Human posture determination is disclosed. Human posture is determined by obtaining range image(s) through a range camera, detecting key points of an estimated skeleton of a human in color data of the range image(s) and calculating positions of the detected key points based on depth data of the range image(s), choosing a feature map from a set of predefined feature maps based on the detected key points among a set of predefined key points, obtaining two features of a body of the human corresponding to the chosen feature map based on the positions of the detected key points, and determining a posture of the human according to the two features in the chosen feature map.

A computer system obtains at least one 3D scan of a body surface; automatically identifies, based on the at least one 3D scan, one or more features (e.g., nose, lips, eyes, eyebrows, cheekbones, or specific portions thereof, or other features) of the body surface; and generates a digital 3D model of the body surface. The digital 3D model includes the identified features of the human body surface. In an embodiment, the step of generating of the digital 3D model is based on the at least one 3D scan and the identified features of the body surface. In an embodiment, the digital 3D model comprises a 3D mesh file. The digital 3D model can be used in various ways. For example, output of a manufacturing process (e.g., a 3D printed item, a cosmetics product, a personal care product) can be based on the digital 3D model.

A system for collecting data for training a computer vision model for shape estimation includes: an imaging system configured to capture one or more images; and a processing system including a processor and memory storing instructions that, when executed by the processor, cause the processor to: receive one or more input images from the imaging system; estimate a pose of an object depicted in the one or more images; render a shape estimate from a 3-D model of the object posed in accordance with the pose of the object; and generate a data point of a training dataset, the data point including one or more images based on the one or more input images and a label corresponding to the one or more images, the label including the shape estimate.

The disclosed technology provides solutions for improving object detection system based on height map data. A process of the disclosed technology can include steps for receiving image data, receiving height map data, the height map data corresponding with a location of the image data, projecting the height map data onto the image data to generate composite image data, and training an object detection model based on the composite image data. In some aspects, the process can further include steps for localizing one or more objects represented by the image data using the object detection model. Systems and machine-readable media are also provided.

A tangible object virtualization station including a base capable of stably resting on a surface and a head component unit connected to the base. The head component unit extends upwardly from the base. At an end of the head component opposite the base, the head component comprises a camera situated to capture a downward view of the surface proximate the base, a lighting array that directs light downward toward the surface proximate the base. The tangible object virtualization station further comprises a display interface included in the base. The display interface is configured to hold a display device in an upright position and connect the display device to the camera and the lighting array.

A method, device, apparatus and a computer-readable storage medium for detecting a height of an obstacle are provided. The method can include: acquiring observation data of a plurality of reference obstacles from a frame; according to the observation data of each of the reference obstacles, fitting a function F: Z=F(ymax), wherein the observation data of a reference obstacle comprises a longitudinal coordinate of a bottom of the reference obstacle in the frame, and a distance between the reference obstacle and a camera capturing the frame; and determining a distance between the obstacle to be detected and the camera, according to the longitudinal coordinate of the bottom of the obstacle in the frame and the function F; and determining an evaluation value of the height of the obstacle to be detected according to the distance between the obstacle to be detected and the camera.

In one embodiment, a method includes receiving sensor data of an environment of the vehicle generated by one or more sensors of the vehicle, the sensors comprising a camera, identifying, based on the sensor data, one or more objects in a field of view of the camera and one or more object types that correspond to the one or more objects, determining one or more target histograms that correspond to the object types, generating a processed image based on an image captured by the camera, wherein the processed image has a histogram based on the target histograms, and using the processed image to determine state information associated with the objects. The processed image may be generated by processing the image captured by the camera using a histogram matching algorithm to generate the histogram of the processed image based on the target histograms.

A computer-implemented method for material extrusion detection in a portion of a mechanical part having a distribution of material. The method includes obtaining a CAD 3D model of the mechanical part including a skin portion representing an outer surface of the portion of the mechanical part and an extrusion axis. The method further includes computing a ratio of an area of an orthogonal projection of the skin portion over an area of the skin portion. The method further includes determining whether or not the distribution of material is arranged as an extrusion based on the ratio and a ratio threshold. The outer surface is determined to be an extrusion surface when the ratio is lower than the ratio threshold. This forms an improved solution for processing a CAD 3D model of a mechanical part.

Systems and methods for automatically generating a 3D model of a roof of a building are provided. In a described embodiment, the method includes receiving point cloud data comprising a plurality of data points corresponding to height measurements at a given location; processing the point cloud data to identify roof surfaces; generating a 3D model of the roof using the identified surfaces; receiving aerial imagery of the roof; registering the aerial imagery with the point cloud data; and refining the 3D model using the aerial imagery. A corresponding computing system and non-transitory computer readable medium for carrying out the methods are also provided.

A system and method for making a custom miniature figurine using a 3D scanned image and a pre-sculpted body is described herein. The system includes a database, a server, a computing device, an automated distributed manufacturing system, and a 3D printing apparatus. An application of the computing device utilizes a camera of the computing device to scan a head of a user, create a 3D representation of the head of the user from the scans, combine the 3D representation of the head of the user with a pre-sculpted digital body and/or accessories selected by the user to create a work order, and transmit the work order to the automated distributed manufacturing system. The automated distributed manufacturing system performs digital modeling tasks, assembles a digital model, and transmits the digital model to the 3D printing apparatus. The 3D printing apparatus creates the custom miniature figurine.