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
Ultrathin fluid-absorbent cores
Front exterior of an automotive tail lamp
Polypeptide microparticles
Systems and methods for picture based communication
Photon density wave based determination of physiological blood parameters
High-density fiber optic modules and module housings and related equipment
Gangable electrical box and leveling assembly
  Randomly Featured Patents
Open-architecture system for real-time consolidation of information from multiple financial systems
Label-free methods using a resonant waveguide grating biosensor to determine GPCR signaling pathways
Ultra short baseline GNSS receiver
Smokeless tobacco composition
Skid steer loader
Systems and methods to approve electronic payments
Anti-fouling tethering device for displaying flags
Boom curtain with zipper connections and method of assembling boom
Scalable reconfigurable concurrent filter for wide-bandwidth communication