An electronic device displays a representation of a field of view of a camera that includes a view of a three-dimensional space. The representation of the field of view is updated over time based on changes to current visual data detected by at least one of the one or more cameras. Movement of the electronic device moves the field of view of the camera in a first direction. While detecting the movement, the electronic device: updates the representation of the field of view in accordance with the movement; identifies one or more elements in the representation of the field of view that extend along the first direction; and, based at least in part on the determination of the one or more elements, displays, in the representation of the field of view, a guide that extends in the first direction and that corresponds to one of the identified elements.

A road surface management device according to an aspect of the present disclosure includes: at least one memory configured to store instructions; and at least one processor configured to execute the instructions to: identify a section in which an image is captured, among a plurality of sections obtained by dividing a traveling road of an airport, based on positional relationships between the plurality of sections and signs, and signs in the image included in sensor information collected on the traveling road; detect an abnormality of the traveling road in the identified section based on the collected sensor information; and output the detected abnormality in association with the identified section.

Systems and methods for automated detection of changes in extent of structures using imagery are disclosed, including a non-transitory computer readable medium storing computer executable code that when executed by a processor cause the processor to: align an outline of a structure at a first instance of time to pixels within an image depicting the structure, the image captured at a second instance of time; assess a degree of alignment between the outline and the pixels within the image depicting the structure, using a machine learning model to generate an alignment confidence score; determine an existence of a change in extent of the structure based upon the alignment confidence score indicating that the outline and the pixels within the image are not aligned; identify a shape of the change in extent of the structure; and store the shape of the change in extent of the structure.

Provided are a road network extraction method, a device, and a storage medium, which relate to the technical field of artificial intelligence and, in particular, to the fields of image processing, computer vision, and the like and are specifically applicable to scenarios such as intelligent transportation and a smart city. A specific implementation scheme includes: extracting a first road network of a target region according to user trajectories of the target region; extracting a second road network of the target region according to a satellite aerial image of the target region; and extract a target road network of the target region according to the first road network, the second road network, and the user trajectories. Efficient and accurate road network extraction can be achieved through techniques in embodiments of the present disclosure.

According to some embodiments, a system, method and non-transitory computer-readable medium are provided comprising an imagery data source storing image data from a plurality of images; a ground point module; a memory storing program instructions; and a ground point processor, coupled to the memory, and in communication with the ground point module and operative to execute the program instructions to: receive image data for an area of interest (AOI); generate a digital surface map from the received image data, wherein the digital surface map includes an elevation value for each of a plurality of points on the digital surface map; generate a ground point sampling based on the elevation values for the plurality of points on the digital surface map; generate an image boundary sampling based on elevation values for the plurality of points along a plurality of edges of the area of interest; and interpolate the generated ground point sampling and the image boundary sampling to generate a digital terrain map. Numerous other aspects are provided.

A method is provided for generation of map geometry through rasterization of probe data over time, where the generated map geometry can be used for map element generation. Methods may include: receiving probe data from a plurality of probe apparatuses within a geographic area where the probe data includes location information and time information; rasterizing the received probe data to generate an image corresponding to the probe data associated with the geographic area, where each pixel of the image includes a property representing at least one component of the probe data; processing the image to obtain one or more map elements; and updating a map database with the one or more map elements.

Provided are a method of individual tree crown segmentation from airborne LiDAR data using a novel Gaussian filter and energy function minimization. First, a dual Gaussian filter was designed with automated adaptive parameter assignment and a screening strategy for false treetops. This preserved the geometric characteristics of sub-canopy trees while eliminating false treetops. Second, anisotropic water expansion controlled by the energy function was applied to accurate crown segmentation. This utilized gradient information from the digital surface model and explored the morphological structures of tree crown boundaries as analogous to the maximal valley height difference from surrounding treetops. We demonstrate the generality of our approach using seven diverse plots in the subtropical Gaofeng Forest, China, coupled with ground verification. Our approach enhanced the detection rate of treetops and ITC segmentation relative to the marked-control watershed method, especially in complicated intersections of multiple crowns.

Remote sensing and social sensing for flood mapping is provided by identifying where floodwater is present in an image of a location affected by a flooding event; identifying a social media post posted on a social media platform from the location and associated with the flooding event; and overlaying the image with the social media post. In some embodiments, the remote and social sensing includes one or more of: generating a permanent water mask identifying where permanent water is located at the location, and applying the permanent water mask to the image to differentiate the floodwater from permanent water for the location; identifying where the social media post was posted from; and overlaying the image with the social media post includes positioning a photograph included in the social media post for display with the image where a subject of the photograph is located at the location.

A method is provided for automatically creating road and lane geometry from images representing probe data within a geographical area using graph estimation. Methods may include: receiving a rasterized image representative of map geometry within a geographic area, where each pixel of the rasterized image includes a property representing at least one feature of the map geometry; identifying pixels within the rasterized image corresponding to nodes of one or more map elements as node pixels; determining, for a respective node pixel, presence of a next node based on the at least one property of the respective node pixel; determining for the respective node pixel, a location corresponding to the next node based on the at least one property of the respective node pixel; generating, from a sequence of node pixels, at least one map element; and updating a map in a map database with the at least one map element.

Computer-implemented methods and systems for identifying topographic features that optimises and subsequently implements a machine learning model to automatically classify and extract topographic features from a set of target imagery are described herein. In particular, the optimised machine learning model creates heat maps from the target imagery corresponding to each class of feature, wherein the intensity of each pixel indicates whether a certain type of feature is present. The resulting heat maps are then processed to transform each pixel, specifically those identifying a topographic feature, into a geospatial vector.