7-m - An Application: Object Tracking How to track this...

Info iconThis preview shows pages 1–5. Sign up to view the full content.

View Full Document Right Arrow Icon
2 An Application: Object Tracking How to track this object against this background pattern/noise?
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
3 Image Subtraction Bright point where object is in second frame Dark point where object was in first frame Then keep only pixels brighter than some threshold value.
Background image of page 2
4 My Problem to Solve • I needed to do this subtraction and thresholding with active videocamera – 30 frames per second = 33 ms per frame • My C++ code took 54 ms to do this: // Subtract background and threshold result simultaneously for (LoopIndex = 0; LoopIndex < ImageSize; LoopIndex++) { ((*ForegroundImage – *BackgroundImage) > Threshold)) { *DataNext++ = LoopIndex; } }
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
5 Solution: Re-write loop in assembly ; C declaration for this routine is: ; void SubThreshLoop(pixel Threshold, image_index ImageSize, image_index* DataNext, pixel* ForegroundImage, pixel* BackgroundImage); ; With register calling convention, variables arrive as follows ; Threshold: AL (EAX) ; Image_Size: EDX ; DataNext: EBX ; ForegroundImage: ECX ; BackgroundImage:
Background image of page 4
Image of page 5
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 09/06/2009 for the course BME 303 taught by Professor Ren during the Spring '08 term at University of Texas at Austin.

Page1 / 8

7-m - An Application: Object Tracking How to track this...

This preview shows document pages 1 - 5. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online