Abstract: The present disclosure relates to systems and methods for analyzing and evaluating movement of a subjects and providing feedback. In some embodiments, a method comprises receiving one or more images of a body of the subject captured during performance of a physical movement by the subject, and then inputting the received one or more images into a convolutional neural network (CNN) to infer physical body information. The output from the CNN may be processed again by a subsequent CNN to refine the inferred body information, which may ultimately be used to generate a recommendation to the user for their physical movements.

Abstract: A method, an apparatus, an electronic device for estimating a pose of an object include determining a confidence of a depth image of an object based on a color image and the depth image of the object, estimating a pose of the object based on a three-dimensional (3D) keypoint in response to the depth image being reliable, and estimating the pose of the object based on a two-dimensional (2D) keypoint in response to the depth image being unreliable.

Abstract: There is provided a survey marker, and an image processing apparatus, method, and program capable of accurately detecting a survey marker from a captured image obtained by image capturing. The survey marker has a planar shape and includes a plurality of circles concentrically disposed, the plurality of circles including adjacent circles each having a different color. A candidate region extraction unit extracts a candidate region from a captured image obtained by image capturing of the survey marker, the candidate region being a candidate of a region in which the survey marker appears. A feature amount extraction unit extracts a feature amount of the candidate region. A discrimination unit discriminates the survey marker on the basis of the feature amount. The present technology can be applied to, for example, a case of detecting a survey marker installed on the ground from a captured image obtained by aerial image capturing.

Abstract: An object recognition unit (200) recognizes an object existing around a moving body (100). A surrounding situation estimation unit (204) analyzes at least any of a position and behavior of the object recognized by the object recognition unit (200), and derives as a latent event, an event which is likely to surface later and is attributed to an object that the object recognition unit (200) has not been able to recognize to exist around the moving body (100).

Abstract: Disclosed herein are an apparatus and a method for recognizing a formalized character set based on weakly supervised localization. The formalized character set recognition apparatus based on weakly supervised localization may include memory for storing at least one program; and a processor for executing the program, wherein the program performs recognizing one or more numerals present in a formalized character set image and a number of appearances of each of the numerals, extracting a class activation map in which a location of attention in the formalized character set image is indicated when a specific numeral is recognized, and outputting a formalized character set number in which numerals recognized based on the extracted class activation map are arranged.

Abstract: A system and methodology provide for annotating videos with entities and associated probabilities of existence of the entities within video frames. A computer-implemented method identifies an entity from a plurality of entities identifying characteristics of video items. The computer-implemented method selects a set of features correlated with the entity based on a value of a feature of a plurality of features, determines a classifier for the entity using the set of features, and determines an aggregation calibration function for the entity based on the set of features. The computer-implemented method selects a video frame from a video item, where the video frame having associated features, and determines a probability of existence of the entity based on the associated features using the classifier and the aggregation calibration function.

Abstract: A method includes obtaining, by a processing device from an optical sensor of a mobile device, an image of an object; processing, by the processing device, the image using a neural network, wherein processing the image includes distinguishing, using the neural network, a first portion of the image including a region of interest, ROI, from a second portion of the image, wherein processing the image comprises processing the image by an encoder to obtain an encoded image and processing the encoded image by a decoder to obtain a decoded output image; after processing the image, extracting, by the processing device, a biometric characteristic of the object from the ROI; extracting, by the processing device, a biometric characteristic of the object from the ROI; and processing, by the processing device, the biometric characteristic of the object to determine whether the biometric characteristic of the object identifies a user.

Abstract: Techniques are disclosed for providing a notification that a person is at a particular location. For example, a resident device may receive from a user device an image that shows a face of a first person, the image being captured by a first camera of the user device. The resident device may also receive, from another device having a second camera, a second image showing a portion of a face of a second person, the second camera having a viewable area showing a particular location. The resident device may determine a score indicating a level of similarity between a first set of characteristics associated with the face of the first person and a second set of characteristics associated with the face of a second person. The resident device may then provide to the user device a notification based on determining the score.

Abstract: Machine vision techniques for determining a region of interest (ROI) are disclosed herein. An example implementation includes a computing device for executing an application, the application operable to: (1) receive a first image; (2) set an first ROI of the first image to a field of view (FOV) of the first image; (3) determine a barcode within the first ROI; (4) determine a bounding box of the barcode; (5) form a second ROI based on the bounding box; (6) receive a second image; and (7) set an ROI of the second image to be the second ROI of the first image.

Abstract: The present disclosure generally relates techniques for audio-assisted enrollment of biometric features. In some embodiments, methods and devices for assisting users with enrollment of biometric features, using spatial audio cues, are described.

Abstract: Methods, systems and computer readable medium for liveness detection authentication of a facial image are provided. The method includes acquiring a first image of the facial image illuminated with a first color, acquiring a second image of the facial image illuminated with a second color, and determining if the facial image is consistent with a three-dimensional (3D) structure in response to a combination of the first and second images. The method further includes authenticating the facial image if the facial image is consistent with a 3D structure and the facial image matches a face of user to be authenticated.

Abstract: A method and system for image processing are provided in the present disclosure. The method may include obtaining a first image and determining whether there is an object of interest in the first image by performing an object detection on the first image. The method may also include upon a determination that there is an object of interest in the first image, retrieving at least one background image from a first storage device, and obtaining a foreground image. The method may further include upon a determination that there is no object of interest in the first image, determining whether a first predetermined condition is satisfied; and upon a determination that the first predetermined condition is satisfied, updating the at least one background image in the first storage device based on at least one candidate image determined as including no object of interest.

Abstract: System, methods, and embodiments described herein relate to dynamically generating a wide field-of-view three-dimensional pseudo point cloud of an environment around a vehicle. A disclosed method may include capturing, via a camera, a first view in a first image, determining a first depth map based on the first image, obtaining, from an external system, a second image of a second view that overlaps the first view and a second depth map based on the second image, inputting the first image and the second image into a self-supervised homograph network that is trained to output a homographic transformation matrix between the first image and the second image, and generating a three-dimensional pseudo point cloud that combines the first depth map and the second depth map based on the homographic transformation matrix.

Abstract: A method for recognizing masked faces includes: obtaining a face image to be recognized; detecting whether the face image to be recognized has a mask; extracting feature vectors of a whole face in the face image to be recognized when the face image to be recognized does not have a mask; comparing the feature vectors of the whole face with face images in a first database, and outputting a face recognition result; extracting feature vectors of an upper half face in the face image to be recognized when the face image to be recognized has a mask; comparing the feature vectors of the upper half face with face images in a second database, and outputting the face recognition result. The method of the present disclosure processes images of faces with and without masks, expanding application scenario of face recognition and improving the accuracy of recognition.

Abstract: In an illustrative embodiment, systems and methods for assisting users in identifying unknown individuals in photographs first apply facial recognition to obtain a first likelihood of match between a target face and other faces in a corpus of images provided by users of a genealogy platform, and then adjusts the first likelihood of match according to similarities and dissimilarities in attributes supplied by users regarding individuals represented by each face. Resultant likelihoods drive presentation of potential matches for consideration by a requesting user.

Abstract: This disclosure describes techniques for authenticating a user. For instance, a system may initially generate and then store authentication data for later authenticating the user. The authentication data may include biometrics data (e.g., facial recognition data), credentials data (e.g., a username, password, etc.), and/or environmental data (e.g., object(s) located within an environment). Later, the system may receive image data generated by a user device of the user. In some examples, the system may then analyze the image data using one or more facial recognition techniques in order to identify the user. The system may then use the authentication data, such as the environmental data, to determine that the image data further represents the object(s). Based on determining that the image data further represents the object(s), the system may then verify the user for access to a resource.

Abstract: A face mask detection system for detecting whether a user is wearing a mask at any given time using simple image recognition, configured to obtain an image of the user with the face mask, validate the image of the user wearing the face mask by an administrator (different from the user) in order to confirm validity of the image, and as a subsequent step use the validated image of the user with the face mask as a model image for benchmarking purposes. The model image is preferably a head profile of the user wearing a face mask. A face mask investigation unit compares the model image to an investigation image captured by an imaging system during an investigation process to determine whether the user in the investigation image is wearing the face mask based on whether an exact match is found between the model image and the investigation image.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, that use generative adversarial models to increase the quality of sensor data generated by a first environmental sensor to resemble the quality of sensor data generated by another sensor having a higher quality than the first environmental sensor. A set of first and second training data generated by a first environmental sensor having a first quality and a second sensor having a target quality, respectively, is received. A generative adversarial mode is trained, using the set of first training data and the set of second training data, to modify sensor data from the first environmental sensor by reducing a difference in quality between the sensor data generated by the first environmental sensor and sensor data generated by the target environmental sensor.

Abstract: Examples described herein provide a method that includes performing cluster matching with one or more cluster sizes for each of a plurality of points of a measurement point cloud. The method further includes determining, based on results of the multi-radii cluster matching, whether an object is displaced or whether the object includes a defect.

Abstract: An artificial intelligence system for identifying attributes in an image. The system may include a processor in communication with a client device; and a storage medium. The storage medium may store instructions that, when executed, configure the processor to perform operations including: extracting first features; categorizing the first images in a first group or a second group; modifying first metadata associated with each image in the first images to include a binary label; calculating a classification function; classifying a second plurality of images using the classification function; extracting second features from the second images classified in the first group; categorizing the second images in the first group by attribute; calculating an attribute identification function that identifies attributes of the second images; and identifying at least one attribute associated with a client image using the attribute identification function, the client image being received from the client device.