摘要:
System and method for analyzing multiple participants' eye-movements over a visual display to determine which features on the display universally attract the most attention, or are the most distracting.
摘要:
A computer-implemented process for smoothing and compression of data having an ordered list of points including a first point, a second point and a third point, each of the points being on the perimeter of a polygon. The method includes determining whether the triangle defined by line segments joining the first, second, and third points has a point of significance in its interior; and if no point of significance is present in the region, removing the second point of the ordered list of points.
摘要:
A computer based system and method for real-time display of co-registered historical and current side scan sonar imagery during a side scan sonar survey. Embodiments also include modules for detection of clutter in the current imagery, identification of features, extraction of snippets, filtering based on predetermined size and shape parameters, and determination if a current feature is the same as a previously identified contact from historical imagery.
摘要:
A computer-implemented method, system, computer-readable medium, and apparatus for identifying a boundary of a cluster in a bitmap, the bitmap having at least one initially set bit, for applying an expansion shape to each of the initially set bits in the bitmap and identifying vertex bits on the boundary of the cluster formed by at least one expansion shape.
摘要:
A computer based system and method for real-time display of co-registered historical and current side scan sonar imagery during a side scan sonar survey. Embodiments also include modules for detection of clutter in the current imagery, identification of features, extraction of snippets, filtering based on predetermined size and shape parameters, and determination if a current feature is the same as a previously identified contact from historical imagery.
摘要:
A method, system, computer-readable medium, and apparatus for identifying a boundary of a cluster in a bitmap, the bitmap having at least one initially set bit, for applying an expansion shape to each of the initially set bits in the bitmap and identifying vertex bits on the boundary of the cluster formed by at least one expansion shape. A method system, computer-readable medium, and apparatus for identifying vertex bits in a bitmap having at least two adjacent bits with non-zero values forming a boundary of a cluster, the interior bits of the cluster having a zero value, including starting from a current non-zero bit, evaluating at least a first adjacent bit and a second adjacent bit, setting an adjacent non-zero bit as the new current bit, and identifying the current bit as a vertex bit if a direction of motion from the current bit to the new current bit changes.
摘要:
A computer based system and method for real-time display of co-registered historical and current side scan sonar imagery during a side scan sonar survey. Embodiments also include modules for detection of clutter in the current imagery, identification of features, extraction of snippets, filtering based on predetermined size and shape parameters, and determination if a current feature is the same as a previously identified contact from historical imagery.
摘要:
A boosting—based method and system for fusing a set of classifiers that performs classification using weak learners trained on different views of the training data. The final ensemble contains learners that are trained on examples sampled with a shared sampling distribution. The combination weights for the final weighting rule are obtained at each iteration based on the lowest training error among the views. Weights are updated in each iteration based on the lowest training error among all views at that iteration to form the shared sampling distribution used at the next iteration. In each iteration, a weak learner is selected from the pool of weak learners trained on disjoint views based on the lowest training error among all views, resulting in a lower training and generalization error bound of the final hypothesis.
摘要:
The moving map composer (MMC) is a device that allows a user to manipulate different sources of map data into a single map for presentation on a display. The MMC has an ability to extract a predetermined area of map coverage defined by sets of latitude and longitude points, or non-orthogonal areas of map coverage, the smallest of which is a segment. A bitmap is a representation of an available map coverage for a given area selected by a user having a “set”, or “1” bit to indicate a segment is present, and a “clear”, or “0” bit to indicate a segment is missing. The size of the bitmap is determined dynamically to assure a two-bit buffer zone of clear bits around a polygon's maximum extent. If the user selected polygon crosses one or more maps, the polygon is subdivided into several new polygons. Once the total map coverage desired has been defined, what available map sources are determined and the resulting subset is displayed, if the resulting coverage is acceptable, the user may transfer the data to the display.