Robust static and moving object detection system via attentional mechanisms

A computer-implemented method for object detection via attentional mechanisms, 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:
• receiving a multi-band image as input, the multi-band image having a size;
• performing an anti-aliasing process and a downsampling process to reduce the size of the multi-band image;
• performing targeted contrast enhancement on the multi-band image to enhance at least one target color of interest;
• generating a response map for each target color of interest;
• processing each response map independently through a saliency process to generate at least one saliency map;
• converting the at least one saliency map into a set of detections representing potential objects of interest, wherein each detection in the set of detections is associated with a plurality of parameters selected from the group consisting of position parameters, size parameters, an orientation parameter, and a score parameter;
• filtering the set of detections in a post-processing process to reduce false alarms, resulting in a final set of detections;
• and
• outputting the final set of detections and their associated plurality of parameters representing objects of interest.

A computer program product for object detection via attentional mechanisms, 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:

• receiving a multi-band image as input, the multi-band image having a size;
• performing an anti-aliasing process and a downsampling process to reduce the size of the multi-band image;
• performing targeted contrast enhancement on the multi-band image to enhance at least one target color of interest;
• generating a response map for each target color of interest;
• processing each response map independently through a saliency process to generate at least one saliency map;
• converting the at least one saliency map into a set of detections representing potential objects of interest, wherein each detection in the set of detections is associated with a plurality of parameters selected from the group consisting of:
• position parameters, size parameters, an orientation parameter, and a score parameter;
• filtering the set of detections in a post-processing process to reduce false alarms, resulting in a final set of detections;
• and
• outputting the final set of detections and their associated plurality of parameters representing objects of interest.