A method for contact-free axle counting of a vehicle on a road, including a step of reading in first image data and reading in second image data, wherein the first image data and/or the second image data represent image data provided to an interface by an image data recording sensor arranged on a side of the road. The first image data and/or the second image data comprise an image of the vehicle. The first image data and/or the second image data is processed in order to obtain processed first image data and/or processed second image data. By using the first image data and/or the second image data in a substep of detecting, at least one object is detected in the first image data and/or the second image data, and wherein object information is provided representing the object and assigned to the first image data and/or the second image data.

A system may be configured to perform label recollection, e.g., by automatically snapping, via a trained ML model, a set of vector labels by aligning one or more of the labels to an image, the alignment being performed at a quality that satisfies a criterion. Before this automatic snapping or matching of vectorized labels with reference imagery, this ML model may obtain training data from an output of another trained ML model. In another context, a computer-implemented method is disclosed for creating training data that better aligns labels with corresponding image features. This training data, created with reduced effort yet increased quality, may then be fed into to existing models, resulting in an automated pipeline.

A device includes: an image data receiving component operable to receive multiband image data of a geographic region; a surface index generation component operable to generate a surface index based on at least a portion of the received multiband image data; a classification component operable generate a land cover classification based on the surface index; a segment data receiving component operable to receive segment data relating to at least a portion of the geographic region; a zonal statistics component operable generate a segment land cover classification based on the land cover classification and the segment data; a feature data receiving component operable to receive feature data; a feature index generation component operable to generate a feature index based on the received feature data; and a catalog component operable to generate a segment feature index based on the feature index and the segment land cover classification.

The present invention discloses an artificial intelligence (AI)-based automatic generation method for an urban road network. According to the method, an anchor point distribution model is constructed by means of machine learning. Anchor points are distributed within a planning range where a boundary is a secondary trunk road. A road center line layout scheme set is generated by means of rectangular expansion. A feasible scheme set is screened out based on a rule base translated from specifications related to urban planning road, a road network scheme set is further automatically generated, and finally, a scheme is outputted to a two-dimensional interaction display device for simulated display. The present invention realizes a road network design by using a combination of machine learning and rules of the urban planning field. The present invention provides a simple and efficient automatic generation method for an urban road network. By means of the present invention, a plurality of schemes can be generated within a short time, which provide an efficient and visualized reference for the design and the practice of AI urban planning.

The disclosure relates to a method and an arrangement for assessing the roadway surface being driven on by a vehicle. In a method according to the disclosure, on the basis of at least one image recorded with a camera that is present on the vehicle, the roadway surface being driven on by the vehicle is classified using a classifier. The classifier is trained on the basis of image features that are extracted from the at least one image, wherein a plurality of image details are defined in the at least one image. The extraction of image features is performed independently for each of these image details.

A system and a method for real-time detection of a moving object on a travel path in a geographical area is provided. The system and method may also be used to track such a moving object in real-time. The system includes an image capturing device for capturing successive images of a geographical area, a geographical reference map comprising contextual information of the geographical area, and a processor configured to calculate differences between successive images to detect, in real-time, a moving object on the travel path. The method includes capturing successive images of the geographical area using the image capturing device, geo-registering at least some of the successive images relative to the geographical reference map, and calculating differences between the successive images to detect, in real-time, an object.

A system for training simultaneous localization and mapping (SLAM) models, including a camera, mounted in a vehicle and in communication with an image server via a cellular connection, that captures images labeled with a geographic position system location and a timestamp, and uploads them to an image server, a storage device that stores geographical maps and images, and indexes the images geographically with reference to the geographical maps, an images server that receives uploaded images, labels the uploaded images with a GPS location and a timestamp, and stores the uploaded images on the storage device, and a training server that trains a SLAM model using images labeled with a GPS location and a timestamp, wherein the SLAM model (i) receives an image as input and predicts the image location as output, and/or (ii) receives an image having error as input and predicts a local correction for the image as output.

A method and apparatus for identifying an object are disclosed. The method includes: performing linear feature detection on an image to be identified by using a linear feature detecting method to obtain detected linear features, wherein the linear feature detection method transforms detection of linear features in an image space to detection of extremal points in another space and assigns larger weights to continuous image points than to discrete image points during the transformation by using a continuous cluster factor; and identifying an object to be identified from the detected linear features by considering characteristics of the object to be identified. The method and apparatus for identifying an object of the invention, when used to detect and identify weak linear objects in high resolution remote sensing images, can effectively suppress the system noise and ambient noise, thereby successfully identifying the interested object and avoiding false alarms. Moreover, short line segments can also be identified.

A method to detect a roadway edge includes calculating a first likelihood of a roadway edge from an aerial image of a roadway by shifting a centerline of the roadway perpendicular to the centerline and overlapping the centerline with image gradients. A second likelihood of the roadway edge is determined using a vehicle telemetry fitting a probability distribution to telemetry points along the roadway. The first likelihood of the roadway edge and the second likelihood of the roadway edge are fused to identify a final likelihood of the roadway edge.

A system for vector extraction comprising a vector extraction engine stored and operating on a network-connected computing device that loads raster images from a database stored and operating on a network-connected computing device, identifies features in the raster images, and computes a vector based on the features, and methods for feature and vector extraction.