Abstract: The disclosure relates to a method for calibrating parameters of a LiDAR sensor and a camera by considering characteristics of LiDAR data. A data generation apparatus extracts one frame of an image captured by a camera and one frame of point cloud data acquired by a LiDAR sensor, identifies feature points of a calibration board included in each of the extracted image and the extracted frame of the LiDAR sensor, and performs calibration of the camera and the LiDAR sensor based on the identified feature points. Performing the calibration includes generating a target plane by applying a RANSAC algorithm based on the feature points of the calibration board, and projecting the point cloud onto the target plane by performing a perspective projection.

Abstract: The disclosure relates to a server and a calibration method for performing calibration between a camera sensor and a LiDAR sensor. The server includes at least one processor configured to acquire an image from a camera and point cloud data from a LiDAR sensor, extract feature points of a calibration board included in the image and the point cloud data, and perform calibration based on the feature points. The processor generates a target plane by using a predetermined RANSAC algorithm, and projects the point cloud data onto the target plane by using perspective projection or orthogonal projection according to a relationship between a ray direction of the LiDAR sensor and a normal vector of the target plane. The processor further optimizes rotation and translation parameters by using a Particle Swarm Optimization (PSO) algorithm. This enables improved calibration accuracy, reduced sensitivity to noise, and robust operation in various environments.

Abstract: The present invention proposes a method for automatically performing calibration between a camera and a LiDAR using a calibration board. The method may include: detecting flat regions corresponding to the calibration board from each of two or more point cloud data acquired by a LiDAR; identifying regions corresponding to the calibration board from each of two or more images captured by a camera at the time the respective point cloud data was acquired, and matching the identified regions with the flat regions for estimating initial positions of the calibration board in three-dimensional coordinates; registering coordinates of the initial positions of the calibration board with coordinates of the flat regions; and determining a pose of the camera based on the registered coordinates.

Abstract: The present invention proposes a method for optimizing parameters among multiple cameras using the coordinates of point cloud data obtained from a LiDAR. The method may include: receiving images captured by a plurality of cameras and, simultaneously, first point cloud data obtained from the LiDAR corresponding to the images; estimating parameters between the pre-stored map and the LiDAR by mapping the first point cloud data to second point cloud data included in a pre-stored map; estimating image coordinates corresponding to coordinates of at least one of the first and second point cloud data based on the estimated parameters by projecting at least one of the first and second point cloud data onto the plurality of images; and optimizing the parameters among the plurality of cameras based on an error between the estimated image coordinates and predefined target coordinates on the image corresponding to the estimated image coordinates.

Abstract: The present disclosure relates to a method for optimizing parameters between a LiDAR and a camera, considering image distortion of the camera. The method may include: acquiring first parameters by projecting first point cloud data acquired from a LiDAR onto an image captured by a camera, by a map generation device; acquiring second parameters modified by optimizing the acquired first parameters while taking into account the image distortion, by the map generation device; calculating a first error between the first point cloud data, which is obtained based on the first parameters, and target point cloud data, and a second error between second point cloud data, which is obtained based on the second parameters, and the target point cloud data, by the map generation device; and determining the second parameters as optimized parameters when the first error is greater than the second error, by the map generation device.

Abstract: Proposed is a method of generating learning data for traffic facilities, which can facilitate recognition of traffic facilities. The method includes the steps of: collecting, by a learning data generation unit, traffic facility sample images; generating, by the learning data generation unit, at least one processed image by processing the collected traffic facility sample images to be recognized as images captured by a camera installed in a vehicle; and generating, by the learning data generation unit, learning data by inserting a background into the generated at least one processed image.

Abstract: Proposed is a multi-sensor synchronization method for synchronizing operation timing and time of each of multiple sensors using signals received from Global Positioning Systems (GPSs). The method may include the steps of: receiving, by a synchronization device, a reference signal for synchronizing a plurality of sensors from a Global Positioning System (GPS) device; generating, by the synchronization device, a trigger signal for each of the plurality of sensors based on the reference signal; recording, by the synchronization device, a time stamp for the trigger signal on the basis of time information included in the reference signal; and transmitting, by the synchronization device, the trigger signal including the time information recorded in the time stamp to each of the plurality of sensors.

Abstract: A trajectory correction method may include the steps of: correcting, by a map generation device, an error generated due to a change in position targeting 3D point cloud data collected in real time through a LiDAR, of which a position changes in real time; estimating, by the map generation device, an expected trajectory (odometry) related to the change in position on the basis of the corrected 3D point cloud data; applying, by the map generation device, curve fitting to the estimated expected trajectory; and mapping, by the map generation device, the expected trajectory before the curve fitting targeting the expected trajectory to which the curve fitting is applied.

Abstract: Proposed is a calibration method for a camera and a lidar using a calibration board having a specific pattern. The method may include extracting one frame for an image captured by a camera and point cloud data acquired by a lidar, by a data generator, identifying a feature point for a calibration board included in one extracted frame for the image and the lidar, by the data generator, and performing calibration for the camera and the lidar based on the identified feature point, by the data generator. The present method is a technology developed with support from the Ministry of Trade, Industry and Energy/Korea Planning and Evaluation Institute of Industrial Technology (Project No. 20022003/Project name-Automotive industry technology development project/Project name-Development of industrial autonomous driving and safety assurance technology based on longitudinal and lateral interconnection).

Abstract: Proposed is a method of generating a map using an aviation LiDAR for effectively generating a 3D map using point cloud data acquired from the LiDAR installed in an aviation device. The method includes the steps of: receiving, by a map generation unit, point cloud data acquired from a LiDAR installed in an aviation device; projecting, by the map generation unit, a top-view of the received point cloud data; and generating a map, by the map generation unit, by scanning the projected point cloud data in a direction perpendicular to the ground.

Abstract: Proposed is a calibration method for a lidar and an IMU using features according to the shape of a specific object included in point cloud data. The method may include placing point cloud data acquired by a lidar mounted on a vehicle on a predefined world coordinate system, by a data generator, extracting a region to be used for calibration from the placed point cloud data, by the data generator, identifying at least one object included in the extracted region, by the data generator, and performing calibration on the point cloud data by fitting point cloud included in the at least one identified object to a pre-stored model, by the data generator. The present method is a technology developed with support from the Ministry of Land/KAIA (Project No. RS-2021-KA160637).

Abstract: Proposed is a map updating method for updating a map using data acquired from other sensors for regions with low global positioning system (GPS) signal sensitivity on a precision road map generated based on GPS information. The method may include loading, by a data generating device, a reference map generated based on location information acquired by a global positioning system (GPS) device and first point cloud data acquired from a first light detection and ranging (LiDAR) and updating, by the data generating device, the reference map based on second point cloud data acquired from a second LiDAR mounted on a vehicle traveling on a path of the reference map.

Abstract: A lane extraction method uses projection transformation of a 3D point cloud map, by which the amount of operations required to extract the coordinates of a lane is reduced by performing deep learning and lane extraction in a two-dimensional (2D) domain, and therefore, lane information is obtained in real time. In addition, black-and-white brightness, which is most important information for lane extraction on an image, is substituted by the reflection intensity of a light detection and ranging (LiDAR) sensor so that a deep learning model capable of accurately extracting a lane is provided. Therefore, reliability and competitiveness is enhanced in the field of autonomous driving, the field of road recognition, the field of lane recognition, and the field of HD road maps for autonomous driving, and the fields similar or related thereto, and more particularly, in the fields of road recognition and autonomous driving using LiDAR.

Abstract: Proposed is a method for estimating the distance to and the location of an autonomous vehicle by using a mono camera, and more particularly, a method that enables information necessary for autonomous travel to be efficiently acquired using a mono camera and LiDAR. In particular, the method can acquire sufficiently reliable information in real time without using expensive equipment, such as a high-precision GPS receiver or stereo camera, required for autonomous travel. Consequently, the method may be widely used in ADAS, such as for semantic information recognition for autonomous travel, estimation of the location of an autonomous vehicle, calculation of vehicle-to-vehicle distance, or the like, even without the use of GPS, and furthermore, a camera capable of performing the same functions can be developed by developing software through the use of the corresponding data.

Abstract: Proposed is a GPS error correction method performed through comparison of three-dimensional HD-maps in a duplicate area, and more particularly, a method that can calculate a correction value for a GPS error by comparing three-dimensional HD-maps of a corresponding duplicate area when the duplicate area is generated on a GPS route in the process of acquiring raw data to be used in a HD-map for autonomous driving. Particularly, in the method, an accurate correction value for the GPS error can be calculated by comparing three-dimensional point cloud data acquired by utilizing basically installed LiDAR, an Inertial Measurement Unit (IMU) and the like, without using expensive equipment such as a plurality of high-precision GPS receivers, stereo cameras or the like.

Abstract: Proposed are a method of synchronizing a rotary LiDAR and a camera, and a device thereof. The synchronization device may include a LiDAR, a camera, and a synchronization control unit. The method of synchronizing a LiDAR and a camera may comprise the steps of: outputting a sample at every predetermined output cycle while rotating, by the LiDAR; deriving a trigger timing that is a time estimated for the LiDAR to rotate from a current position to a trigger target on the basis of the sample, by the synchronization control unit; and outputting a trigger signal to the camera after a time indicated by the trigger timing elapses, by the synchronization control unit. The sample may include a rotation angle indicating the current position of the LiDAR, and the trigger target may indicate a virtual direction in which the center of the angle of view of the LiDAR matches that of the camera.

Abstract: A method of collecting road sign information using a mobile mapping system, which can collect information on the markings on the road in real-time and map the information to a high definition map using the mobile mapping system including a remote sensing device and a navigation device is disclosed. Particularly, the system may collect correct road marking information in real-time by extracting objects and attributes from successive images on the basis of deep learning and map the road marking information to a high definition map, and remarkably improve accuracy of recognizing the road marking information. Accordingly, reliability and competitiveness may be enhanced in the autonomous driving field, the road recognition field, the high definition road map field for autonomous driving, and the fields similar or related thereto.