Detection Module
From FarsightWiki
(Difference between revisions)
Line 1: | Line 1: | ||
The tracker is automatically initialized by the detector. Worm detection generally involves: | The tracker is automatically initialized by the detector. Worm detection generally involves: | ||
− | *Binarization and filling small holes (for images with cluttered background, a background image is computed first, then the original image will be subtracted by it to remove static spots) | + | *Binarization and filling small holes (for images with cluttered background, a background image is computed first(figure.1), then the original image will be subtracted by it to remove static spots) |
*Worm boundary extraction based on binary image | *Worm boundary extraction based on binary image | ||
*Head and Tail detection | *Head and Tail detection | ||
Line 8: | Line 8: | ||
− | [[Image:BGImage.png|thumb| | + | [[Image:BGImage.png|thumb|center|700px| Figure.1 Background Image]] |
− | [[Image:DetectionModule2.png|thumb| | + | [[Image:DetectionModule2.png|thumb|center|700px| Figure.2(a) Initialization by Detection on image with clean background]] |
− | [[Image:DetectionModule1.png|thumb| | + | [[Image:DetectionModule1.png|thumb|center|700px| Figure.2(b) Initialization by Detection on image with cluttered background]] |
Revision as of 02:26, 1 July 2009
The tracker is automatically initialized by the detector. Worm detection generally involves:
- Binarization and filling small holes (for images with cluttered background, a background image is computed first(figure.1), then the original image will be subtracted by it to remove static spots)
- Worm boundary extraction based on binary image
- Head and Tail detection
- Center line and width computation
- Instantiation of the worm model.
In the detection module, detection is followed by the worm model validation to remove errors caused by spots in the background or overlapping worms. The detection is also used for correcting mis-tracked worms during the tracking process.