Dennis Lee Matthies

3D model based vehicle classification in aerial imagery

We present an approach that uses detailed 3D models to detect and classify objects into fine levels of vehicle categories. Unlike other approaches that use silhouette information to fit a 3D model, our approach uses complete appearance from the image. Each 3D model has a set of salient location markers that are determined a-priori. These salient locations represent a sub-sampling of 3D locations that make up the model. Scene conditions are simulated in the rendering of 3D models and the salient locations are used to bootstrap a HoG based feature classifier. HoG features are computed in both rendered and real scenes and a novel object match score the ‘Salient Feature Match Distribution Matrix’ is computed. For each 3D model we also learn the patterns of misalignment with other vehicle types and use it as an additional cue for classification. Results are presented on a challenging aerial video dataset consisting of vehicle imagery from various viewpoints and environmental conditions.1

Rear projection screens for bright ambient applications

Displays typically are not able to deliver a viewable image in sunlight or environments with a high level of ambient light. The degradation of the image contrast is caused by reflection of ambient light from the display surface. Ambient light reflectivity from the display is an important measure of a displays ability to maintain image contrast. Projection displays are mostly used in low ambient light environments. Front projection screens have high reflectivity by design and are totally unsatisfactory for high ambient light applications. Commercially available rear projection screens use a variety of approaches to reduce ambient light reflections. Until now, their reduction was insufficient for daylight applications. An analysis of contrast deficiency in existing screen types is presented. Under DARPA sponsorship, the Max Levy Autograph and Sarnoff Corporations have combined to develop a rear projection screen technology with an improved suppression of ambient light reflections. Screen samples will be manufactured for use in daylight and high ambient environments. Other features of these screens include high resolution and the ability to match light distribution to the viewing requirements. The performance of this new technology is presented in this paper.