초록 ▼

A system and method of tracking moving targets in video images comprises retrieving a reference video frames each comprising arrays of digital pixels; computing a first averaged image for each of the reference video frames, wherein each pixel value of the first averaged image comprises an average pi

A system and method of tracking moving targets in video images comprises retrieving a reference video frames each comprising arrays of digital pixels; computing a first averaged image for each of the reference video frames, wherein each pixel value of the first averaged image comprises an average pixel intensity value associated with all corresponding pixel values in the reference video frames; computing a second averaged image for a second set of the reference video frames, wherein each pixel value of the second averaged image comprises an average pixel intensity value associated with all corresponding pixel values in the reference video frames; viewing an input video frame comprising arrays of digital pixels; subtracting the input video frame from the first and second averaged images separately to form at two difference images; and combining the difference images to form a change map.

대표청구항 ▼

What is claimed is: 1. A method of tracking moving targets in video images, said method comprising: retrieving a plurality of reference video frames each comprising arrays of digital pixels; computing a first averaged image for each of said plurality of reference video frames, wherein each pixel va

What is claimed is: 1. A method of tracking moving targets in video images, said method comprising: retrieving a plurality of reference video frames each comprising arrays of digital pixels; computing a first averaged image for each of said plurality of reference video frames, wherein each pixel value of said first averaged image comprises an average pixel intensity value associated with all corresponding pixel values in said plurality of reference video frames; computing a second averaged image for a second set of said plurality of reference video frames, wherein each pixel value of said second averaged image comprises an average pixel intensity value associated with all corresponding pixel values in said plurality of reference video frames; viewing an input video frame comprising arrays of digital pixels, wherein said input video frame is sequenced consecutively after said plurality of reference video frames; subtracting said input video frame from the first and second averaged images separately to form two difference images; and combining said difference images to form a change map. 2. The method of claim 1, further comprising multiplying each pixel value associated with a first difference image with the value of a corresponding pixel of the second difference image. 3. The method of claim 1, further comprising combining an even number of difference images together, wherein said even number is at least two. 4. The method of claim 1, further comprising computing a mean and standard deviation associated with said average pixel intensity values for each predefined, non-overlapping, and fully partitioning blocks of said change map. 5. The method of claim 1, further comprising measuring a magnitude of change experienced in each partitioning block of said change map. 6. The method of claim 1, further comprising: enhancing a digital signature of moving objects in said change map using a pyramidal mean stacking process; determining a pixel location in the enhanced change map that exhibits a highest pixel intensity value; determining whether said highest pixel intensity value meets a minimum acceptance threshold for detection; and determining whether a maximum allowable number of detections per input frame has been reached. 7. The method of claim 6, further comprising predefining values for said minimum acceptance threshold for detection and maximum allowable number of detections per input frame. 8. A program storage device readable by computer, tangibly embodying a program of instructions executable by said computer to perform a method of tracking moving targets in video images, said method comprising: retrieving a plurality of reference video frames each comprising arrays of digital pixels; computing a first averaged image for each of said plurality of reference video frames, wherein each pixel value of said first averaged image comprises an average pixel intensity value associated with all corresponding pixel values in said plurality of reference video frames; computing a second averaged image for a second set of said plurality of reference video frames, wherein each pixel value of said second averaged image comprises an average pixel intensity value associated with all corresponding pixel values in said plurality of reference video frames; viewing an input video frame comprising arrays of digital pixels, wherein said input video frame is sequenced consecutively after said plurality of reference video frames; subtracting said input video frame from the first and second averaged images separately to form two difference images; and combining said difference images to form a change map. 9. The program storage device of claim 8, wherein said method further comprises multiplying each pixel value associated with a first difference image with a value of a corresponding pixel of a second difference image. 10. The program storage device of claim 8, wherein said method further comprises combining an even number of difference images together, wherein said even number is at least two. 11. The program storage device of claim 8, wherein said method further comprises computing a mean and standard deviation associated with said average pixel intensity values for each predefined, non-overlapping, and fully partitioning blocks of said change map. 12. The program storage device of claim 8, wherein said method further comprises measuring a magnitude of change experienced in each partitioning block of said change map. 13. The program storage device of claim 8, wherein said method further comprises: enhancing a digital signature of moving objects in said change map using a pyramidal mean stacking process; determining a pixel location in the enhanced change map that exhibits a highest pixel intensity value; determining whether said highest pixel intensity value meets a minimum acceptance threshold for detection; and determining whether a maximum allowable number of detections per input frame has been reached. 14. The program storage device of claim 13, wherein said method further comprises predefining values for said minimum acceptance threshold for detection and maximum allowable number of detections per input frame. 15. A system for tracking moving targets in video images, said system comprising: means for retrieving a plurality of reference video frames each comprising arrays of digital pixels; means for computing a first averaged image for each of said plurality of reference video frames, wherein each pixel value of said first averaged image comprises an average pixel intensity value associated with all corresponding pixel values in said plurality of reference video frames; means for computing a second averaged image for a second set of said plurality of reference video frames, wherein each pixel value of said second averaged image comprises an average pixel intensity value associated with all corresponding pixel values in said plurality of reference video frames; means for viewing an input video frame comprising arrays of digital pixels, wherein said input video frame is sequenced consecutively after said plurality of reference video frames; means for subtracting said input video frame from the first and second averaged images separately to form at least two difference images; and means for combining said difference images to form a change map. 16. The system of claim 15, further comprising means for multiplying each pixel value associated with a first difference image with a value of a corresponding pixel of a second difference image. 17. The system of claim 15, further comprising means for combining an even number of difference images together, wherein said even number is at least two. 18. The system of claim 15, further comprising means for computing a mean and standard deviation associated with said average pixel intensity values for each predefined, non-overlapping, and fully partitioning blocks of said change map. 19. The system of claim 15, further comprising means for measuring a magnitude of change experienced in each partitioning block of said change map. 20. The system of claim 15, further comprising: means for enhancing a digital signature of moving objects in said change map using a pyramidal mean stacking process; means for determining a pixel location in the enhanced change map that exhibits a highest pixel intensity value; means for determining whether said highest pixel intensity value meets a minimum acceptance threshold for detection; and means for determining whether a maximum allowable number of detections per input frame has been reached. 21. The system of claim 20, further comprising means for predefining values for said minimum acceptance threshold for detection and maximum allowable number of detections per input frame.