Abstract: Architecture that detects entrances on building facades. In a first stage, scene geometry is exploited and the multi-dimensional problem is reduced down to a one-dimensional (1D) problem. Entrance hypotheses are generated by considering pairs of locations along lines exhibiting strong gradients in the transverse direction. In a second stage, a rich set of discriminative image features for entrances is explored according to constructed designs, specifically focusing on properties such as symmetry and color consistency, for example. Classifiers (e.g., random forest) are utilized to perform automatic feature selection and entrance classification. In another stage, a joint model is formulated in three dimensions (3D) for entrances on a given facade, which enables the exploitation of physical constraints between different entrances on the same facade in a systematic manner to prune false positives, and thereby select an optimum set of entrances on a given facade.

Abstract: Architecture that detects entrances on building facades. In a first stage, scene geometry is exploited and the multi-dimensional problem is reduced down to a one-dimensional (1D) problem. Entrance hypotheses are generated by considering pairs of locations along lines exhibiting strong gradients in the transverse direction. In a second stage, a rich set of discriminative image features for entrances is explored according to constructed designs, specifically focusing on properties such as symmetry and color consistency, for example. Classifiers (e.g., random forest) are utilized to perform automatic feature selection and entrance classification. In another stage, a joint model is formulated in three dimensions (3D) for entrances on a given facade, which enables the exploitation of physical constraints between different entrances on the same facade in a systematic manner to prune false positives, and thereby select an optimum set of entrances on a given facade.

Abstract: Architecture that detects entrances on building facades. In a first stage, scene geometry is exploited and the multi-dimensional problem is reduced down to a one-dimensional (1D) problem. Entrance hypotheses are generated by considering pairs of locations along lines exhibiting strong gradients in the transverse direction. In a second stage, a rich set of discriminative image features for entrances is explored according to constructed designs, specifically focusing on properties such as symmetry and color consistency, for example. Classifiers (e.g., random forest) are utilized to perform automatic feature selection and entrance classification. In another stage, a joint model is formulated in three dimensions (3D) for entrances on a given facade, which enables the exploitation of physical constraints between different entrances on the same facade in a systematic manner to prune false positives, and thereby select an optimum set of entrances on a given facade.

Abstract: Architecture that summarizes a large amount (e.g., thousands of miles) of street-level image/video data of different perspectives and types (e.g., continuous scan-type data and panorama-type data) into a single view that resembles aerial imagery. Polygons surfaces are generated from the scan patterns and the image data is projected onto the surfaces, and then rendered into the desired orthographic projection. The street-level data is processed using a distributed computing approach across cluster nodes. The collection is processed into image tiles on the separate cluster nodes representing an orthographic map projection that can be viewed at various levels of detail. Map features such as lower-level roads, that are at lower elevations than higher-level roads, and are hidden by higher-level overpassing roads, can be navigated in the map. With the summarized data, the maps can be navigated and zoomed efficiently.

Abstract: Architecture that summarizes a large amount (e.g., thousands of miles) of street-level image/video data of different perspectives and types (e.g., continuous scan-type data and panorama-type data) into a single view that resembles aerial imagery. Polygons surfaces are generated from the scan patterns and the image data is projected onto the surfaces, and then rendered into the desired orthographic projection. The street-level data is processed using a distributed computing approach across cluster nodes. The collection is processed into image tiles on the separate cluster nodes representing an orthographic map projection that can be viewed at various levels of detail. Map features such as lower-level roads, that are at lower elevations than higher-level roads, and are hidden by higher-level overpassing roads, can be navigated in the map. With the summarized data, the maps can be navigated and zoomed efficiently.

Abstract: Architecture that detects entrances on building facades. In a first stage, scene geometry is exploited and the multi-dimensional problem is reduced down to a one-dimensional (1D) problem. Entrance hypotheses are generated by considering pairs of locations along lines exhibiting strong gradients in the transverse direction. In a second stage, a rich set of discriminative image features for entrances is explored according to constructed designs, specifically focusing on properties such as symmetry and color consistency, for example. Classifiers (e.g., random forest) are utilized to perform automatic feature selection and entrance classification. In another stage, a joint model is formulated in three dimensions (3D) for entrances on a given facade, which enables the exploitation of physical constraints between different entrances on the same facade in a systematic manner to prune false positives, and thereby select an optimum set of entrances on a given facade.

Abstract: Architecture that detects entrances on building facades. In a first stage, scene geometry is exploited and the multi-dimensional problem is reduced down to a one-dimensional (1D) problem. Entrance hypotheses are generated by considering pairs of locations along lines exhibiting strong gradients in the transverse direction. In a second stage, a rich set of discriminative image features for entrances is explored according to constructed designs, specifically focusing on properties such as symmetry and color consistency, for example. Classifiers (e.g., random forest) are utilized to perform automatic feature selection and entrance classification. In another stage, a joint model is formulated in three dimensions (3D) for entrances on a given facade, which enables the exploitation of physical constraints between different entrances on the same facade in a systematic manner to prune false positives, and thereby select an optimum set of entrances on a given facade.

Abstract: Architecture that detects entrances on building facades. In a first stage, scene geometry is exploited and the multi-dimensional problem is reduced down to a one-dimensional (1D) problem. Entrance hypotheses are generated by considering pairs of locations along lines exhibiting strong gradients in the transverse direction. In a second stage, a rich set of discriminative image features for entrances is explored according to constructed designs, specifically focusing on properties such as symmetry and color consistency, for example. Classifiers (e.g., random forest) are utilized to perform automatic feature selection and entrance classification. In another stage, a joint model is formulated in three dimensions (3D) for entrances on a given facade, which enables the exploitation of physical constraints between different entrances on the same facade in a systematic manner to prune false positives, and thereby select an optimum set of entrances on a given facade.

Abstract: Architecture that summarizes a large amount (e.g., thousands of miles) of street-level image/video data of different perspectives and types (e.g., continuous scan-type data and panorama-type data) into a single view that resembles aerial imagery. Polygons surfaces are generated from the scan patterns and the image data is projected onto the surfaces, and then rendered into the desired orthographic projection. The street-level data is processed using a distributed computing approach across cluster nodes. The collection is processed into image tiles on the separate cluster nodes representing an orthographic map projection that can be viewed at various levels of detail. Map features such as lower-level roads, that are at lower elevations than higher-level roads, and are hidden by higher-level overpassing roads, can be navigated in the map. With the summarized data, the maps can be navigated and zoomed efficiently.

Abstract: An approach is provided for providing augmented reality based on tracking. Information, including location information, orientation information, or a combination thereof of a device is determined. A representation of a location indicated based, at least in part, on the information is determined. One or more items are selected to associate with one or more points within the representation. Display information is determined to be generated, the display information including the one or more items overlaid on the representation based, at least in part, on the one or more points.

Abstract: Architecture that detects entrances on building facades. In a first stage, scene geometry is exploited and the multi-dimensional problem is reduced down to a one-dimensional (1D) problem. Entrance hypotheses are generated by considering pairs of locations along lines exhibiting strong gradients in the transverse direction. In a second stage, a rich set of discriminative image features for entrances is explored according to constructed designs, specifically focusing on properties such as symmetry and color consistency, for example. Classifiers (e.g., random forest) are utilized to perform automatic feature selection and entrance classification. In another stage, a joint model is formulated in three dimensions (3D) for entrances on a given facade, which enables the exploitation of physical constraints between different entrances on the same facade in a systematic manner to prune false positives, and thereby select an optimum set of entrances on a given facade.

Abstract: An apparatus for enabling provision of collaboration of remote and on-site users of indirect augmented reality may include at least one processor and at least one memory including computer program code. The at least one memory and the computer program code may be configured, with the processor, to cause the apparatus to perform at least selecting a stored image including a virtual representation of a real world location based on position information and orientation information of a mobile terminal, causing provision of first visual content to be displayed at the mobile terminal based on the virtual representation, causing provision of second visual content to be displayed at a remote device based on the virtual representation, and enabling collaborative interaction between a user of the mobile terminal and a user of the remote device with respect to the first visual content and the second visual content. A corresponding method and computer program product are also provided.

Abstract: A method of recognizing features in a 3D environment includes using a sensor that collects a plurality of sensed data points, populating a strip histogram grid having a plurality of strips, each strip having a dx dimension and a dy dimension, by assigning each sensed data point to a strip in the strip histogram grid that has x, y and z dimensions that encompass the spatial coordinate information of the respective assigned sensed data point, and estimating the local ground plane for a strip in the strip histogram grid by using information on each sensed data point assigned to that strip and surrounding strips in the strip histogram grid. Further methods include extracting smooth surfaces, building segmentation, top down segmentation and bottom up segmentation.

Abstract: A method of extracting street and road data from a dataset obtained using LIDAR techniques to scan a terrestrial region of the earth's surface of interest to form the dataset. The method includes: converting the dataset into an implicit representation using a population function; converting the implicit representation into 2D point data which are supplied to an agglomerative Gaussian mixture decomposition module, the agglomerative Gaussian mixture decomposition module automatically and parsimoniously fitting the 2-D point data with a set of Gaussian components; and modeling a segment of a street grid in the dataset by Gaussian models and constraining the Gaussian models to align with each other and a dominant orientation of the streets in order to detect streets. Ray tracing techniques may be used to detect curbs and medians.

Abstract: In an embodiment, a grammar-based, cueing method of object recognition is disclosed. The method may include or comprise accessing cells that define a portion of a three-dimensional (3-D) scene, assigning occupation parameters to the cells to define a plurality of occupied cells and at least one vacant cell, and assigning localization parameters to the occupied cells based on the occupation parameters of their respective neighboring cells. The method may further include or comprise characterizing a plurality of the occupied cells as geometric cues based on their respective occupation and localization parameters, and identifying a target geometric shape associated with the geometric cues.

Abstract: A method of recognizing geometrically salient objects from sensed data points collected in a 3D environment includes using a sensor that collects a plurality of sensed data points each having spatial coordinate information in three dimensions x, y and z, populating a strip histogram grid having a plurality of strips, each strip having a z, dx and dy dimensions, wherein dx is a portion of an x dimension and dy is a portion of a y dimension of the strip histogram grid, by assigning each sensed data point to a strip that has x, y and z dimensions that encompass the spatial coordinate information of the respective assigned sensed data point, and segmenting the strip histogram grid into a plurality of segmented regions, each segmented region comprising one strip or a group of neighboring strips having similar attributes.

Abstract: An apparatus for enabling provision of collaboration of remote and on-site users of indirect augmented reality may include at least one processor and at least one memory including computer program code. The at least one memory and the computer program code may be configured, with the processor, to cause the apparatus to perform at least selecting a stored image including a virtual representation of a real world location based on position information and orientation information of a mobile terminal, causing provision of first visual content to be displayed at the mobile terminal based on the virtual representation, causing provision of second visual content to be displayed at a remote device based on the virtual representation, and enabling collaborative interaction between a user of the mobile terminal and a user of the remote device with respect to the first visual content and the second visual content. A corresponding method and computer program product are also provided.

Abstract: An approach is provided for providing augmented reality based on tracking. Information, including location information, orientation information, or a combination thereof of a device is determined. A representation of a location indicated based, at least in part, on the information is determined. One or more items are selected to associate with one or more points within the representation. Display information is determined to be generated, the display information including the one or more items overlaid on the representation based, at least in part, on the one or more points.