Abstract: The present disclosure relates to a system that includes one or more processors configured to receive a plurality of aerial property data corresponding to a target property, and applying a height threshold to the plurality of aerial property images. Additionally, the system is configured to remove areas within the plurality of property images that exceed the height threshold, and apply a perimeter calculation to define a perimeter around the target property within the aerial property images. Further, the system calculates an area of the detected vegetation and structures within the perimeter of the aerial property images.

Abstract: A deep learning model may be trained to provide an estimated image of the interior of a patient, based on a number of image sets, each image set comprising an interior image of the interior of a person and a contour image of the person's outer contour at a specific point in time. The model is trained to establish an optimized parametrized conversion function G specifying the correlation between the interior of the person and the persons outer contour based on the image sets. The conversion function G can then be used to provide estimated images of patient's interior based on their contours.

Abstract: Performing semantic segmentation in an absence of labels for one or more semantic classes is provided. One or more weak predictors are utilized to obtain label proposals of novel classes for an original dataset for which at least a subset of sematic classes are unlabeled classes. The label proposals are merged with ground truth of the original dataset to generate a merged dataset, the ground truth defining labeled classes of portions of the original dataset. A machine learning model is trained using the merged dataset. The machine learning model is utilized for performing semantic segmentation on image data.

Abstract: A non-standard user interface object identification system includes an object candidate extractior that extracts one or more objects from an image, a first similarity analyzer that determines object type candidates of the one or more objects in accordance with similarities between the one or more objects and a standard user interface (UI) element, a second similarity analyzer that selects object type-specific weight values in accordance with layout characteristics of the one or more objects and determines object types of the one or more objects using the object type candidates and the object type-specific weight values, and an object identifier that receives type and characteristic information of a search target object and identifies the search target object in accordance with characteristic information and the object types of the one or more objects.

Abstract: Techniques related to optical flow estimation for equirectangular images are discussed. Such techniques include combining an optical flow map generated using an input pair of equirectangular images and an optical flow map generated using a transformed pair of equirectangular images rotated with respect to the input pair to move polar regions in the input pair to central regions in the transformed pair.

Abstract: An example embodiment includes: a determination unit that, based on an image including an eye of a recognition subject, determines whether or not a colored contact lens is worn; and a matching unit that, when it is determined by the determination unit that the colored contact lens is worn, performs matching of the iris by using a feature amount extracted from a region excluding a predetermined range including an outer circumference of the iris out of a region of the iris included in the image.

Abstract: A computer-implemented method is provided for detecting a dynamic object in a visual line of sight of an aircraft. The method includes implementing, by a computer system, the following operations: receiving at least two image frames; detecting a horizon within at least one of the at least two image frames; segmenting each of the at least two image frames into at least first and second search regions using the detected horizon, wherein the first search region is defined above the detected horizon in the at least two image frames and the second search region is defined below the horizon in the at least two image frames; determining, across the at least two image frames, a motion vector field within at least one of the first search region or the second search region; and identifying a detection proposal using the determined motion vector field.

Abstract: Systems and methods for dynamic sensor data adaptation using a deep learning loop are provided. A method includes classifying, using a discriminator model, a first object from first sensor data associated with a first sensing condition, wherein the discriminator model is trained for a second sensing condition different from the first sensing condition; generating, using a generator model in response to the discriminator model failing to classify the first object, second sensor data representing a second object comprising at least a modified element of the first object; classifying, using the discriminator model, the second object from the second sensor data; and adapting, based at least in part on a difference between the first object and the second object in response to the discriminator model successfully classifying the second object, a machine learning model associated with object classification for the first sensing condition.

Abstract: Methods, systems, and storage media for classifying content across media formats based on weak supervision and cross-modal training are disclosed. The system can maintain a first feature classifier and a second feature classifier that classifies features of content having a first and second media format, respectively. The system can extract a feature space from a content item using the first feature classifier and the second feature classifier. The system can apply a set of content rules to the feature space to determine content metrics. The system can correlate a set of known labelled data to the feature space to construct determinative training data. The system can train a discrimination model using the content item and the determinative training data. The system can classify content using the discrimination model to assign a content policy to the second content item.

Abstract: An information processing system (10) includes: an acquisition unit (50) configured to sequentially acquire a plurality of elements included in sequential data; a first calculation unit (110) configured to calculate, for each of the plurality of elements, a first indicator indicating which one of a plurality of classes the element belongs to; a weight calculation unit (130) configured to calculate, for each of the plurality of elements, a weight according to a confidence related to calculation of the first indicator; a second calculation unit (120) configured to calculate, based on the first indicators each weighted with the weight, a second indicator indicating which one of the plurality of classes the sequential data belongs to; and a classification unit (60) configured to classify the sequential data as any one of the plurality of classes, based on the second indicator. According to such an information processing system, sequential data can be appropriately classified.

Abstract: A method for identifying a user using an image of an object of the user, the method comprising: obtaining, by an optical sensor of a mobile device, the image of the object, wherein the object comprises a biometric characteristic of the user; providing the image to a neural network; processing the image by the neural network to identify-a position of the object and the object in the image; extracting, from the identified object, the biometric characteristic; storing the biometric characteristic in a storage device; and providing at least the biometric characteristic as input to an identification means to determine whether the biometric characteristic identifies the user.

Abstract: Systems, methods, and devices are described for monitoring and protecting electronic hardware, data assets, and the facility itself, particularly well-suited to monitoring remote facilities and resources in edge locations, including for determining door state for both equipment and personnel doors, and for determining values of one or more environmental parameters, using optical image analytics. An example system includes one or more edge-located hardware monitoring devices having one or more physical sensors, and custom software distributed across edge, cloud, mobile, and enterprise platforms. An example monitoring device can include an embedded computer, various sensors of different types, one or more cameras, a power supply, and several communication interfaces. All or virtually all sensing and processing capabilities can be integrated into the edge device, which utilizes low-cost sensors and video analytics to monitor the environment.

Abstract: Disclosed herein are systems and methods for classifying traffic indicators to detect intersection crossings by a vehicle. A computing device can receive a sequence of frames captured by a capture device mounted to the vehicle, and generate an intersection status data structure for each frame in the sequence of frames using a full-frame classification model. The computing device can also classify a set of features detected in each frame using an object detection model, and detect an intersection crossing event based on the intersection status data structure of each frame and the classification of each of the set of features detected in each frame. The systems and methods described herein improve upon existing traffic light classification models by using a full-frame intersection classification model in connection with traditional object tracking techniques, thereby reducing false-positive crossing-event detection and improving the accuracy of classification in a variety of environmental conditions.

Abstract: Subject matter disclosed herein relates to systems, devices, and/or processes for processing signals relating to surfaces that may be viewable by subjects though one or more devices. In an embodiment, a surface may include one or more devices embedded therein to provide one or more signals to define a portion of the surface.

Abstract: Methods, devices and computer-readable media for processing a compressed video to perform an inference task are disclosed. Processing the compressed video may include selecting a subset of frame encodings of the compressed video, or zero or more modalities (RGB, motion vectors, residuals) of a frame encoding, for further processing to perform the inference task. Pre-existing motion vector and/or residual information in frame encodings of the compressed video are leveraged to adaptively and efficiently perform the inference task. In some embodiments, the inference task is an action recognition task, such as a human action recognition task.

Abstract: A hole filling method for providing a virtual three-dimensional (3D) model, the hole filling method being executable on a computing device and including: acquiring an original learning image and a hole generation learning image for the original learning image, wherein the hole generation learning image is an image in which at least one hole is generated based on the original learning image; generating a hole filling learning image by performing hole filling on the hole generation learning image by using a neural network; performing a spherical transformation on each of the hole filling learning image and the original learning image; and training the neural network based on a difference between the spherically-transformed hole filling learning image and the spherically-transformed original learning image.

Abstract: Techniques are described for optimizing deep learning model performance using image harmonization as a pre-processing step. According to an embodiment, a method comprises decomposing, by a system operatively coupled to a processor, an input image into sub-images. The method further comprises harmonizing the sub-images with corresponding reference sub-images of at least one reference image based on two or more different statistical values respectively calculated for the sub-images and the corresponding reference-sub images, resulting in transformation of the sub-images into modified sub-images images. In some implementations, the modified sub-images can be combined into a harmonized image having a more similar appearance to the at least one reference image relative to the input image.

Abstract: Systems and methods are disclosed for correcting for artificial deformations in anatomical modeling. One method includes obtaining an anatomic model; obtaining information indicating a presence of an artificial deformation of the anatomic model; identifying a portion of the anatomic model associated with the artificial deformation; estimating a non-deformed local area corresponding to the portion of the anatomic model; and modifying the portion of the anatomic model associated with the artificial deformation, based on the estimated non-deformed local area.

Abstract: Patterning device modulates a light beam intensity distribution according to two-gradation first image data having a first number of pixels. Processing device calculates a correlation between detection intensity b based on output of photodetector and m-gradation (m?2) random second image data having a second number of pixels smaller than the first number, to generate a reconstructed image G(x,y) of an object. When the first and second image data are scaled to the same size and overlapped, each pixel is associated with a pixel group including multiple pixels of the overlapping first image data. With the normalized gradation value of a given pixel as k, the number of pixels included in the pixel group as L, and the number of pixels having a value of 1 in the pixel group as l, l=L×k holds true.

Abstract: The device (1) for estimating the distance between an observer (2) and a target (4) using at least one image generated by a digital image generator (6) from the position (P1) of the observer (2) comprises a detection and identification unit configured to detect and identify a target (4) in the image and define an imaged representation of the target (4), and a distance estimation unit configured to perform, on the image, multiple different projections of a three-dimensional model of the target (4) to obtain projected representations of the target (4) and to select the projected representation most similar to the imaged representation, the distance associated with the selected projected representation representing the estimated distance (D) between the position of the observer (2) and the target (4).