality of characteristic points in a first image and a second image imaged with two cameras having angles of view or angular velocity of line scan different from each other, a characteristic point pair determining unit configured to determine a plurality of characteristic point pairs between the first image and the second image from the detected plurality of characteristic points, a mapping parameter calculating unit configured to calculate a first parameter indicating mapping between the first image and the second image, and a distortion parameter calculating unit configured to obtain a second parameter indicating distortion of the first image and the second image from the first parameter.

Abstract: According to an embodiment, a measurement device includes a processing circuitry. A plurality of images are captured in time series by an image capturing unit installed in a moving object. The processing circuitry identifies a region in which other moving object moving in surroundings of the moving object is present for each of the images, based on position and direction information of the moving object, and moving object information of the other moving object. The processing circuitry estimates position and posture of the image capturing unit based on the images. The processing circuitry searches for sets of corresponding points among non-moving object regions in the respective images. The processing circuitry performs 3D measurement based on the position and posture of the image capturing unit and the sets of the corresponding points.

Abstract: According to one embodiment, a monitor apparatus includes a memory and processing circuitry. The processing circuitry acquires first information indicating a position and a moving direction of a target, acquires second information indicating a position of each of moving objects and sensors which are provided in the moving objects, selects at least one of a first moving object for monitoring the target from among the moving objects or a first sensor for monitoring the target from among the sensors, based on the first information and the second information, and transmits third information indicating the target and at least one of the first moving object or the first sensor.

Abstract: An information processing apparatus according to an embodiment includes a determination unit and an output control unit. The determination unit determines whether a particular part related to a type of an object is included in a blind spot of an object of interest. The output control unit outputs output information when it is determined that the part is included in the blind spot.