Robust static and moving object detection system via attentional mechanisms
Described, is a system for object detection via multi-scale attentional mechanisms. The system receives a multi-band image as input. Anti-aliasing and downsampling processes are performed to reduce the size of the multi-band image. Targeted contrast enhancement is performed on the multi-band image to enhance a target color of interest. A response map for each target color of interest is generated, and each response map is independently processed to generate a saliency map. The saliency map is converted into a set of detections representing potential objects of interest, wherein each detection is associated with parameters, such as position parameters, size parameters, an orientation parameter, and a score parameter. A post-processing step is applied to filter out false alarm detections in the set of detections, resulting in a final set of detections. Finally, the final set of detections and their associated parameters representing objects of interest is output.
1. A system for object detection via attentional mechanisms, the system comprising:
one or more processors and a non-transitory computer-readable medium having executable instructions encoded thereon such that when executed, the one or more processors 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.
2. The system as set forth in claim 1 , wherein the post-processing process receives, as input, a confidence function which takes each detection in the set of detections and its associated plurality of parameters and outputs a probability of acceptance for further processing for each detection.
3. The system as set forth in claim 2 , wherein the score parameter is a value which indicates the detection's strength or confidence in the saliency map.
4. The system as set forth in claim 3 , wherein the saliency process is a spectral residue saliency process.
5. The system as set forth in claim 4 , wherein the one or more processors further perform an operation of detecting stationary and moving objects of unknown type from the multi-band image.
6. 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.
7. The method as set forth in claim 6 , wherein the post-processing process receives, as input, a confidence function which takes each detection in the set of detections and its associated plurality of parameters and outputs a probability of acceptance for further processing for each detection.
8. The method as set forth in claim 7 , wherein the score parameter is a value which indicates the detection's strength or confidence in the saliency map.
9. The method as set forth in claim 8 , wherein the saliency process is a spectral residue saliency process.
10. The method as set forth in claim 9 , wherein the data processor further performs an operation of detecting stationary and moving objects of unknown type from the multi-band image.
11. 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.
12. The computer program product as set forth in claim 11 , wherein the post-processing process receives, as input, a confidence function which takes each detection in the set of detections and its associated plurality of parameters and outputs a probability of acceptance for further processing for each detection.
13. The computer program product as set forth in claim 12 , wherein the score parameter is a value which indicates the detection's strength or confidence in the saliency map.
14. The computer program product as set forth in claim 13 , wherein the saliency process is a spectral residue saliency process.
15. The computer program product as set forth in claim 14 , further comprising instructions for causing the processor to perform an operation of detecting stationary and moving objects of unknown type from the multi-band image.