The present application describes a system (100) and method for detecting and labeling structures of interest. The system includes a current patient study database (102) containing a current patient study (200) with clinical contextual information (706). The system also includes an image metadata processing engine (118) configured to extract metadata for preparing an input for an anatomical structure classifier (608), a natural language processing engine (120) configured to extract clinical context information (706) from the prior patient documents, an anatomical structure detection and labeling engine (718), and a display device (108) configured to display findings from the current patient study. The anatomical structure detection and labeling engine (718) is configured to identify and label one or more structures of interest (716) from the extracted metadata and clinical context information (706). The processor (112) is also configured to aggregate series level data. The method detects, label and prioritize anatomical structures (710). Specifically, once patient information is received from the current patient study (108), the labeled anatomical structures (710) and the high risk anatomical structures (714) are combined to form an optimized prioritized list of structures of interest (716).

A method includes fusing multi-modal sensor data from a plurality of sensors having different modalities. At least one region of interest is detected in the multi-modal sensor data. One or more patches of interest are detected in the multi-modal sensor data based on detecting the at least one region of interest. A model that uses a deep convolutional neural network is applied to the one or more patches of interest. Post-processing of a result of applying the model is performed to produce a post-processing result for the one or more patches of interest. A perception indication of the post-processing result is output.

The techniques and device provided herein relate to receiving, via a processor, image data representative of a borehole of a well. The technique may include generating dequantized image data based on the image data, such that the dequantized image data filters one or more artifacts present in a Hough transformed version of the image data. One or more dip orientations (inclination and azimuth) associated with one or more formation dips present in the image data may be determined based on the dequantized image data. The technique may also include performing an a-contration validation algorithm for for the one or more formation dips to verify whether at least a formation dip having the or one of the possible dip orientation is present at a predetermined measured depth in the image data..

A normal vector or a curvature at each of a plurality of vertexes that are included in data relating to an oral cavity shape including a tooth crown shape of at least one tooth and define the oral cavity shape is acquired. Then, a vertex group that defines the tooth crown shape of the at least one tooth is extracted from the plurality of vertexes based on the acquired normal vectors or curvatures. Further, the extracted vertex group is outputted as tooth crown shape information that specifies a tooth crown portion in the oral cavity shape. Consequently, automatic construction of a database for a tooth crown shape can be implemented.

An unmanned aerial vehicle according to the present disclosure is an unmanned aerial vehicle that can fly in midair and includes a propulsion unit configured to generate a propulsion force for fly in midair, a laser light source configured to illuminate laser light, an imaging unit configured to generate a captured image by capturing vertically below the unmanned aerial vehicle during flight in midair, and a controller configured to control an operation of the propulsion unit. The controller analyzes a captured image, extracts a light spot formed by laser light, measures a positional relationship with another unmanned aerial vehicle based on the extracted light spot, and executes a collision avoidance operation with respect to another unmanned aerial vehicle based on the measured positional relationship.

There are provided a focusing point determining method and apparatus. The focusing point determining method comprises: obtaining a view-finding image within a view-finding coverage; identifying a significance area in the view-finding image; and extracting at least one focusing point from the identified significance area. By identifying the significance area in the view-finding image and extracting at least one focusing point from the identified significance area, the focusing point determining method and apparatus can ensure accuracy of a selected focusing point to a certain extent, so as to ensure accuracy of focusing.

An information processing method is provided. The information processing method includes acquiring a motion state of eyes of a user to form eye motion data and record a first acquisition time of the eye motion data; extracting position data of the user's eyeballs from the eye motion data; and capturing user behavior activity data to record a second acquisition time of the user behavior activity data. The method also includes, based on the first acquisition time and the second acquisition time, determining a correspondence relationship between the position data of the user's eyeballs and the user behavior activity data; and, based on the correspondence relationship and a current eye motion, determining a current user behavior activity.

An image processing method for iris recognition of a predetermined subject, comprises acquiring through an image sensor, a probe image illuminated by an infra-red (IR) illumination source, wherein the probe image comprises one or more eye regions and is overexposed until skin portions of the image are saturated. One or more iris regions are identified within the one or more eye regions of said probe image; and the identified iris regions are analysed to detect whether they belong to the predetermined subject.

A method for evaluating quality of tone-mapping image based on exposure analysis is provided, which explores the exposure properties on each area of the high dynamic range image utilizing the pre-exposure method and divides the high dynamic range image into three parts of an easy overexposed area, an easy underexposed area and an easy natural-exposed area, wherein different quality characteristics are extracted in different areas, which is capable of ensuring that the follow-up quality characteristic extraction is more targeted. The present invention takes the difference of distortion between the tone-mapping image and the conventional image into account, and extracts image characteristics such as the abnormal exposure rate, the underexposed residual energy, the overexposed residual energy and the exposure color index, so as to accurately reflect the quality degradation of the tone-mapping image.

Systems, methods, and non-transitory computer-readable media can obtain a test content item having a plurality of video frames. At least one video fingerprint is determined based on a set of video frames corresponding to the test content item. At least one reference content item is determined using at least a portion of the video fingerprint. At least one portion of the test content item that matches at least one portion of the reference content item is determined based at least in part on the video fingerprint of the test content item and one or more video fingerprints of the reference content item.