Many object detection systems are constrained by the time required to convolve a target image with a bank of filters that code for different aspects of an object's appearance, such as the presence of component parts. We exploit locality-sensitive hashing to replace the dot-product kernel operator in the convolution with a fixed number of hash-table probes that effectively sample all of the filter responses in time independent of the size of the filter bank. To show the effectiveness of the technique, we apply it to evaluate 100,000 deformable-part models requiring over a million (part) filters on multiple scales of a target image in less than 20 seconds using a single multi-core processor with 20GB of RAM. This represents a speed-up of approximately 20,000 times - four orders of magnitude - when compared with performing the convolutions explicitly on the same hardware. While mean average precision over the full set of 100,000 object classes is around 0.16 due in large part to the challenges in gathering training data and collecting ground truth for so many classes, we achieve a mAP of at least 0.20 on a third of the classes and 0.30 or better on about 20% of the classes.

The graphics processor (GPU) on today's commodity video cards has evolved into an extremely powerful and flexible processor. Modern graphics architectures provide tremendous memory bandwidth and computational horsepower, with dozens of fully programmable shading units that support vector operations and IEEE floating point precision. High-level languages have emerged for graphics hardware, making this computational power accessible. GPGPU stands for "General-Purpose Computation on GPUs". GPGPU researchers have achieved over an order of magnitude speedup over modern CPUs on some non-graphics problems.This course provides detailed coverage of general-purpose computation on graphics hardware. We emphasize core computational building blocks, ranging from linear algebra to database queries, and review the tools, perils, and strategies in GPU programming. We present analysis of GPU performance characteristics, and use this analysis to provide insight into how to build efficient GPGPU algorithms. Finally we present a set of case studies on general-purpose applications of graphics hardware.

article Free Access Share on Fast shadows and lighting effects using texture mapping Authors: Mark Segal Silicon Graphics Computer Systems, 2011 N. Shoreline Blvd., Mountain View, CA Silicon Graphics Computer Systems, 2011 N. Shoreline Blvd., Mountain View, CAView Profile , Carl Korobkin Silicon Graphics Computer Systems, 2011 N. Shoreline Blvd., Mountain View, CA Silicon Graphics Computer Systems, 2011 N. Shoreline Blvd., Mountain View, CAView Profile , Rolf van Widenfelt Silicon Graphics Computer Systems, 2011 N. Shoreline Blvd., Mountain View, CA Silicon Graphics Computer Systems, 2011 N. Shoreline Blvd., Mountain View, CAView Profile , Jim Foran Silicon Graphics Computer Systems, 2011 N. Shoreline Blvd., Mountain View, CA Silicon Graphics Computer Systems, 2011 N. Shoreline Blvd., Mountain View, CAView Profile , Paul Haeberli Silicon Graphics Computer Systems, 2011 N. Shoreline Blvd., Mountain View, CA Silicon Graphics Computer Systems, 2011 N. Shoreline Blvd., Mountain View, CAView Profile Authors Info & Claims ACM SIGGRAPH Computer GraphicsVolume 26Issue 2July 1992 pp 249–252https://doi.org/10.1145/142920.134071Online:01 July 1992Publication History 266citation2,979DownloadsMetricsTotal Citations266Total Downloads2,979Last 12 Months78Last 6 weeks13 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteeReaderPDF

A polyhedral solid modeler that operates on boundary representations of objects must infer topological information from numerical data. Unavoidable errors (due to limited precision) affect these calculations so that their use may produce ambiguous or contradictory results. These effects cause existing polyhedral modelers to fail when presented with objects that nearly align or barely intersect[10][7].An object description associating a tolerance with each of its topological features (vertices, edges, and faces) is introduced. The use of tolerances leads to a definition of topological consistency that is readily applied to boundary representations. The implications of using tolerances to aid in making consistent topological determinations from imprecise geometric data are explored and applied to the calculations of a polyhedral solid modeler. The resulting modeler produces a consistent polyhedral boundary when given consistent boundaries as input.

Algorithms for computer graphics or solids modeling must often infer the structure of geometrical objects from numerical data. Unavoidable errors (due to limited precision) affect the calculations from which these data are produced and may thus affect topological information so derived. Ambiguities or even contradictions may result from inferences made from an object's representation.To resolve these ambiguities for arbitrary polyhedral objects, we introduce a minimum feature size and a face thickness and show how to convert any object description into a form which insures topological immunity to numerical perturbations. The minimum feature size depends on the object's overall dimensions and on its placement in space. The face thickness depends on how well a face's vertices conform to its computed plane.