Rapid object detection by combining structural information from image segmentation with bio-inspired attentional mechanisms

A computer-implemented method for rapid object detection, comprising:

• an act of causing a data processor to execute instructions stored on a non-transitory memory such that upon execution, the data processor performs operations of:
• oversegmenting an input image into a set of superpixels, each superpixel comprising a plurality of pixels;
• determining, for each superpixel, a bounding box defining a region of the input image representing a detection hypothesis;
• calculating, for each superpixel, an average residual saliency (ARS) for the plurality of pixels belonging to the superpixel;
• eliminating each detection hypothesis that is out of a range of a predetermined threshold value for object size, resulting in a first set of remaining detection hypotheses;
• eliminating each remaining detection hypothesis in the first set of remaining detection hypotheses having an ARS below a predetermined threshold value, resulting in a second set of remaining detection hypotheses;
• calculating, for each remaining detection hypothesis in the second set of remaining detection hypotheses, color contrast for the region defined by the bounding box, and eliminating each detection hypothesis in the second set of remaining detection hypotheses having a color contrast below a predetermined threshold value, resulting in a third set of remaining detection hypotheses;
• and
• outputting the third set of remaining detection hypotheses to a classifier for object recognition.

A computer program product for rapid object detection, the computer program product comprising computer-readable instructions stored on a non-transitory computer-readable medium that are executable by a computer having a processor for causing the processor to perform operations of:

• oversegmenting an input image into a set of superpixels, each superpixel comprising a plurality of pixels;
• determining, for each superpixel, a bounding box defining a region of the input image representing a detection hypothesis;
• calculating, for each superpixel, an average residual saliency (ARS) for the plurality of pixels belonging to the superpixel;
• eliminating each detection hypothesis that is out of a range of a predetermined threshold value for object size, resulting in a first set of remaining detection hypotheses;
• eliminating each remaining detection hypothesis in the first set of remaining detection hypotheses having an ARS below a predetermined threshold value, resulting in a second set of remaining detection hypotheses;
• calculating, for each remaining detection hypothesis in the second set of remaining detection hypotheses, color contrast for the region defined by the bounding box, and eliminating each detection hypothesis in the second set of remaining detection hypotheses having a color contrast below a predetermined threshold value, resulting in a third set of remaining detection hypotheses;
• and
• outputting the third set of remaining detection hypotheses to a classifier for object recognition.