1. Smoke Segmentation Method Based on Improved Differential Box-Counting Fractal Dimension
- Author
-
李桂菊 Li Gui-ju and 于海晶 Yu Hai-jing
- Subjects
Pixel ,Physics::Instrumentation and Detectors ,business.industry ,Computer science ,ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION ,Scale-space segmentation ,Image segmentation ,Mathematical morphology ,Fractal dimension ,Electronic, Optical and Magnetic Materials ,Box counting ,Fractal ,Computer Science::Computer Vision and Pattern Recognition ,Signal Processing ,Segmentation ,Computer vision ,Artificial intelligence ,business ,Instrumentation ,ComputingMethodologies_COMPUTERGRAPHICS - Abstract
Aiming at the different texture characteristics of the forest and the smoke image,a smoke segmentation method about the improvement of differential box-counting(DBC)fractal dimension algorithm is proposed.Firstly,the improved algorithm expands the scope of child window based on the existing algorithm,calculates every pixel fractal dimension and analyses them.Then,it filters the pixels marked the smoke feature by choosing the fit threshold,it can realize smoke image segmentation.Finally,the expansive algorithm in the morphology is used to the connected processing.The experimental results demonstrate that the improved differential box-counting fractal dimension algorithm has a satisfying segmentation result.
- Published
- 2013