Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for scalable three-dimensional (3-D) object recognition in a cross reality system. One of the methods includes maintaining object data specifying objects that have been recognized in a scene. A stream of input images of the scene is received, including a stream of color images and a stream of depth images. A color image is provided as input to an object recognition system. A recognition output that identifies a respective object mask for each object in the color image is received. A synchronization system determines a corresponding depth image for the color image. A 3-D bounding box generation system determines a respective 3-D bounding box for each object that has been recognized in the color image. Data specifying one or more 3-D bounding boxes is received as output from the 3-D bounding box generation system.

A method of generating a color image using a monochromatic image sensor. The method includes sequentially illuminating a surface in a plurality of colors, one color at a time. The monochromatic image sensor captures a plurality of image frames of the surface based on the plurality of colors. The plurality of image frames are identified, and at least one feature in the target of the plurality of image frames is highlighted. Color intensities of the plurality of image frames are normalized. A color intensity map of the target for each of the plurality of image frames is generated. A correlation score is determined by comparing each color intensity map of the plurality of image frames. The color image is generated based on the correlation score.

A method of generating a color image using a monochromatic image sensor. The method includes sequentially illuminating a surface in a plurality of colors, one color at a time. The monochromatic image sensor captures a plurality of image frames of the surface based on the plurality of colors. The plurality of image frames are identified, and at least one feature in the target of the plurality of image frames is highlighted. Color intensities of the plurality of image frames are normalized. A color intensity map of the target for each of the plurality of image frames is generated. A correlation score is determined by comparing each color intensity map of the plurality of image frames. The color image is generated based on the correlation score.

Disclosed embodiments include apparatuses, systems, and methods for determining a field in a path of travel of a vehicle for detection of objects in the path of travel. In an illustrative embodiment, an apparatus includes a path identifier configured to identify a path of travel for a vehicle. At least one camera is disposed on the vehicle and is configured to capture image data of an area including the path of travel. A region of interest selector is configured to select a region of interest within the image data. A horizon identifier is configured to identify a horizon in the image data. A field determiner is configured to project the horizon onto the region of interest to isolate a field specified by the path of travel and the horizon, the field being evaluatable for the presence of objects in the path of travel of the vehicle.

Disclosed embodiments include apparatuses, systems, and methods for determining a field in a path of travel of a vehicle for detection of objects in the path of travel. In an illustrative embodiment, an apparatus includes a path identifier configured to identify a path of travel for a vehicle. At least one camera is disposed on the vehicle and is configured to capture image data of an area including the path of travel. A region of interest selector is configured to select a region of interest within the image data. A horizon identifier is configured to identify a horizon in the image data. A field determiner is configured to project the horizon onto the region of interest to isolate a field specified by the path of travel and the horizon, the field being evaluatable for the presence of objects in the path of travel of the vehicle.

An image is analyzed, a scene of the image is recognized, imaging information regarding capturing in a case where the image is captured is acquired, and reproduction information in a case where the image is reproduced on a display is acquired. An image coincident with preference of a user of the imaging device from among images having the same scene is decided for each scene based on the reproduction information, and a preference parameter table in which the scene and imaging information of the imaging device in a case where the image coincident with the preference of the user is captured are stored in association with each other is created. Imaging information associated with a scene coincident with a scene of an image to be captured next by the user is selected from the preference parameter table, and an image is captured by using the imaging information.

An image is analyzed, a scene of the image is recognized, imaging information regarding capturing in a case where the image is captured is acquired, and reproduction information in a case where the image is reproduced on a display is acquired. An image coincident with preference of a user of the imaging device from among images having the same scene is decided for each scene based on the reproduction information, and a preference parameter table in which the scene and imaging information of the imaging device in a case where the image coincident with the preference of the user is captured are stored in association with each other is created. Imaging information associated with a scene coincident with a scene of an image to be captured next by the user is selected from the preference parameter table, and an image is captured by using the imaging information.

A system and methods are provided for determining a vehicle action during a phantom projection attack, including processing a received image to identify a traffic object, and creating from the received image multiple processed images that are applied to respective neural network (NN) models. Latent representations of the multiple processed images from each of the NN models are then fed to a combiner model trained to determine whether the latent representations indicate a phantom projection attack, and, responsively to a determination of a phantom projection attack, issuing a phantom projection indicator.

Described herein are techniques that may be used to provide for automatic obfuscation of one or more objects in a media data. Such techniques may comprise receiving, from a data source, a media data comprising a depiction of a number of objects, identifying, within the received media data, a set of objects associated with the media data, and storing an indication of one or more locations of the objects in the set of objects within the media data with respect to time. Upon receiving a request for the media data, such techniques may further comprise updating the media data by applying an obfuscation effect to the one or more locations with respect to time, and providing the updated media data in response to the request.

Described herein are techniques that may be used to provide for automatic obfuscation of one or more objects in a media data. Such techniques may comprise receiving, from a data source, a media data comprising a depiction of a number of objects, identifying, within the received media data, a set of objects associated with the media data, and storing an indication of one or more locations of the objects in the set of objects within the media data with respect to time. Upon receiving a request for the media data, such techniques may further comprise updating the media data by applying an obfuscation effect to the one or more locations with respect to time, and providing the updated media data in response to the request.