Methods for discriminating moving objects in motion image sequences
View Patent ↗In an exemplary embodiment of the present invention, an automated, computerized method is provided for classifying pixel values in a motion sequence of images. According to a feature of the present invention, the method comprises the steps of determining spectral information relevant to the sequence of images, and utilizing the spectral information to classify a pixel as one of background, shadow and object.
1. Automated, computerized method for tracking an object in a motion sequence of images, comprising the steps of:
a computer executing the following steps:
determining motion pixels from the motion sequence of images;
calculating Nth order tokens as a function of the motion pixels; and
identifying motion of an object as a function of the Nth order tokens, based upon a comparison of spectral ratios and reflectance ratios between Nth order tokens of separate instances of motion pixels, in separate images of the motion sequence of images.
2. The method of claim 1 , wherein the Nth order tokens comprise second order tokens.
3. A computer system, comprising:
a CPU; and
a memory storing a motion sequence of images;
the CPU arranged and configured to execute a routine to determine motion pixels from the motion sequence of images, calculate Nth order tokens as a function of the motion pixels and identify motion of an object as a function of the Nth order tokens, based upon a comparison of spectral ratios and reflectance ratios between Nth order tokens of separate instances of motion pixels, in separate images of the motion sequence of images.