A method for estimating human body temperature includes receiving, via a thermal camera, a thermal image captured of a real-world environment, the thermal image including thermal intensity values for each of a plurality of pixels of the thermal image. A position of a human face is identified within the thermal image, the human face corresponding to a human subject. An indication of a distance between the human subject and the thermal camera is received. Based on the distance, a distance correction factor is applied to one or more thermal intensity values of one or more pixels corresponding to the human face to give one or more distance-corrected thermal intensity values. Based on the one or more distance-corrected thermal intensity values an indication of a body temperature of the human subject is reported.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for labeling point clouds using distance field data. One of the methods includes obtaining a point cloud characterizing a region of the environment, the point cloud comprising a plurality of points; obtaining distance field data specifying, for each of a plurality of locations in the region of the environment, a distance from the location to a nearest static object in the environment; determining, using the distance field data and for each of the plurality of points, a respective distance from the point to a nearest static object in the environment to the point; and identifying, based on the respective distances for the plurality of points in the point cloud, one or more of the points as candidate dynamic object points that are likely to be measurements of a dynamic object in the environment.

An individual identification system includes an acquiring means and a determining means. The acquiring means is configured to acquire a matched image obtained by shooting part of a predetermined region of a matching target object. The determining means is configured to calculate a score representing a degree to which a partial image similar to the matched image exists in a registration image obtained by shooting a predetermined region of a registration target object, and determine based on the score whether or not the matching target object is identical to the registration target object.

A geographic object recognition unit (120) recognizes, using image data (192) obtained by photographing in a measurement region where a geographic object exists, a type of the geographic object from an image that the image data (192) represents. A position specification unit (130) specifies, using three-dimensional point cloud data (191) indicating a three-dimensional coordinate value of each of a plurality of points in the measurement region, a position of the geographic object.

Provided is a method of generating a three-dimensional (3D) avatar from a two-dimensional (2D) image. The method may include obtaining a 2D image by capturing a face of a person, detecting a landmark of the face in the obtained 2D image, generating a first mesh model by modeling a 3D geometrical structure of the face based on the detected landmark, extracting face texture information from the obtained 2D image, determining a second mesh model to be blended with the first mesh model in response to a user input, wherein the first mesh model and the second mesh model have the same mesh topology, generating a 3D avatar by blending the first mesh model and the second mesh model, and applying, to the 3D avatar, a visual expression corresponding to the extracted face texture information.

An artificial neural network-based method for detecting a surface type of an object includes: receiving a plurality of object images, wherein a plurality of spectra of the plurality of object images are different from one another and each of the object images has one of the spectra; transforming each object image into a matrix, wherein the matrix has a channel value that represents the spectrum of the corresponding object image; and executing a deep learning program by using the matrices to build a predictive model for identifying a target surface type of the object. Accordingly, the speed of identifying the target surface type of the object is increased, further improving the product yield of the object.

The invention relates to a shot-processing device which comprises a memory (10), a detector (20), a preparer (30), a combiner (40), an estimator (50) and a selector (60). The memory (10) is arranged to receive, on the one hand, scene data (12) that comprise three-dimensional object pairs each associating an object identifier, and ellipsoid data which define an ellipsoid and its orientation and a position of its centre in a common frame of reference and, on the other hand, shot data (14) defining a two-dimensional image of the scene associated with the scene data (12), from a viewpoint corresponding to a desired pose. The detector (20) is arranged to receive shot data (14) and to return one or more two-dimensional object pairs (22) each comprising an object identifier present in the scene data, and a shot region associated with this object identifier. The preparer (30) is arranged to determine, for at least some of the two-dimensional object pairs (22) from the detector (20), a set of positioning elements (32) whose number is less than or equal to the number of three-dimensional object pairs in the scene data (12) that comprise the object identifier of the two-dimensional object pair (22) in question, each positioning element (32) associating the object identifier and the ellipsoid data of a three-dimensional object pair comprising this object identifier, and ellipse data which define an ellipse approximating the shot region of the two-dimensional object pair in question and its orientation as well as a position of its centre in the two-dimensional image. The combiner (40) is arranged to generate a list of candidates (42) each associating one or more positioning elements (32) and a shot orientation, and/or the combination of at least two positioning elements (32), the positioning elements (32) of a single candidate (42) being taken from separate two-dimensional object pairs (22) and not relating to the same three-dimensional object pair. The estimator (50) is arranged to calculate, for at least one of the candidates, a pose (52) comprising a position and an orientation in the common frame of reference from the ellipse data and the ellipsoid data of the positioning elements, or from the ellipse data and the ellipsoid data of the one or more positioning elements and the shot orientation. The selector (60) is arranged, for at least some of the poses, to project all of the ellipsoid data of the scene data onto the shot data from the pose, to determine a measurem

A floorplan modelling method and system. The floorplan modelling method includes receiving 2D images of each corner of an interior space from a camera, generating a corresponding camera position and camera orientation in a 3D coordinate system in the interior space for each 2D image, generating a depth map for each 2D image to estimate depth for each pixel, generating a corresponding edge map for each 2D image, and generating a 3D point cloud for each 2D image using the corresponding depth map and parameters of the camera. The floorplan modelling method includes transforming the 3D point clouds with the corresponding edge map into a 2D space in the 3D coordinate system of the camera, regularizing the 3D point clouds into 2D boundary lines, and generating a 2D plan of the interior space from the boundary lines.

Pixel image data of a scene is received in which the pixel image data includes a two-dimensional representation of an object in the scene. Point cloud data including three-dimensional point coordinates of a physical object within the scene corresponding to the two-dimensional representation of the object is received. The three-dimensional point coordinates include depth information of the physical object. The point cloud data is mapped to an image plane of the pixel image data to form integrated pixel image data wherein one or more pixels of the pixel image data have depth information integrated therewith. A three-dimensional bounding box is predicted for the object using a convolutional neural network based upon the integrated pixel image data.

Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing at least one program and method for rendering three-dimensional captions (3D) in real-world environments depicted in image content. An editing interface is displayed on a client device. The editing interface includes an input component displayed with a view of a camera feed. A first input comprising one or more text characters is received. In response to receiving the first input, a two-dimensional (2D) representation of the one or more text characters is displayed. In response to detecting a second input, a preview interface is displayed. Within the preview interface, a 3D caption based on the one or more text characters is rendered at a position in a 3D space captured within the camera feed. A message is generated that includes the 3D caption rendered at the position in the 3D space captured within the camera feed.