Google Inc.

Christopher James Ducote

Romain Clément

Chetan Mahadeswaraswamy

Ian Rickard Muldoon

Jingjin Xie

A vehicle mounted imaging system tracks and resolves image using an object image regions of interest at a higher resolution than that which can be provided by typical wide-angle optics. The imaging system includes an object identification camera, a sampling camera, and one or more computing devices. The one or more computing devices obtain a full-frame image from the object identification camera and identify at least one region of interest within the full frame image. The one or more computing devices then configure the sampling camera to capture images of a sampling area containing the region of interest, wherein the sampling area consists of some, but not all, of a field of view of the sampling camera. Using a super-image resolution technique, the one or more computing devices create a high-resolution image of the region of interest from a plurality of images captured by the sampling camera.

Feature recognition assisted super-resolution method

Systems and methods for extracting a feature in an image are provided. In one example embodiment, a computer-implemented method includes obtaining image data representing a scene, wherein the image data includes a plurality of images of the scene, each image associated with a different polarization angle. The method includes determining attribute information based at least in part on the plurality of images. The method includes determining one or more features in the image data based at least in part on the attribute information.

Growing community of inventors

San Jose, CA, United States of America

Christopher James Ducote