Abstract: An AI training method includes inputting training data to an existing trained AI model to acquire a trained-layer feature value output from a trained layer in the existing trained AI model, merging the trained-layer feature value with a training-target layer feature value output from a training-target layer in the training-target AI model to generate a merged feature value, and inputting the merged feature value to a training-target layer subsequent to the training-target layer to generate a new trained AI model.

Abstract: An apparatus includes a base structure having a first portion including a plurality of transistors and a second portion surrounding the first portion; a storage structure on the first portion of the base structure, the storage structure including a plurality of storage capacitors each coupled to a corresponding one of the plurality of transistors; an interface structure on the second portion of the base structure; and a peripheral structure on the interface structure; wherein the interface structure is divided into a plurality of insulating films and the plurality of insulating films are arranged away from each other to have a plurality of voids between the second portion of the base structure and the peripheral structure.

Abstract: The environmental change proposing system includes: an acquiring unit configured to acquire processing information regarding processing of a conveyance task from a conveyance robot that has executed the conveyance task using an environmental map; an evaluation computing unit configured to perform an evaluation computation for evaluating, based on the processing information, a virtual layout in which the arrangement of installation objects on the environmental map has been changed; and an output unit configured to generate and output proposal information regarding a change in arrangement of the installation objects, based on an evaluation result of the evaluation computing unit.

Abstract: An apparatus includes a base structure having a first portion including a plurality of transistors and a second portion surrounding the first portion; a storage structure on the first portion of the base structure, the storage structure including a plurality of storage capacitors each coupled to a corresponding one of the plurality of transistors; an interface structure on the second portion of the base structure; and a peripheral structure on the interface structure; wherein the interface structure is divided into a plurality of insulating films and the plurality of insulating films are arranged away from each other to have a plurality of voids between the second portion of the base structure and the peripheral structure.

Abstract: In an image recognition apparatus, a processor performs, based on an input image and using an image recognition model, a plurality of object detection processes to detect as an object detection region a region in the input image where a recognition target object is judged to be present. In the plurality of object detection processes, a plurality of mutually different image recognition models are used. The processor generates inference result data according to the degree of overlap among a plurality of object detection regions detected in the plurality of object detection processes.

Abstract: A route planning system according to one or more embodiments may include an obtaining unit configured to obtain an environmental map indicating, for any obstacle, a location and a degree of certainty that the obstacle is present at that location, a planning unit configured to plan a movement route along which a mobile robot moves, excluding any obstacles in the environmental map, that have a degree of certainty that does not satisfy a predetermined standard, and an output unit configured to output route information, which is information on the planned movement route, to the mobile robot.

Abstract: A signal color determination device includes a processor configured to acquire a captured image. If a part of a plurality of signal lamps of a traffic signal is detected from the captured image, the processor determines a signal color of the traffic signal.

Abstract: A vehicle onboard apparatus mounted in a vehicle includes an in-vehicle processing unit that performs image recognition on an input image from a camera mounted in the vehicle. The in-vehicle processing unit performs the image recognition using an image recognition model corresponding to position information of the vehicle and additional reference information different from the position information.

Abstract: An image processing device for generating learning data that is used for machine learning includes a processor that obtains image data. The processor specifies an unprocessable region that is a region in which a predetermined process cannot be performed or a region in which the predetermined process is not performed in an image region of the image data, and generates image data on which the predetermined process is performed in a region except the unprocessable region in the image region, as the learning data.

Abstract: A learning apparatus for training a student model with a teacher model includes a processor. The processor computes the performance difference between the teacher and student models. The processor makes at least one of a determination, based on the performance difference, of whether to use the teacher model and a determination, based on the performance difference, of whether to change the weight coefficient in calculating the loss in the student model.

Abstract: A model generating apparatus includes a measurement unit and a change unit. The measurement unit measures a size of an object appearing on an image included in data set. The change unit changes, based on a distribution of the size, a layer to be connected to a detection unit of a Convolutional Neural Network (CNN) for detecting an object appearing on the image, among layers for extracting feature included in the CNN.

Abstract: An object to reduce a possibility that a detection target appearing in a captured image is not detected. In order to achieve such an object, an image processing device includes: a first detection unit that is configured to detect a predetermined object and a predetermined part of the predetermined object from an acquired captured image; a setting unit that sets a detection range in the captured image based on a detection result of the first detection unit in a case where only the predetermined object out of the predetermined object and the predetermined part has been detected by the first detection unit; and a second detection unit that attempts to detect the predetermined part in the detection range.

Abstract: An information processing device includes a memory and a processor coupled to the memory. The processor acquires a first image at a first time and a second image at a second time later than the first time from a monocular camera mounted on a vehicle, calculates an amount of movement of the vehicle based on a sensor value acquired during a measurement period between the first time and the second time, outputs a result of distance measurement using a first distance measurement method to perform distance measurement using the first image or the second image or a second distance measurement method to perform distance measurement using the first image and the second image, depending on the amount of movement and outputs a result of calculation of a route to guide the vehicle to a parking space, based on the result of distance measurement.

Abstract: An image processing device includes: a detection unit which detects a target object based on edge information acquired from image data; and a judging unit which judges whether a certain region in the image data is an improper region that is not suitable for detection of the target object based on an edge pattern of edge information in the certain region and a feature pattern indicating a feature of the target object, and the detection unit detects the target object excluding a region that has been judged to be the improper region by the judging unit.

Abstract: In a travel status recording apparatus, a data acquisition unit acquires first travel status data and second travel status data indicating a travel status in relation to a vehicle. An event detection unit detects a predetermined event that occurs in relation to the vehicle based on the first travel status data acquired. In response to the predetermined event being detected, a data analysis unit analyzes the second travel status data using artificial intelligence. A recording control unit records, in a storage unit, an analysis result of the second travel status data in association with event detection information in relation to the predetermined event.

Abstract: An image processing device includes: a delimiting line detection unit configured to detect a delimiting line candidate based on image data obtained by capturing a surrounding of a vehicle; an exclusion determination unit configured to determine whether there is a parking-unavailable area in which parking of the vehicle is not permitted; and a parking space detection unit configured to detect the parking space based on the delimiting line candidate. In a case where plural parallel lines that are adjacent to the delimiting line candidate and that have a predetermined angle to the delimiting line candidate is detected, the exclusion determination unit regards an area in which the plural parallel lines are provided as the parking-unavailable area, and prohibits the parking space detection unit from detecting the parking space across the delimiting line candidate adjacent to the parking-unavailable area.

Abstract: An image processing device includes: an extraction unit which extracts, from image data taken by shooting a neighborhood of a vehicle, edge points that are to be used for detecting partition lines of a parking frame and whose edge intensity values are larger than an edge threshold value; and a correction unit which corrects the edge threshold value based on a density of the edge points extracted by the extraction unit.

Abstract: An image processing device includes: a delimiting line detection unit configured to detect a delimiting line candidate based on image data obtained by capturing a surrounding of a vehicle, the delimiting line candidate being a candidate of a delimiting line that delimits a parking space; and an exclusion determination unit configured to determine whether or not to exclude the delimiting line candidate detected by the delimiting line detection unit from the candidate of the delimiting line. In a case where a plurality of the delimiting line candidates is detected within a predetermined range in the image data, the exclusion determination unit determines whether or not to exclude the delimiting line candidate from the candidate of the delimiting line by comparing edge strength of the plurality of delimiting line candidates.

Abstract: An image processing device includes: a detection unit which detects partition line candidates that are candidates for a partition line for partitioning a parking frame, based on edge lines that are detected based on luminance of each pixel of image data taken by shooting a neighborhood of a vehicle; and a generation unit which generates an integrated partition line candidate by integrating the partition line candidates detected by the detection unit, according to a prescribed integration condition.

Abstract: An image processing device includes: an extraction unit which extracts edge lines based on image data taken by an imaging device by shooting a neighborhood of a vehicle; a selection unit which selects, as a pair of edge lines, edge lines that satisfy a prescribed condition from the extracted edge lines; an exclusion unit which, in a case where a non-paint-out region exists between the pair of edge lines, excludes quasi-edge lines that form the non-paint-out region from the pair of edge lines; and a detection unit which detects a partition line that partitions a parking frame based on the pair of edge lines from which the quasi-edge lines are excluded.