The proposed system has been found to have significantly superior discrimination and robustness capabilities allowing to detect an unknown target in an input scene and to determine the target's trajectory when this target is in motion.
Traditionally, an optical correlator is used to compare an unknown input scene with a pre-captured reference image library, to detect if the reference occurs within the input.
To calculate this measure, we used the saliency map as a binary classifier on every location in an input scene.
Reliable vision-based control of an autonomous vehicle requires the ability to focus attention on the important features in an input scene.
We present the design of correlation filters for detection of a target in a noisy input scene when the object of interest is given in a noisy reference image.
One possibility is that posterior hippocampus processes visuospatial input to support the formation of a scene representation.
The ar-chitecture uses the color and texture features as input attributes to discriminate the objects in a scene.
The pattern recognition system is also designed for the identification of multiple targets belonging to multiple reference objects simultaneously in a given input scene.
From top to bottom rows: scenes with turbidities T=1.9, T=2.11, T=2.94, and T=4.36. a Input real scenes.
In addition, we developed a scene change detection method to handle various input videos containing one or more scene changes.
A trial begins with the presentation of a scene (e.g., A), which activates the cells that receive input from that scene (e.g., C Aa, C Ab, C Ac, C Ad).
