Abstract: A kinematic analysis system captures and records participant motion via a plurality of video cameras. A participant feature and participant pose are identified in a frame of video data. The feature and pose are correlated across a plurality of frames. A three-dimensional path of the participant is determined based on correlating the feature and pose across the plurality of frames. A potential impact is identified based on analysis of the participant's path.

Abstract: Computer implemented methods for categorizing documents are provided that include: receiving a document having a plurality of headnotes and metadata associated with the document, wherein the plurality of headnotes each comprise a segment of text that summarizes at least a portion of the document; predicting using at least a first machine learning model, for at least a first of the plurality of headnotes, a statute pertaining to the first headnote, wherein the predicted statute has associated therewith a taxonomy of topics; predicting using the first machine learning model, a topic from the taxonomy of topics associated with the statute that the first headnote pertains; and associating the first headnote with the predicted topic.

Abstract: A first image is aligned with a second image. A first motion value is computed based at least in part on a sum of differences between corresponding pixels in the first image and the second image. A second motion value is computed further based at least in part on a third image. An impact score is generated based at least in part on a difference between values derived from the first motion value and the second motion value and an action is performed depending at least in part on whether the impact score indicates that damage has occurred among objects represented in the first image and the second image.

Abstract: A first digital representation in an image and a second digital representation in a second image is identified based at least in part on specified criteria. A first epipolar line in the second image is determined based at least in part on a position of the first digital representation in the image. A second epipolar line is determined based at least in part on a position of the second digital representation in the second image. At least one cost value is determined based at least in part on the first digital representation, the second digital representation, the first epipolar line, and the second epipolar line. The first digital representation and the second digital representation are determined, based at least in part on the at least one cost value, to represent a same object. The first digital representation is associated in a data store with the second digital representation.