Camera or object pose calculation is described, for example, to relocalize a mobile camera (such as on a smart phone) in a known environment or to compute the pose of an object moving relative to a fixed camera. The pose information is useful for robotics, augmented reality, navigation and other applications. In various embodiments where camera pose is calculated, a trained machine learning system associates image elements from an image of a scene, with points in the scene's 3D world coordinate frame. In examples where the camera is fixed and the pose of an object is to be calculated, the trained machine learning system associates image elements from an image of the object with points in an object coordinate frame. In examples, the image elements may be noisy and incomplete and a pose inference engine calculates an accurate estimate of the pose.

The various embodiments described herein include methods, devices, and systems for providing event alerts. In one aspect, a method includes: (1) obtaining a video feed, the video feed comprising a plurality of images; and, (2) for each image, analyzing the image to determine whether the image includes a person, the analyzing including: (a) determining that the image includes a potential instance of a person by analyzing the image at a first resolution; (b) in accordance with the determination that the image includes the potential instance, denoting a region around the potential instance; (c) determining whether the region includes an instance of the person by analyzing the region at a second resolution, greater than the first resolution; and (d) in accordance with a determination that the region includes the instance of the person, determining that the image includes the person.

A system and method for for determining a degree of point cloud data degradation of a LiDAR sensor of a Self-Driving Car (SDC) using a machine-learning algorithm (MLA) are provided. The method comprises: determining, based on a training point cloud generated by the LiDAR sensor representative of surroundings of the SDC, a plurality of LiDAR features; determining, for each training object in the surroundings, based on statistical data of coverage of training objects with LiDAR points, a plurality of enrichment features; receiving a respective label indicative of a degradation degree of the training point cloud; generating, based on the plurality of LiDAR features, the plurality of enrichment features, and the respective label, a given feature vector of a plurality of feature vectors; training, based on the plurality of feature vectors, the MLA to determine an in-use degree of degradation of in-use sensed data further generated by the LiDAR sensor.

A computer-implemented method for defect analysis is provided. The computer-implemented method includes obtaining a plurality of sets of defect point coordinates, a respective set of the plurality of sets of detect point coordinates including coordinates of defect points in a respective substrate of a plurality of substrates, the coordinates of defect points in the respective substrate being coordinates in an image coordinate system; combining the plurality of sets of defect point coordinates according to the image coordinate system into a composite set of coordinates to generate a composite image; and performing a clustering analysis to classify defect points in the composite set in the composite image into a plurality of clusters.

Systems, and method and computer readable media that store instructions for obtaining a first group concept structure that comprises first identifiers of first objects that belong to a first group; obtaining a second group concept structure that comprises second identifiers of second objects that belong to a second group; wherein the first identifiers were generated by processing media units that captured the first objects; wherein the second identifiers were generated by processing media units that captured the second objects; searching for shared pattern segments, each shared pattern segment appears in at least one first identifier and at least one second identifier; wherein a single shared pattern segment is indicative of a match; wherein a single non-shared pattern segment is suffice to represent a match; and responding to a finding of one or more shared pattern segments.

In example embodiments, techniques are provided to automatically classify individual elements of an infrastructure model by training one or more machine learning algorithms on classified infrastructure models, producing a classification model that maps features to classification labels, and utilizing the classification model to classify the individual elements of the infrastructure model. The resulting classified elements may then be readily subject to analytics, for example, enabling the display of dashboards for monitoring project performance and the impact of design changes. Such techniques enable classification of elements of new infrastructure models or in updates to existing infrastructure models.

An automatic industry classification method comprises: determining a scope of target patents, defining a target industry tree; generating marks on the target industry tree; performing a rough classification for the target patents by using the marks; performing a fine classification for the target patents according to a result of the rough classification. The automatic industry classification method and system provided by the present invention uses a transductive learning method, so that full mining of small annotation quantity information is realized. The automatic industry classification method and system uses information of IPC, so that information dimension is enriched, and calculation amount needed in the classification is reduced. The automatic industry classification method and system further uses the hierarchical vectors generated by the abstract, the claims and the description, so that the information of word order relation is reserved, and the patent text is deeply mined.

Various systems and methods for clustering facial images in, for example, surveillance systems.

A computing system obtains a video feed. For a frame of the video feed, the computing system analyzes the frame to determine whether the frame includes a potential instance of an event. In accordance with a determination that the frame includes the potential instance of an event, the computing system determines for the event an event category from a plurality of predefined event categories. It stores an indication of the event category. It determines whether the event category matches a predefined notification filter definition. In accordance with a determination that the event category matches the predefined notification filter definition, the computing system issues an alert notification to a user client device. In accordance with a determination that the event category does not match the predefined notification filter definition, the computing system refrains from issuing the alert notification.

A method for clustering based on unsupervised learning according to an embodiment of the invention enables clustering for newly generated patterns and is robust against noise, and does not require tagging for training data. According to one or more embodiments of the invention, noise is accurately removed using three-dimensional stacked spatial auto-correlation, and multivariate spatial probability distribution values and polar coordinate system spatial probability distribution values are used as learning features for clustering model generation, making them robust to noise, rotation, and fine unusual shapes. In addition, clusters resulting from clustering are classified into multi-level clusters, and stochastic automatic evaluation of normal/defect clusters is possible only with measurement data without a label.