In one exemplary embodiment in accordance with the disclosure, an image processing system is configured to use a distance authentication template to execute a detection procedure that detects at least one non-linear distortion in a subject image. The distance authentication template can be generated by mapping a set of spatial coordinates of three features in a distortion-free image to a set of pixel coordinates of the three features in the distortion-free image. Addressing a non-linear distortion in the subject image can include performing remedial actions to remedy the non-linear distortion, or taking into consideration the non-linear distortion when using the distance authentication template to identify one or more features in the subject image.

An electronic apparatus performs a method of recovering a complete and dense point cloud from a partial point cloud. The method includes: constructing a sparse but complete point cloud from the partial point cloud through a contrastive teacher-student neural network; and transforming the sparse but complete point cloud to the complete and dense point cloud. In some embodiments, the contrastive teacher-student neural network has a dual network structure comprising a teacher network and a student network both sharing the same architecture. The teacher network is a point cloud self-reconstruction network, and the student network is a point cloud completion network.

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.

The present invention relates to a detection method for an assembly body multi-view change based on feature matching, comprising the following steps: S1, acquiring a first image and a second image; S2, performing feature point extraction and feature matching on the first image and the second image to obtain a matching pair set, a first unmatched point set of the first image and a second unmatched point set of the second image; S3, acquiring a first to-be-matched area set of the first image according to the first unmatched point set; acquiring a second to-be-matched area set of the second image according to the second unmatched point set; S4, performing feature matching on each first unmatched area and each second unmatched area one by one to obtain a plurality of matching results; and S5, outputting the assembly body change type according to the plurality of matching results.

A system for modeling a three-dimensional structure utilizing two-dimensional segments comprising a memory and a processor in communication with the memory. The processor extracts a plurality of two-dimensional segments corresponding to the three-dimensional structure from a plurality of images indicative of different views of the three-dimensional structure. The processor determines a plurality of three-dimensional candidate segments based on the extracted plurality of two-dimensional segments and adds the plurality of three-dimensional candidate segments to a three-dimensional segment cloud. The processor transforms the three-dimensional segment cloud into a wireframe indicative of the three-dimensional structure by performing a wireframe extraction process on the three-dimensional segment cloud.

Disclosed are a point cloud quality assessment method, an encoder and a decoder. The method comprises: decoding a bitstream to acquire a feature parameter of a point cloud to be assessed; determining a model parameter of a quality assessment model; and according to the model parameter and the feature parameter of the point cloud, determining a subjective quality measurement value of the point cloud using the quality assessment model.

Efficient location and identification of documents in images. In an embodiment, at least one quadrangle is extracted from an image based on line(s) extracted from the image. Parameter(s) are determined from the quadrangle(s), and keypoints are extracted from the image based on the parameter(s). Input descriptors are calculated for the keypoints and used to match the keypoints to reference keypoints, to identify classification candidate(s) that represent a template image of a type of document. The type of document and distortion parameter(s) are determined based on the classification candidate(s).

Disclosed herein is an apparatus comprising a camera and a processing unit operatively coupled to the camera, wherein the processing unit is configured to: receive a sequence of images captured by the camera; process a first image of the received sequence of images to compute respective likelihoods of each of a plurality of predetermined facial features being visible in the first image; compute, from the computed likelihoods, a probability that the first image depicts a predetermined first side of a human head; responsive to at least the computed probability exceeding the predetermined detection probability, trigger performance of a predetermined action.

A shape identification program causes a computer to execute a process including: acquiring a third shape dataset and a fourth shape dataset, respectively generated by changing sizes of a first shape dataset and a second shape dataset in each of directions of a plurality of coordinate axes according to a specific rule; and generating a first plurality of images and a second plurality of images by capturing the third shape dataset and the fourth shape dataset, respectively, from both directions of the respective plurality of coordinate axes. The process further includes identifying a second portion in the second shape dataset corresponding to a first portion in the first shape dataset by aligning orientations of the first shape dataset and the second shape dataset based on a result of comparison between the first plurality of images and the second plurality of images.

An apparatus for matching point cloud data according to an embodiment includes a generation unit configured to generate an input model and an input model group including a plurality of the input models, the input model being obtained by reducing a data amount of the point cloud data, an extraction unit configured to extract some of the input models from the input model group according to shape information of the input models, a calculation unit configured to compare an extracted extraction model with a reference model based on reference point cloud data and calculate a cost, a determination unit configured to determine whether or not the cost has converged, and a change unit configured to change a position and a posture so that the cost is reduced when the cost has not converged.