Abstract: Aspects concern a method for point of interest (POI) detection clustering using image embeddings, the method including obtaining, using a neural network, the image embeddings from POI detections including portions of one or more images that are captured in an area of a map, in which at least one POI is detected, calculating an embedding distance between the obtained image embeddings, and recognizing texts included in the POI detections. The method further includes calculating an optical character recognition (OCR) distance between the recognized texts, calculating a final distance between the POI detections, based on the calculated embedding distance and the calculated OCR distance, and clustering the POI detections, based on the calculated final distance.

Abstract: Aspects concern a method for gathering image training data for training a machine learning model to detect features for vehicle navigation or vehicle control, comprising mounting a camera onto a vehicle or the driver of a vehicle, determining a location of the vehicle, determining a relevancy of the determined location for map data generation or vehicle control and recording a video with the camera if the determined relevancy is above a predetermined threshold and recording single images if the determined relevancy is below the predetermined threshold.

Abstract: A system configured for managing orders is disclosed. The system may include one or more processor(s) which may collect first 2D training image data; collect second 2D training image data; construct a 3D map for the geographical area based on the first training image data and the second training image data; determine a likelihood of a potential missing feature in the 3D map based on the first 2D training image data and the second 2D training image data; collect third 2D training image data comprising third map images of the geographical area acquired by the one or more image acquisition apparatus if the likelihood of the potential missing feature is above a predetermined threshold; and generate the road map based on the first 2D training image data, the second 2D training image data and the third 2D training image data.

Abstract: Aspects concern a method for generating map data, the method including: generating of a plurality of cells of a real space area, each cell representing a two-dimensional sub-space of the real space area, wherein each of the cells comprise at least one global positioning system (GPS) point, and wherein the real space area comprises a road network; determining a number of GPS points for each cell of the plurality of cells; determining a road network based on the numbers of GPS points using a Smoothed Particle Hydrodynamics (SPH) analysis, wherein the cells of the plurality of cells are particles of the SPH analysis and the number of GPS points per cell of the plurality of cells are a scalar of each cell of the plurality of cells in the SPH analysis; and comparing the road network determined using the SPH analysis with the road network of the real space area.

Abstract: Aspects concern a method for generating map data, the method including: generating of a plurality of cells of a real space area, each cell representing a two-dimensional sub-space of the real space area, wherein each of the cells comprise at least one global positioning system (GPS) point, and wherein the real space area comprises a road network; determining a number of GPS points for each cell of the plurality of cells; determining a road network based on the numbers of GPS points using a Smoothed Particle Hydrodynamics (SPH) analysis, wherein the cells of the plurality of cells are particles of the SPH analysis and the number of GPS points per cell of the plurality of cells are a scalar of each cell of the plurality of cells in the SPH analysis; and comparing the road network determined using the SPH analysis with the road network of the real space area.

Abstract: Aspects concern a method for gathering image training data for training a machine learning model to detect features for vehicle navigation or vehicle control, comprising mounting a camera onto a vehicle or the driver of a vehicle, determining a location of the vehicle, determining a relevancy of the determined location for map data generation or vehicle control and recording a video with the camera if the determined relevancy is above a predetermined threshold and recording single images if the determined relevancy is below the predetermined threshold.

Abstract: Aspects concern a method for generating map data, the method including: generating of a plurality of cells of a real space area, each cell representing a two-dimensional sub-space of the real space area, wherein each of the cells comprise at least one global positioning system (GPS) point, and wherein the real space area comprises a road network; determining a number of GPS points for each cell of the plurality of cells; determining a road network based on the numbers of GPS points using a Smoothed Particle Hydrodynamics (SPH) analysis, wherein the cells of the plurality of cells are particles of the SPH analysis and the number of GPS points per cell of the plurality of cells are a scalar of each cell of the plurality of cells in the SPH analysis; and comparing the road network determined using the SPH analysis with the road network of the real space area.