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.

An approach is provided for detecting and map-coding a tunnel based on probes and image data. The approach involves, for example, identifying a gap in probe data collected from one or more location sensors of a plurality vehicles. The gap represents a probe gap segment along which at least one probe point of the probe data does not occur or occurs below a threshold number. The approach also involves retrieving image data depicting a geographic area based on location coordinate data associated with the gap. The approach further involves processing the image data to identify one or more end points of a road network depicted in the image data. The approach further involves locating a tunnel start point and/or a tunnel end point based on the one or more endpoints. The approach further involves providing the tunnel start point and/or the tunnel end point as a map data output.

This specification describes systems and methods for refining point cloud data. Methods can include receiving point cloud data for a physical space, iteratively selecting points along an x, y, and z dimension, clustering the selected points into 2D histograms, determining a slope value for each 2D histogram, and removing, based on the slope value exceeding a predetermined value, points from the point cloud data. Methods can also include iteratively voxelizing each 2D histogram into predetermined mesh sizes, summating points in each voxelized 2D histogram, removing, based on determining the summation is below a predetermined sum value, points from the point cloud data, keeping, based on determining that a number of points in each voxelized 2D histogram exceeds a threshold value, a center point, selecting, for each histogram, a point, identifying, nearest neighbors in the point cloud data, removing the identified nearest neighbors from the data, and returning remaining points.

Provided herein is a method for quantifying and measuring human mobility within defined geographic regions and sub-regions. Methods may include: identifying sub-regions within a region; identifying static information associated with the sub-regions from one or more static information sources; obtaining dynamic information associated with the sub-regions from one or more dynamic information sources; determining correlations between elements of the static information associated with a respective sub-region and elements of the dynamic information associated with the respective sub-regions; generating a mobility score for the respective sub-region based, at least in part, on the correlations between the elements of the static information and the elements of the dynamic information associated with the respective sub-region; and providing the mobility score to one or more clients for guiding an action relative to the mobility score.

Systems and methods of automating the generation of a correction of an estimate of an elevation of a digital elevation model (DEM) of the bare earth under forest canopy. The disclosed embodiments facilitate generation of a more accurate DEM in areas of canopy coverage (where the input X-band DSM cannot see the ground) to estimate both the canopy height and the associated DEM. In some embodiments, the result of computationally correcting an estimate of an original DEM is a modified DEM. The method of correcting an estimate of an original DEM utilizes a pair of P-band radar images, an original DEM overlapping the same scene as the P-band radar images, at least one common, uniquely-identifiable point in the P-band radar images, and a definition of a geographical area surrounding the common, uniquely identifiable point over which the elevation correction is applicable.

Computer vision systems and methods for detecting power line hazards from imagery are provided. The system obtains at least one image from an image database having an object and/or a structure present therein, and generates a digital surface model (DSM), a vegetation mask, and a three-dimensional (3D) power line model based on the obtained image. The system generates a digital line model based on the 3D power line and a risk distance indicative of a distance between the 3D power line and vegetation proximate to the 3D power line, and also generates a digital tree model. The system generates a digital difference model based on an intersection of the digital line model and the digital tree model, identifies sections of a power line within a risk distance of vegetation located proximate to the power line based on the digital difference model, and generates a vegetation risk report based on the identified sections of the power line, the predetermined 2D risk distance, a predetermined 3D risk distance, and an elevation risk distance.

This document describes techniques, apparatuses, and systems for enabling multispectral object-detection with thermal imaging. A thermal sensor, a multispectral stereo camera system, and an illumination system are used in combination to provide a multispectral object-detection system for use with safety or driving systems for autonomous and semi-autonomous vehicles. The illumination system can provide illumination for the stereo camera system and serve as a range-finder that can determine a distance between the stereo camera system and an object in the system's field-of-view. The stereo camera system can include one or more of various camera or sensor technologies, including infrared or near-infrared, thermal imaging, or visible light. The system can be used to detect objects in the field-of-view, determine a distance to the object, and estimate the object's size and relative motion. The system can reduce costs and resource usage while enabling accurate, high-quality object-detections for safety and autonomous or semi-autonomous control.

The present disclosure pertains generally to image feature extraction. Both transfer-learning and multi-task training approaches are considered. In one example, a machine learning model is trained to perform a geographic classification task of distinguishing between images captured in different geographic regions based on their visual content. In another example, a machine learning model is trained to perform an order recognition task of determining information about the order of an image sequence based on its visual content, where the order of the image sequence may be different than the order in which its constituent images were captured. A further example combines the two approaches. The knowledge gained by the ML model in learning one or more such tasks can be applied to a desired image recognition task, such as image segmentation, structure detection or image classification, e.g. with a pre-training/fine-tuning framework or a multi-task learning framework.

Provided herein is a method for quantifying and measuring human mobility within defined geographic regions and sub-regions. Methods may include: identifying sub-regions within a region; identifying static information associated with the sub-regions from one or more static information sources; obtaining dynamic information associated with the sub-regions from one or more dynamic information sources; determining correlations between elements of the static information associated with a respective sub-region and elements of the dynamic information associated with the respective sub-regions; generating a mobility score for the respective sub-region based, at least in part, on the correlations between the elements of the static information and the elements of the dynamic information associated with the respective sub-region; and providing the mobility score to one or more clients for guiding an action relative to the mobility score.

A system for incorporating geographical data into a map-related system, adding objects being tracked while moving within a specific geographic area and automatically analyzing their movement characteristics; wherein the tracking is done by visual means from a sky-borne platform.