Abstract: An automatic driving assistance apparatus includes a driving state acquirer, an own vehicle location acquirer, a traveling environment information acquirer, a branch lane determining unit, a lane change calculator, and a traveling state controller. The driving state acquirer acquires a driving state of an own vehicle. The own vehicle location acquirer acquires a location of the own vehicle. The traveling environment acquirer acquires a traveling environment in which the own vehicle is traveling. The branch lane determining unit examines whether a target travel path toward which the own vehicle travels is set to a branch lane direction. The lane change calculator obtains a deceleration start position and a lane change start position of the own vehicle. The traveling state controller controls a traveling state of the own vehicle based on the deceleration start position and the lane change start position.

Abstract: An environmental state estimation device according to one embodiment of the present disclosure includes an environmental state estimation unit configured to estimate an environmental state of a prescribed area, based on information regarding a surrounding environmental state acquired by a plurality of vehicles in the prescribed area. A method for environmental state estimation according to another embodiment of the present disclosure includes an estimation step of an environmental state estimation device estimating an environmental state of a prescribed area, based on information regarding a surrounding environmental state acquired by a plurality of vehicles in the prescribed area.

Abstract: A vehicular image synthesis apparatus include a plurality of cameras mounted on a vehicle for capturing an image of a driver. The plurality of images captured by the plurality of cameras may be compared to detect a boundary suitable for synthesis. The plurality of images may be synthesized at the boundary.

Abstract: A vehicle control device includes a preceding vehicle recognition unit which recognizes a preceding vehicle, a lane marking recognition unit which recognizes a lane marking for sectioning a lane in which a host vehicle travels, and a traveling control unit which performs first traveling control for causing the host vehicle to travel along a traveling route based on the lane marking recognized by the lane marking recognition unit in a case where the degree of recognition of the lane marking recognized by the lane marking recognition unit satisfies a predetermined standard, and performs second traveling control for causing the host vehicle to travel on the basis of a trajectory of the preceding vehicle recognized by the preceding vehicle recognition unit in a case where the degree of recognition of the lane marking recognized by the lane marking recognition unit does not satisfy the predetermined standard, and the traveling control unit changes the predetermined standard on the basis of a vehicle speed of the h

Abstract: In an image processing apparatus, a vehicle speed obtainer obtains vehicle speed information indicative of a speed of a vehicle. A deactivation controller determines whether the speed of the vehicle represented by the vehicle speed information is equal to or lower than a speed-related deactivation threshold previously determined for a target device. The target device is a selected one of first and second imaging devices. The selected one of the first and second imaging devices has one of first and second angular fields of view smaller than the other of the first and second angular fields of view. The deactivation controller deactivates a capture operation of the target device upon determination that the speed of the vehicle represented by the vehicle speed information is equal to or lower than the speed-related deactivation threshold previously determined for the target device.

Abstract: A method that includes obtaining real training samples that include real images that depict real objects, obtaining simulated training samples that include simulated images that depict simulated objects, defining a training dataset that includes at least some of the real training samples and at least some of the simulated training samples, and training a machine learning model to detect subject objects in unannotated input images using the training dataset.

Abstract: Disclosed is a vehicle. The vehicle comprises: storage in which a plurality of reference images and position information corresponding to respective plurality of reference images are stored; and a processor which acquires through a camera an image of the surrounding environment in which the vehicle is traveling, acquires a reference image corresponding to the current position of the vehicle among the plurality of reference images if the visibility of the surrounding environment image satisfies a predetermined condition, acquires an image in which the surrounding environment image and the reference image are merged, and controls the operation of the vehicle on the basis of the merged image.

Abstract: According to one embodiment, a road surface management system inputs image data of road surface and capturing information of each of the image data and registers them. The image data are collected by repeatedly capturing a same route at predetermined distance. The capturing information includes information of a location and time at time of capturing. The system selects old and new images at a same spot from the registered image data, performs an association process, extracts an original image which is an old image at an arbitrary spot and a target image which is a new image associated with the original image unit based on the result of the association process, and outputs the original image and the target image.

Abstract: According to one embodiment, the image processing device includes imagers disposed on an outer circumference of a mobile object for imaging surroundings of the mobile object to generate multiple images including mutually overlapping regions, and a processor that corrects the images on the basis of one color-value mean value and another color-value mean value to generate a peripheral image by combining the corrected images. The one color-value mean value is an average of color values of a target region set in an overlapping region of one of the images. Another color-value mean value is an average of color values of a target region set in an overlapping region of another one of the images.

Abstract: An image-based road cone recognition method, apparatus, storage medium, and vehicle. Said method comprises: acquiring, during vehicle driving, an image of an object to be recognized; performing differential processing of the image, so as to acquire an image on which the differential processing has been performed, and performing, according to a preset threshold, ternary processing of the image on which the differential processing has been performed, so as to acquire a ternary image comprising forward boundary pixels and negative boundary pixels; acquiring, according to the forward boundary pixels and the negative boundary pixels, a forward straight line segment and a negative straight line segment which represent the trend of the boundaries of the object to be recognized; when position information of the forward and negative straight line segments matches boundary position information of a known road cone, determining that the object to be recognized is a road cone.

Abstract: A method for detecting objects in a vehicle blind spot comprises the following steps: generating a region of interest onto an image taken from one camera placed on one side of the vehicle; generating a top view of the region of interest; detecting an object in the region of interest; determining if the object in the region of interest is a target object; and triggering a signal if it is determined that there is a target object in the region of interest.

Abstract: A method and an apparatus for extracting a lane line, a device, a computer readable-storage medium and a collection entity are provided. The method includes: obtaining a first group of lane lines of a road based on a first image generated from a point cloud collected by a laser radar; obtaining a second group of lane lines of the road based on a second image collected by a camera; and determining a lane line set of the road based on the first group of lane lines and the second group of lane lines.

Abstract: A system and method control a vehicular headlamp for preventing a shadow area between a low beam and a high beam of a headlamp using a camera unit. The method includes periodically determining whether a high beam of the vehicular headlamp is lit or illuminated. Upon determining that the high beam is illuminated, the method includes determining whether a darkness cell is formed in front image data of the vehicle, which is transmitted from a camera unit. Upon determining that the darkness cell is formed, the method includes changing a leveling motor to be directed upward by 1 step and storing a changed number of steps. Upon determining that the darkness cell is not formed, the method includes driving the leveling motor by the pre-stored number of steps.

Abstract: Disclosed is a fallen object detection apparatus and method for controlling a component to continuously provide a service, provided by a communication device, when the communication device has fallen inside a vehicle. A fallen object detection apparatus inside a vehicle includes: a monitor configured to monitor an inside of the vehicle in which a passenger and an object are present: an identifier configured to identify that the object is a communication device capable of being connected to the component inside the vehicle in response to determination that the object is determined to have fallen on the basis of a monitoring result; and a processor configured to connect the object with the component and control the component to continuously provide a service, provided by the object, when the object is identified to be the communication device.

Abstract: An information processing system is equipped with at least one vehicle and a server that can communicate with the at least one vehicle. The vehicle acquires an image obtained by imaging a landscape outside the vehicle, a humidity outside the vehicle, and an imaging position of the image. The vehicle or the server generates floating substance information on an atmospheric floating substance around the vehicle, based on the image and the humidity. The server stores at least one pair of the floating substance information and the imaging position corresponding thereto, and provides information to a client through the use of the at least one pair of the stored floating substance information and the stored imaging position corresponding thereto.

Abstract: According to an embodiment, an information processing apparatus includes an attribute determiner and a setter. Each of acquired first sets indicates a combination of observation information indicating a result of observation of an area surrounding a moving body and position information. The attribute determiner is configured to determine, based on the observation information, an attribute of each of areas into which the area surrounding the moving body is divided, and to generate second sets, each indicating a combination of attribute information indicating the attribute of each area and the position information. The setter is configured to set, based on the second sets, reliability of the attribute of the area of a target second set, from correlation between the attribute of the area of the target second set and the attribute of corresponding areas each indicating the area corresponding to the target area in the areas of the other second sets.

Abstract: A method for controlling a vehicle as it travels along a road includes processing at an ECU provided image data captured by a forward viewing camera and processing at the ECU a provided output indicative of a determined geographical location of the vehicle. Responsive at least in part to processing of the provided output, a geographically-derived path of travel of the vehicle is generated. Responsive to determination of a traffic lane in which the vehicle is traveling along the road, a camera-derived path of travel of the vehicle is generated. The vehicle is controlled based on (i) the geographically-derived path of travel of the vehicle and/or (ii) the camera-derived path of travel of the vehicle. The vehicle is controlled based on diminished weight of the geographically-derived path or diminished weight of the camera-derived path when a respective reliability level is below a threshold level.

Abstract: A system, a method, and a computer program product for generating classification data of a sign. The method comprises obtaining map data of the sign, obtaining a map matched link and at least one parallel link associated with the sign based on the map data, determining presence data of at least one blocking link between the map-matched link and the at least one parallel link, wherein the at least one blocking link satisfies one or more of a heading criterion and a distance criterion. The method further comprises generating the classification data of the sign based on the presence data of the at least one blocking link.

Abstract: An object recognition method performed by an object recognition system includes: setting a first binarization area in a portion of a binarization target area of an image, and a first coefficient calculation area including the first binarization area and having an area wider than the first binarization area by a predetermined ratio; determining a first binarization coefficient on the basis of pixel values included in the first coefficient calculation area; performing binarization on the first binarization area through the determined first binarization coefficient; setting a second binarization area in a portion other than the first binarization area, and a second coefficient calculation area including the second binarization area and having an area wider than the second binarization area; determining a second binarization coefficient on the basis of pixel values included in the second coefficient calculation area; and performing binarization on the second binarization area through the determined second binariz

Abstract: A method and an apparatus for generating vehicle damage information are provided. The method includes: acquiring a damage area image of a target vehicle; performing image segmentation on the damage area image to obtain a first suspected damage area; inputting the damage area image to a pre-trained detection model to obtain a second suspected damage area, the detection model being configured to detect a location of the suspected damage area in the image; determining a damage image feature based on the first suspected damage area and the second suspected damage area; and inputting the damage image feature to a pre-trained classification model to generate a damage type, the classification model being configured to characterize a corresponding relationship between the image feature and the damage type.

Abstract: The present disclosure relates to an information processing apparatus, an information processing method, and a program capable of obtaining the accuracy of the parameter regarding the attitude of a plurality of viewpoints with higher accuracy. Provided is an information processing apparatus including: a plane estimator configured to estimate a plane on the basis of a first depth map, the first depth map being obtained on the basis of a plurality of captured images acquired by image-capturing at a plurality of viewpoints; and a correction unit configured to correct a parameter regarding an attitude of the plurality of viewpoints on the basis of comparison between the first depth map and the plane.

Abstract: The present disclosure relates to a method and an apparatus for measuring a distance using a vehicle-mounted camera, a storage medium, and an electronic device. The method includes: calibrating a camera based on camera calibration images to obtain a camera parameter; detecting parallel lane lines to obtain a vanishing point of the parallel lane lines according to the detected parallel lane lines; calculating a pitch angle of the camera according to the camera parameter and the vanishing point; determining information of an object to be detected in an image captured by the camera; and calculating a distance from the object to be detected to the camera and a size of the object to be detected according to the information of the object to be detected, the pitch angle of the camera, and the camera parameter.

Abstract: An information processing device, includes: a gesture detection unit that recognizes gestures by a user; an output information control unit that controls output information to a display unit; and a device control unit, wherein: if the gesture detection unit has detected that the user has raised a hand for a certain time period, then the output information control unit displays upon the display unit a plurality of candidates for selection in association with gestures for operation; and if the gesture detection unit has detected a predetermined gesture by the user, the device control unit considers that, among the candidates for selection displayed upon the display unit, a candidate corresponding to the gesture that has been detected has been selected.

Abstract: A vehicle control device includes a recognizer that is configured to recognize an object around a subject vehicle, a driving controller that is configured to control a speed or steering of the subject vehicle, and a predictor that is configured to predict that a predetermined vehicle will move to a front of the subject vehicle on a subject lane. The driving controller is configured to perform a behavior control in a case where it is predicted that the predetermined vehicle will move to the front of the subject vehicle on the subject lane and limits the vehicle behavior control in a case where it is predicted that the predetermined vehicle does not move to the front of the subject vehicle on the subject lane as compared with a case where it is predicted that the vehicle will move to the front of the subject vehicle on the subject lane.

Abstract: Disclosed is a road speed limit identification method. The road speed limit identification method includes: obtaining a driving image captured during driving of a moving object; setting a region of interest in the obtained driving image and generating a grayscale-processed image on the basis of an image of the region of interest; detecting a speed limit sign image from the grayscale-processed image; calculating a first brightness value of a number region, a second brightness value of a border region, and a third brightness value of an in-border region other than the number region in the detected speed limit sign image; and identifying a speed limit displayed on a speed limit sign on the basis of the plurality of calculated brightness values.

Abstract: A driving teaching device is provided. The driving teaching device for a vehicle includes a visual attraction portion and a confirmation determination portion. The visual attraction portion guides, as an attractive display, a visual line of a driver to a confirmation object to which a safety confirmation is to be executed by the driver. The confirmation determination portion determines whether the driver executes the safety confirmation to the confirmation object. The driving teaching device further includes a reaction determination portion and a feedback portion. The reaction determination portion determines a reaction degree of the driver to the attractive display. The feedback portion provides information based on the reaction degree determined by the reaction determination portion when the confirmation determination portion determines that the driver executes the safety confirmation to the confirmation object.

Abstract: An object detection system can identify a specific object in a two-dimensional image. A processor can receive the two-dimensional image with bounding boxes around objects. The processor can cause a point to appear in the two-dimensional image. The point can represent a position, in three-dimensional space, of the specific object. The processor can determine an existence of a condition. The condition can be that the point is enclosed by a plurality of bounding boxes. The processor can receive, in response to the existence of the condition, a depth image. The processor can determine, in response to the existence of the condition and based on information included in the depth image and a location of the point in the two-dimensional image, a specific bounding box that encloses the point. The processor can cause, based on a location of the specific bounding box, an indication of the specific object to be presented.

Abstract: Example-based affine registration is provided. In various embodiments, a plurality of training images is read. A predetermined affine transform is read for each of the plurality of training images. Each affine transform maps its associated image to a template. Weights are determined for each of the plurality of training images. The weights are determined to minimize a difference between the test image and a weighted linear combination of the training images. An affine transform is determined mapping the test image to the template by computing a weighted linear combination of the affine transforms using the weights.

Abstract: A vehicle exterior environment detection apparatus includes an image width calculator, a predicted distance calculator, and a relative distance calculator. The image width calculator calculates a first image width of a target vehicle on the basis of a first image. The predicted distance calculator calculates a first predicted distance to the target vehicle on the basis of the first image width. The relative distance calculator calculates a first reliability of the first image width, and, when the first reliability is higher than a predetermined threshold, calculates a first real width of the target vehicle on the basis of the first image width and the first predicted distance, updates a smoothed real width by performing smoothing processing on the basis of the first real width, and calculates a first distance to the target vehicle on the basis of the smoothed real width and the first image width.

Abstract: A server of an information processing system receives, from each of the vehicles, a signal detection location where a traffic signal is detected by an imaging unit of each of the vehicles, and travel information at the signal detection location, calculates, based on the information from each of the vehicles, a mean distance L from the signal detection location to the traffic signal, and a mean speed S at the signal detection location, and evaluate a risk of the traffic signal based on at least the mean distance L and the mean speed S. The server then provides attention information to the vehicle approaching the traffic signal having the risk higher than a prescribed value.

Abstract: A vehicle surrounding area monitoring device comprises a processor including a top perspective view image producing section taking images of a surrounding area of a vehicle and synthesizing the images into a top perspective view image and displaying the top perspective view image on a display. The processor further includes a vehicle running direction information receiving section receiving information on a direction in which the vehicle is running from a control device to control the vehicle to run frontward or rearward. The top perspective view image producing section produces a frontward top perspective view image of the vehicle and the surrounding area seen from a viewing point upward and rearward of the vehicle when the vehicle is running frontward and a rearward top perspective view image of the vehicle and the surrounding area seen from another viewing point upward and frontward of the vehicle when the vehicle is running rearward.

Abstract: A vehicle exterior environment recognition apparatus includes a position derivation unit, a grouping unit, and a speed derivation unit. The position derivation unit is configured to derive three-dimensional positions of respective blocks from an image received from an imaging device. The grouping unit is configured to group the respective blocks and to identify a three-dimensional object. The speed derivation unit is configured to make a determination as to whether a side of the three-dimensional object satisfies a determination condition that the side of the three-dimensional object is included in an end area situated on an end side of the image in a horizontal direction. The speed derivation unit is configured to derive the speed of the three-dimensional object in accordance with an end of the side of the three-dimensional object in a depth direction when the determination is made that the side of the three-dimensional object satisfies the determination condition.

Abstract: A system is provided for performing image processing. During operation, the system can obtain a video stream of a target object, and obtain, from the video stream, a plurality of images ranked according to a first sequence. The target object can be, e.g., a damage vehicle. The system can then extract a set of feature vectors corresponding to the plurality of images. The system may sequentially provide the set of feature vectors to a trained damage assessment image judgment model. Next, the system can apply the trained damage assessment image judgment model to determine whether each image in the plurality of images corresponds to a damage assessment image.

Abstract: Aspects of the disclosure relate to detecting an emergency vehicle. For instance, a plurality of images may be taken from a perspective of an autonomous vehicle. One or more gates representing a region of interest at a respective distance from the vehicle may be generated for the images. A plurality of lights may be detected within the one or more gates. A first candidate emergency vehicle may be identified from a detected plurality of lights in one or more gates of one of the images, and a second candidate emergency vehicle may be identified from a detected plurality of lights in one or more gates of another of the images. The first and second candidate emergency vehicles are determined to be the same emergency vehicle and to be active. An operational system of the autonomous vehicle is controlled based on the determination that the given emergency vehicle is active.

Abstract: A server device includes: a server communication unit configured to communicate with a vehicle, and receive fallen object avoidance information from the vehicle, the fallen object avoidance information including position information on a fallen object and information indicating whether an avoidance operation was performed by the vehicle for the fallen object; and a server control unit configured to determine, for the same fallen object that is present at the same position, whether the same fallen object should be avoided based on the fallen object avoidance information, and notify a first following vehicle that the same fallen object should be avoided when the server control unit determines that the same fallen object should be avoided, the first following vehicle being a vehicle that is traveling within a predetermined range behind the same fallen object.

Abstract: A system for creating a driving route of a vehicle includes: a vehicle selecting device to select a surrounding vehicle that is adjacent to a host vehicle; an intention determining device to determine an intention of the surrounding vehicle by using information including a location and a speed of the surrounding vehicle; a driving route predicting device to predict a driving route of the surrounding vehicle based on the determined intention of the surrounding vehicle; a map creating device to create a map by using the predicted driving route of the surrounding vehicle; and a driving route creating device to create a driving route of the host vehicle.

Abstract: According to an embodiment, an information processing apparatus includes a memory having computer executable components stored therein; and a processing circuit communicatively coupled to the memory. The processing circuit acquires a plurality of pieces of observation information of surroundings of a moving body, generates a plurality of pieces of attribute information of the surroundings of the moving body on the basis of the plurality of pieces of observation information, and sets a reliability of the attribute information of the surroundings of the moving body on the basis of correlation of the plurality of pieces of attribute information.

Abstract: A recognition apparatus includes an image acquisition unit configured to acquire an image obtained by photographing an object and a recognition processing unit configured to, when it is not clearly determined whether the object is a human being or an animal as a result of detecting the human being or the an animal in the acquired image using a full-body recognition dictionary of the human being and the animal, increase a certainty that the object is the animal to thereby detect the animal when the animal's head, face, or buttocks are detected in a range different from that of a human being within a detection range using a partial-body recognition dictionary, the partial-body recognition dictionary being for detecting the animal's head, face, or buttocks in the detection range in which the human being or the animal is detected.

Abstract: The present disclosure relates to systems and methods for road edge detection and mapping, for vehicle wheel identification and navigation based thereon, and for classification of objects as moving or non-moving. Such systems and methods may include the use of trained systems, such as one or more neural networks. Further, autonomous vehicle systems may incorporate aspects of one or more of the disclosed systems and methods.

Abstract: The present subject matter provides various technical solutions to technical problems facing advanced driver assistance systems (ADAS) and autonomous vehicle (AV) systems. In particular, disclosed embodiments provide systems and methods that may use cameras and other sensors to detect objects and events and identify them as predefined signal classifiers, such as detecting and identifying a red stoplight. These signal classifiers are used within ADAS and AV systems to control the vehicle or alert a vehicle operator based on the type of signal. These ADAS and AV systems may provide full vehicle operation without requiring human input. The embodiments disclosed herein provide systems and methods that can be used as part of or in combination with ADAS and AV systems.

Abstract: Aspects of the disclosure relate providing a lane change notification when a vehicle is to perform a lane change. One or more computing devices may generate and display a video, where the video is generated from a perspective of a virtual camera at a default position and default pitch. The one or more computing devices may receive an indication that the vehicle is to perform a lane change from a first lane to a second lane and adjust, after the vehicle receives the indication, the default position and default pitch of the virtual camera to an updated position further above the vehicle relative to ground than the default position and an updated pitch directed more towards the ground than the default pitch. The video may be generated and displayed from the perspective of the virtual camera at the updated position and updated pitch.

Abstract: A method for detecting changes in road information includes converting a captured road image and a projected road-layout map into first intermediate data and second intermediate data of a same feature space, respectively, and calculating the similarity between the captured road image and the projected road-layout map based on the first intermediate data and the second intermediate data Thereafter, the presence or the absence of changes in road information on the projected road-layout map is detected based on the calculated similarity.

Abstract: A vehicle control system includes an object placement portion in which an object can be placed, an automated driving controller configured to execute automated driving for automatically controlling at least one of acceleration or deceleration and steering of a vehicle, and an object placement controller configured to change the object placement portion from a first mode to a second mode in which the object placement portion is more easily used by an occupant of the vehicle than in the first mode in accordance with a control state of automated driving executed by the automated driving controller.

Abstract: A system, comprising a computer that includes a processor and a memory, the memory storing instructions executable by the processor to detect and locate an object by processing video camera data with a capsule network, wherein training the capsule network includes determining routing coefficients with a scale-invariant normalization function. The computer can be further programmed to receive the detected and located object.

Abstract: Embodiments for generating recommendations for user activity onboard a vehicle are provided. A first user and a second user onboard a vehicle are identified. A relationship between the first user and the second user is determined based on at least one information source associated with at least one of the first user and the second user. A traffic condition associated with the vehicle traveling to a destination is detected. A recommendation of an joint activity for the first user and the second user while onboard the vehicle is generated based on the determined relationship between the first user and the second user, the detected traffic condition, and the at least one information source.

Abstract: Systems and methods monitor driver behavior for vehicular fleet management in a fleet of vehicles using driver-facing imaging device. The systems and methods herein relate generally to vehicular fleet management for enhancing safety of the fleet and improving the performance of the fleet drivers, and further relate to monitoring the operation of fleet vehicles using one or more driver-facing imaging devices disposed in the fleet vehicles for recording activities of the fleet drivers and their passengers, storing information relating to the monitored activities, selectively generating warnings related to the monitored activities, and reporting the monitored activities to a central fleet management system for use in enhancing the safety of the vehicles of the fleet and for helping to improve the performance of the fleet drivers.

Abstract: A system, method and computer program product are provided for classifying at least one speed sign associated with a region. In an example embodiment, the method may include obtaining sensor data comprising speed limit data associated with the at least one speed sign. The method may further include obtaining map data associated with a segment of the region, wherein the map data comprises conditional speed limit data associated with a conditional speed limit sign linked with the segment. The method may further include comparing the speed limit data with the conditional speed limit data and classifying the at least one speed sign as one of a conditional speed sign or a non-conditional speed sign based on the comparison.

Abstract: A vehicle periphery display device includes: an acquisition portion acquiring a captured image obtained by imaging a periphery of a vehicle with an imaging portion; and a display processing portion causing a display image that is a stereoscopic image of the vehicle and the periphery of the vehicle to be displayed on a display portion on the basis of the captured image. The display processing portion causes at least one of a contour guide line representing a contour of the vehicle, and a predicted course guide line that is a trajectory drawn by the contour guide line according to movement of the vehicle to be included in the display image, and changes a position of at least one of the contour guide and predicted course guide lines such that the contour guide and predicted course guide lines are present above a road surface when the vehicle is turned.

Abstract: Among other things, one or more travel signals are identified by analyzing one or more images and data from sensors, classifying candidate travel signals into zero, one or more true and relevant travel signals, and estimating a signal state of the classified travel signals.

Abstract: Localization apparatuses and methods are disclosed where a localization apparatus extracts a feature of an object from an input image, generates an image in which the object is projected with respect to localization information of a device based on map data, and evaluates the localization information based on feature values corresponding to vertices included in a projection image.