Abstract: Embodiments described herein relate, inter alia, to receiving one or more segments of a digital recording, wherein the one or segments include video and/or audio data of a surgical procedure; analyzing, via a video/audio understanding model, the one or more segments to (i) characterize a plurality of independent features associated with a technical skill and/or a non-technical practice that are evident in the one or more segments and (ii) determine a higher-order pattern based upon analyzing a group of at least two of the plurality of independent features; comparing the higher-order pattern to ratings data associated to outcomes following one or more surgical procedures; and automatically generating a quality score based upon the comparing, wherein the quality score is predictive of an assessment of the technical skill and/or non-technical practice.

Abstract: System, methods, and other embodiments described herein relate to predicting lane changes for nearby vehicles of a host vehicle. In one embodiment, a method includes, in response to detecting that one or more of the nearby vehicles are present proximate to the host vehicle, collecting pose information about the nearby vehicles. The nearby vehicles are traveling proximate to the host vehicle and in a direction of the host vehicle. The method includes analyzing the pose information of the nearby vehicles using separate recurrent units of a structural recurrent neural network (S-RNN) to generate factors according to the lanes. The method includes generating prediction indicators for the nearby vehicles as a function of the factors for the lanes using the S-RNN. The method includes providing electronic outputs identifying the prediction indicators that specify a likelihood of the nearby vehicles changing between the lanes.

Abstract: System, methods, and other embodiments described herein relate to predicting lane changes for nearby vehicles of a host vehicle. In one embodiment, a method includes, in response to detecting that one or more of the nearby vehicles are present proximate to the host vehicle, collecting pose information about the nearby vehicles. The nearby vehicles are traveling proximate to the host vehicle and in a direction of the host vehicle. The method includes analyzing the pose information of the nearby vehicles using separate recurrent units of a structural recurrent neural network (S-RNN) to generate factors according to the lanes. The method includes generating prediction indicators for the nearby vehicles as a function of the factors for the lanes using the S-RNN. The method includes providing electronic outputs identifying the prediction indicators that specify a likelihood of the nearby vehicles changing between the lanes.

Abstract: The present invention is a method for carrying out high-level activity recognition on a wide variety of videos. In one embodiment, the invention leverages the fact that a large number of smaller action detectors, when pooled appropriately, can provide high-level semantically rich features that are superior to low-level features in discriminating videos. Another embodiment recognizes activity using a bank of template objects corresponding to actions and having template sub-vectors. The video is processed to obtain a featurized video and a corresponding vector is calculated. The vector is correlated with each template object sub-vector to obtain a correlation vector. The correlation vectors are computed into a volume, and maximum values are determined corresponding to one or more actions.

Abstract: Systems and methods for capturing and mosaicking images of one or more surfaces of a collapsed cavity are described. One embodiment includes capturing images using an endoscope, where the optics of the endoscope are radially symmetrical, locating the optical center and dewarping each of the captured images by mapping the image from polar coordinates centered on the optical center of the image to rectangular coordinates, discarding portions of each dewarped image to create high clarity dewarped images, estimating the motion of the endoscope with respect to the interior surface of the cavity that occurred between successive high clarity dewarped images, registering the high clarity dewarped images with respect to each other using the estimates of motion, and combining the registered high clarity dewarped images to create at least one mosaic.

Abstract: Systems and methods for extracting and measuring motion from images capture during capsule endoscopy in accordance with embodiments of the invention are disclosed. In one embodiment of the invention, an endoscope system configured to generate a spatial index of images captured along a passageway includes a processor and a camera configured to capture a plurality of images as the camera moves along a passageway, wherein the processor is configured to compare sets of at least two images from the plurality of images, determine motion of the camera along the passageway using the sets of at least two images, determine the distance the camera traveled along the passageway at the point at which an image in each of the sets of at least two images was captured, and generate a spatial index for the plurality of images by associating distances traveled along the passageway with the images.

Abstract: Systems and methods for capturing and mosaicking images of one or more surfaces of a collapsed cavity are described. A number of embodiments are capable of performing mosaicking in real time. Many embodiments are configured to perform multiple passes during motion estimation and/or registration to improve the quality of the resulting mosaic(s).