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.