A sensor-based bare hand data labeling method and system are provided. The method comprises: performing device calibration processing on a depth camera and on one or more sensors respectively preset at one or more specified positions of a bare hand, so as to acquire coordinate transformation data; collecting a depth image of the bare hand by the depth camera, and collecting 6DoF data of one or more bone points; acquiring, based on the 6DoF data and the coordinate transformation data, three-dimensional position information of a preset number of bone points; determining two-dimensional position information of the preset number of bone points on the depth image based on the three-dimensional position information of the preset number of bone points; and labeling joint information on all of the bone points in the depth image according to the two-dimensional position information and the three-dimensional position information.

A point cloud data processing apparatus (11) includes: a memory (21) configured to store point cloud data (7) and pieces of image data (5), with positions of pixels of at least any one piece of image data (5) among the pieces of image data (5) being associated with points that constitute the point cloud data (7); and a processor, the processor being configured to cause a display unit (9) to display the point cloud data such that three-dimensional rotation, three-dimensional movement, and rescaling are enabled, accept a designation of a specified point in the point cloud data (7) displayed on the display unit (9), select a region of a target object including a region corresponding to the specified point, on the piece of image data (5), and assign the same attribute information to points, in the point cloud data (7), corresponding to the region of the target object.

Various embodiments are generally directed to techniques of overlaying a virtual object on a physical object in augmented reality (AR). A computing device may receive one or more images of the physical object, perform analysis on the images (such as image segmentation) to generate a digital outline, and determine a position and a scale of the physical object based at least in part on the digital outline. The computing device may configure (e.g., rotate, scale) a 3D model of the physical object to match the determined position and scale of the physical object. The computing device may place or overlay a 3D virtual object on the physical object in AR based on a predefined location relation between the 3D virtual object and the 3D model of the physical object, and further, generate a composite view of the placement or overlay.

The present invention provides an image processing apparatus comprising: a first camera obtaining a true-color image by capturing a subject; a second camera spaced apart from the first camera and obtaining an infrared image by capturing the subject; and a control unit connected to the first camera and the second camera, wherein the control unit matches the true-color image and the infrared image and obtains three-dimensional information of the subject by using the matched infrared image in a region corresponding to the matched true-color image and a valid pixel.

The present disclosure provides a three-dimensional (3D) object detection method, a 3D object detection apparatus, an electronic device, and a readable storage medium, belonging to a field of computer vision technologies. Two-dimensional (2D) image parameters and initial 3D image parameters are determined for a target object. Candidate 3D image parameters are determined for the target object based on a disturbance range of 3D parameters and the initial 3D image parameters determined for the target object. Target 3D image parameters are selected for the target object from the candidate 3D image parameters determined for the target object based on the 2D image parameters. A 3D detection result of the target object is determined based on the target 3D image parameters.

Techniques for context-aware identification of anomalies in civil infrastructure. A method includes applying an anomaly identification model to features extracted from visual content showing civil infrastructure in order to determine at least one anomalous portion shown in the visual multimedia content, a type of each anomalous portion, and a quantification of each anomalous portion; wherein the anomaly identification model is selected based on a type of material of the civil infrastructure; and generating a semantically labeled three-dimensional (3D) model based on the at least one anomalous portion and the type of each anomalous portion, wherein the semantically labeled 3D model includes anomalous points; wherein each anomalous point represents one of the at least one anomalous portion; wherein the anomalous points collectively define a pattern of the at least one anomalous portion; wherein each anomalous point is visually distinguished to indicate the quantification of the respective anomalous portion.

This disclosure relates to method and system for detecting and tracking at least one object in a rotational environment. The method includes receiving a set of first features based on first data and a set of second features based on second data, detecting at least one object based on the set of first features using a Convolutional Neural Network (CNN) based predictive model, determining a set of first parameters for the at least one object, detecting the at least one object based on the set of second features using the CNN based predictive model, determining a set of second parameters for the at least one object, and tracking the at least one object based on the set of first parameters and the set of second parameters. It should be noted that the first data and the second data sequentially belong to an input dataset that includes images or video frames.

The present invention provides system and method for tracking and analyzing golf shot, the method comprising: turning on a light source; a capturing a pair of images of the golf shot using a pair of stereo cameras having a same focal length and triggered by single signal; a analyzing a disparity between the pair of images; a producing a disparity map, a three dimension simulation, and a first motion analysis data; a capturing an image of the golf shot from before to after contact between a golf club and a golf ball using a single camera; a analyzing image sequences captured by the single camera; a producing a second motion analysis data including at least one of ball spinning, club face angle, and swing, and displaying the three dimension simulation, the image sequence, and the first and the second motion analysis data.

A device determines positions of objects in a scene. The device obtains object detection data (ODD) which identifies the objects and locations of reference points of the objects in 2D images of the scene. The device processes the ODD to generate candidate association data (CAD) which associates pairs of objects between the images, computes estimated 3D positions in the scene for associated pairs of objects in the CAD, and performs clustering of the estimated positions. The device further generates, based on estimated 3D positions in one or more clusters, final association data (FAD) which associates one or more objects between the images, and computes one or more final 3D positions in the scene for one or more reference points of the one or more objects in the FAD. The final 3D position(s) represent the 3D position or the 3D pose of the respective object in the scene.

This specification relates to reconstructing three-dimensional (3D) scenes from two-dimensional (2D) images using a neural network. According to a first aspect of this specification, there is described a method for creating a three-dimensional reconstruction of a scene with multiple objects from a single two-dimensional image, the method comprising: receiving a single two-dimensional image; identifying all objects in the image to be reconstructed and identifying the type of said objects; estimating a three-dimensional representation of each identified object; estimating a three-dimensional plane physically supporting all three-dimensional objects; and positioning all three-dimensional objects in space relative to the supporting plane.