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
Method of generating integrated circuit model
Focus information generating device and focus information generating method
Enzymatic demethylation of flavonoids
Spectral sensor for checking documents of value
Powerline communication device with load characterization functionality
Method and system for dynamically representing distributed information
  Randomly Featured Patents
Method and apparatus for marking the unbalances onto a rotating body, especially an automobile wheel
Aluminized steel alloys containing chromium
Dynamic memory cell using silicon-on-insulator transistor with trench capacitor
Method and device for selecting one station from a set of stations dialoging with a main station
Method for scavenging radicals with urocanic acid, derivatives and analogues
High-intensity UV-C gun and methods of use
Pallet building machine
Surgical pad for gynecological procedures
Herbicidal 2S-(2.beta.,4.beta.,5.beta.)-5-Arylmethoxy-4-substituted 2-alkyl-1,3-dioxane derivatives