This application provides an image processing method, a network training method, and a related device, and relates to image processing technologies in the artificial intelligence field. The method includes: inputting a first image including a first vehicle into an image processing network to obtain a first result output by the image processing network, where the first result includes location information of a two-dimensional 2D bounding frame of the first vehicle, coordinates of a wheel of the first vehicle, and a first angle of the first vehicle, and the first angle of the first vehicle indicates an included angle between a side line of the first vehicle and a first axis of the first image; and generating location information of a three-dimensional 3D outer bounding box of the first vehicle based on the first result.

A camera with a field of view toward an external environment of an aircraft is disposed within an aircraft door such that a ground surface is within the field of view of the camera during taxiing of the aircraft. A display device is disposed within an interior of the aircraft. A processor is operatively coupled to the camera and to the display device. The processor analyzes image data captured by the camera for docking guidance by identifying, within the captured image data, a region on the ground surface corresponding to an alignment fiducial indicating a parking location for the aircraft, determining, based on the region of the captured image data corresponding to the alignment fiducial indicating the parking location, a relative location of the aircraft with respect to the alignment fiducial, and outputting an indication of the relative location of the aircraft to the alignment fiducial.

Commercial interactions with non-discretized items such as liquids in carafes or other dispensers are detected and associated with actors using images captured by one or more digital cameras including the carafes or dispensers within their fields of view. The images are processed to detect body parts of actors and other aspects therein, and to not only determine that a commercial interaction has occurred but also identify an actor that performed the commercial interaction. Based on information or data determined from such images, movements of body parts associated with raising, lowering or rotating one or more carafes or other dispensers may be detected, and a commercial interaction involving such carafes or dispensers may be detected and associated with a specific actor accordingly.

Commercial interactions with non-discretized items such as liquids in carafes or other dispensers are detected and associated with actors using images captured by one or more digital cameras including the carafes or dispensers within their fields of view. The images are processed to detect body parts of actors and other aspects therein, and to not only determine that a commercial interaction has occurred but also identify an actor that performed the commercial interaction. Based on information or data determined from such images, movements of body parts associated with raising, lowering or rotating one or more carafes or other dispensers may be detected, and a commercial interaction involving such carafes or dispensers may be detected and associated with a specific actor accordingly.

A method implemented on a visual computing device to authenticate one or more users includes receiving a first three-dimensional pattern from a user. The first three-dimensional pattern is sent to a server computer. At a time of user authentication, a second three-dimensional pattern is received from the user. The second three-dimensional pattern is sent to the server computer. An indication is received from the server computer as to whether the first three-dimensional pattern matches the second three-dimensional pattern within a margin of error. When the first three-dimensional pattern matches the second three-dimensional pattern within the margin of error, the user is authenticated at the server computer. When the first three-dimensional pattern does not match the second three-dimensional pattern within the margin of error, user is prevented from being authenticated at the server computer.

Systems and methods for semantic labeling of point clouds using images. Some implementations may include obtaining a point cloud that is based on lidar data reflecting one or more objects in a space; obtaining an image that includes a view of at least one of the one or more objects in the space; determining a projection of points from the point cloud onto the image; generating, using the projection, an augmented image that includes one or more channels of data from the point cloud and one or more channels of data from the image; inputting the augmented image to a two dimensional convolutional neural network to obtain a semantic labeled image wherein elements of the semantic labeled image include respective predictions; and mapping, by reversing the projection, predictions of the semantic labeled image to respective points of the point cloud to obtain a semantic labeled point cloud.

Systems and methods for semantic labeling of point clouds using images. Some implementations may include obtaining a point cloud that is based on lidar data reflecting one or more objects in a space; obtaining an image that includes a view of at least one of the one or more objects in the space; determining a projection of points from the point cloud onto the image; generating, using the projection, an augmented image that includes one or more channels of data from the point cloud and one or more channels of data from the image; inputting the augmented image to a two dimensional convolutional neural network to obtain a semantic labeled image wherein elements of the semantic labeled image include respective predictions; and mapping, by reversing the projection, predictions of the semantic labeled image to respective points of the point cloud to obtain a semantic labeled point cloud.

In one embodiment, a computing system may update a first 3D model of a region of an environment based on comparisons between the first 3D model and first depth measurements of the region generated during a first time period. The computing system may determine that the region is static by comparing the first 3D model to second depth measurements of the region generated during a second time period. The computing system may in response to determining that the region is static, detect whether the region changed after the second time period based on comparisons between a second 3D model of the region and third depth measurements of the region generated after the second time period, the second 3D model having a lower resolution than the first 3D model. The computing system may in response to detecting a change in the region, update the first 3D model of the region.

In one embodiment, a computing system may update a first 3D model of a region of an environment based on comparisons between the first 3D model and first depth measurements of the region generated during a first time period. The computing system may determine that the region is static by comparing the first 3D model to second depth measurements of the region generated during a second time period. The computing system may in response to determining that the region is static, detect whether the region changed after the second time period based on comparisons between a second 3D model of the region and third depth measurements of the region generated after the second time period, the second 3D model having a lower resolution than the first 3D model. The computing system may in response to detecting a change in the region, update the first 3D model of the region.

A method for determining a current gaze direction of a user in relation to a three-dimensional (“3D”) scene, the 3D scene sampled by a rendering function to produce a two-dimensional (“2D”) projection image of the 3D scene, the sampling performed based on a virtual camera in turn being associated with a camera position and camera direction in the 3D scene. The method includes determining, by a gaze direction detection means, a first gaze direction of the user related to the 3D scene at a first gaze time point. The method includes determining a time-dependent virtual camera 3D transformation representing a change of a virtual camera position and/or virtual camera direction between the first gaze time point and a second sampling. The method includes determining the current gaze direction as a modified gaze direction calculated based on the first gaze direction and an inverse of the time-dependent virtual camera 3D transformation.