Abstract: Systems and methods for synchronization are provided. In some aspects, a method for synchronizing an image sensor is provided. The method includes receiving image data captured using an image sensor that is moving along a pathway, and assembling an image sensor trajectory using the image data. The method also includes receiving position data acquired along the pathway using a position sensor, wherein timestamps for the image data and position data are asynchronous, and assembling a position sensor trajectory using the position data. The method further includes generating a spatial transformation that aligns the image sensor trajectory and position sensor trajectory, and synchronizing the image sensor based on the spatial transformation.

Abstract: An approach is provided for lane width estimation from incomplete lane marking detections of a road lane. The approach, for example, involves generating one or more perpendicular lines respectively from location centers of one or more first lane marking detections. A respective lane marking detection represents at least a portion of a boundary of the road lane as a line delimited by two location data points in accordance with detections by at least one sensor device onboard at least one vehicle. The approach also involves identifying second lane marking detections that each respectively intersect one of the one or more perpendicular lines. The approach further involves selecting one or more candidate lane widths based on one or more respective distances from the location centers to the second lane marking detections. The approach further involves determining an estimated lane width of the road lane based on the one or more candidate lane widths.

Abstract: An approach is provided for reconstructing a road linear feature. The approach, for example, involves receiving two or more linear feature detections that respectively represent a linear feature of a road as a line segment delimited by two feature points. The approach also involves map matching the two or more linear feature detections to a road link segment of a geographic database. The approach further involves determining an orientation difference for each of the two or more linear feature detections based on an angle difference between each linear feature detection and a link orientation of the map matched road link segment. The approach further involves determining a feature orientation of the linear feature based on an aggregation of the orientation difference for each linear feature detection. The approach further involves constructing a representation of the linear feature based at least in part on the feature orientation.

Abstract: An approach is provided for using a machine learning model for identifying planar region(s) in an image. The approach involves, for example, determining the model for performing image segmentation. The model comprises at least: a trainable filter that convolves the image to generate an input volume comprising a projection of the image at different resolution scales; and feature(s) to identify image region(s) having a texture within a similarity threshold. The approach also involves processing the image using the model by generating the input volume from the image using the trainable filter and extracting the feature(s) from the input volume to determine the region(s) having the texture. The approach further involves determining the planar region(s) by clustering the image regions. The approach further involves generating a planar mask based on the planar region(s). The approach further involves providing the planar mask as an output of the image segmentation.

Abstract: An apparatus and method for encoding objects in a camera-captured image with a deep neural network pipeline including multiple convolutional neural networks or convolutional layers. After identifying at least a portion of the camera-capture image, a first convolutional layer is applied to the at least the portion of the camera-captured image and multiple subregion representations are pooled from the output of the first convolutional layer. One or more additional convolutions are performed. At least one deconvolution is performed and concatenated with the output of one or more convolutions. One or more final convolutions are performed. The at least the portion of the camera-captured image is classified as an object category in response to an output of the one or more final convolutions.

Abstract: Systems and methods for synchronization are provided. In some aspects, a method for synchronizing an image sensor is provided. The method includes receiving image data captured using an image sensor that is moving along a pathway, and assembling an image sensor trajectory using the image data. The method also includes receiving position data acquired along the pathway using a position sensor, wherein timestamps for the image data and position data are asynchronous, and assembling a position sensor trajectory using the position data. The method further includes generating a spatial transformation that aligns the image sensor trajectory and position sensor trajectory, and synchronizing the image sensor based on the spatial transformation.

Abstract: An approach is provided for providing dynamic model switching and/or model parameter switching (e.g., for object detection). The approach, for example, involves providing a plurality of machine learning models trained to detect one or more objects (e.g., vehicles, pedestrians, etc.) and/or road attributes (e.g., road hazards, road furniture, road signs, etc.). The approach also involves processing sensor data to determine at least one context (e.g., location), at least one use of the one or more road attributes, or a combination thereof. The approach further involves selecting at least one machine learning model of the plurality of machine learning models based on at least one context. The approach further involves providing the selected at least one machine learning model to detect the one or more objects and/or road attributes.

Abstract: An approach is provided for using a machine learning model for identifying planar region(s) in an image. The approach involves, for example, determining the model for performing image segmentation. The model comprises at least: a trainable filter that convolves the image to generate an input volume comprising a projection of the image at different resolution scales; and feature(s) to identify image region(s) having a texture within a similarity threshold. The approach also involves processing the image using the model by generating the input volume from the image using the trainable filter and extracting the feature(s) from the input volume to determine the region(s) having the texture. The approach further involves determining the planar region(s) by clustering the image regions. The approach further involves generating a planar mask based on the planar region(s). The approach further involves providing the planar mask as an output of the image segmentation.

Abstract: A method map matches probe data to a candidate road segment or node. Methods may include: searching for candidate road segments or nodes for each probe data point to be matched to, where searching for candidate road segments or nodes includes: searching within a predefined radius of each probe data point for road segments or nodes and in response to no road segments or nodes being found within the predefined radius of the respective probe data point, iteratively increasing the predefined radius and searching again until a predefined maximum radius is reached or at least two road segment candidates or node candidates are found; map matching each probe data point to a respective road segment candidate or node candidate based on the road segment candidate or node candidate found in the search; and generating a path based on the map matched probe data points from a respective probe.

Abstract: An approach is provided for estimating a real-world depth information from a monocular image. The approach, for example, involves determining a vanishing point of the monocular image captured by a camera. The approach also involves generating a vanishing point ray from an optical center of the camera through the vanishing point on an image plane of the monocular image to infinity. The approach further involves generating a center line ray from the optical center through a geometric center of the image plane to a feature line that is parallel to the vanishing point ray at a lateral distance. The approach further involves generating a feature ray from the optical center through a location of the feature on the image plane to the feature line. The approach further involves computing the real-world distances of the feature based on image coordinates of the rays, lines, angles derived therefrom, and a known pixel-wise distance of the monocular image.

Abstract: An approach is provided for estimating a real-world depth information from a monocular image. The approach, for example, involves determining a vanishing point of the monocular image captured by a camera. The approach also involves generating a vanishing point ray from an optical center of the camera through the vanishing point on an image plane of the monocular image to infinity. The approach further involves generating a center line ray from the optical center through a geometric center of the image plane to a feature line that is parallel to the vanishing point ray at a lateral distance. The approach further involves generating a feature ray from the optical center through a location of the feature on the image plane to the feature line. The approach further involves computing the real-world distances of the feature based on image coordinates of the rays, lines, angles derived therefrom, and a known pixel-wise distance of the monocular image.

Abstract: A method, apparatus, and computer program product are described herein for determining pedestrian behavior profiles for road segments of a road network, from those pedestrian behavior profiles, determining the likelihood that an adverse pedestrian event will occur, and determining the action to be taken in response. Example embodiments may provide a mapping system including: a memory having map data; and processing circuitry. The processing circuitry may be configured to: receive data points associated with pedestrian movement; associate pedestrian movement with a road segment; determine, based on the data points, a pedestrian behavior profile for the road segment; and in response to the pedestrian behavior profile for the road segment indicating a likelihood for an adverse pedestrian event that satisfies a predetermined likelihood, cause at least one action in response thereto.

Abstract: An apparatus and method for encoding objects in a camera-captured image with a deep neural network pipeline including multiple convolutional neural networks or convolutional layers. After identifying at least a portion of the camera-capture image, a first convolutional layer is applied to the at least the portion of the camera-captured image and multiple subregion representations are pooled from the output of the first convolutional layer. One or more additional convolutions are performed. At least one deconvolution is performed and concatenated with the output of one or more convolutions. One or more final convolutions are performed. The at least the portion of the camera-captured image is classified as an object category in response to an output of the one or more final convolutions.

Abstract: A method map matches probe data to a candidate road segment or node. Methods may include: searching for candidate road segments or nodes for each probe data point to be matched to, where searching for candidate road segments or nodes includes: searching within a predefined radius of each probe data point for road segments or nodes and in response to no road segments or nodes being found within the predefined radius of the respective probe data point, iteratively increasing the predefined radius and searching again until a predefined maximum radius is reached or at least two road segment candidates or node candidates are found; map matching each probe data point to a respective road segment candidate or node candidate based on the road segment candidate or node candidate found in the search; and generating a path based on the map matched probe data points from a respective probe.

Abstract: A method, apparatus, and computer program product are described herein for determining pedestrian behavior profiles for road segments of a road network, from those pedestrian behavior profiles, determining the likelihood that an adverse pedestrian event will occur, and determining the action to be taken in response. Example embodiments may provide a mapping system including: a memory having map data; and processing circuitry. The processing circuitry may be configured to: receive data points associated with pedestrian movement; associate pedestrian movement with a road segment; determine, based on the data points, a pedestrian behavior profile for the road segment; and in response to the pedestrian behavior profile for the road segment indicating a likelihood for an adverse pedestrian event that satisfies a predetermined likelihood, cause at least one action in response thereto.