Resources Contact Us Home
System and method for detecting still objects in images

Image Number 6 for United States Patent #7853072.

The present invention provides an improved system and method for object detection with histogram of oriented gradient (HOG) based support vector machine (SVM). Specifically, the system provides a computational framework to stably detect still or not moving objects over a wide range of viewpoints. The framework includes providing a sensor input of images which are received by the "focus of attention" mechanism to identify the regions in the image that potentially contain the target objects. These regions are further computed to generate hypothesized objects, specifically generating selected regions containing the target object hypothesis with respect to their positions. Thereafter, these selected regions are verified by an extended HOG-based SVM classifier to generate the detected objects.

  Recently Added Patents
Electronic device with embedded antenna
Communication terminal device, and recording medium
Method and system for modeling a common-language speech recognition, by a computer, under the influence of a plurality of dialects
DFPase enzymes from Aplysia californica
Methods of making a diagnostic device by interweaving hydrophobic and hydrophilic fibers, and diagnostic device therefrom
Quaternary chalcogenide wafers
System and method for redirected firewall discovery in a network environment
  Randomly Featured Patents
Support and thermal transfer image-recording material
Apparatus for recording a wobbling, spiral guide groove on an optical disc
Water-free metaloxide colloids and metal oxide polymers, method for the production thereof and use thereof
Cantilever fastener assembly
Laser beam transformation and combination using tapered waveguides
Door, deep draw molded door facing, and methods of forming door and facing
Damped steering mechanism for a watercraft
System and method for generating multiple parallel beams and planes
Enhanced analysis of array-based netlists via phase abstraction