Optimal feature extraction for segmentation of Diesel spray images.

A one-dimensional simplification, based on optimal feature extraction, of the algorithm based on the likelihood-ratio test method (LRT) for segmentation in colored Diesel spray images is presented. If the pixel values of the Diesel spray and the combustion images are represented in RGB space, in most cases they are distributed in an area with a given so-called privileged direction. It is demonstrated that this direction permits optimal feature extraction for one-dimensional segmentation in the Diesel spray images, and some of its advantages compared with more-conventional one-dimensional simplification methods, including considerably reduced computational cost while accuracy is maintained within more than reasonable limits, are presented. The method has been successfully applied to images of Diesel sprays injected at room temperature as well as to images of sprays with evaporation and combustion. It has proved to be valid for several cameras and experimental arrangements.

[1]  J V Pastor,et al.  Diesel spray image segmentation with a likelihood ratio test. , 2001, Applied optics.

[2]  Anders Larsson,et al.  Optical Studies in a DI Diesel Engine , 1999 .

[3]  Karlheinz Prescher,et al.  Investigation of the Atomization and Evaporation of Diesel Fuel and Heavy Fuel Sprays Using Optical Measurement Techniques , 1999 .

[4]  Michael L. Corradini,et al.  Image Analysis of Diesel Sprays , 1992 .

[5]  Makoto Abe,et al.  INVESTIGATION OF DROPLETS AND AMBIENT GAS INTERACTION IN A DIESEL SPRAY USING A NANO-SPARK PHOTOGRAPHY METHOD , 1998 .

[6]  J. Naber,et al.  Effects of Gas Density and Vaporization on Penetration and Dispersion of Diesel Sprays , 1996 .

[7]  Dennis L. Siebers,et al.  Liquid-Phase Fuel Penetration in Diesel Sprays , 1998 .

[8]  José V. Pastor,et al.  The Influence of Injection Parameters on Diesel Spray Characteristics , 1999 .

[9]  Yong Yan,et al.  Quantitative characterization of diesel sprays using digital imaging techniques , 2003 .

[10]  H. Hiroyasu,et al.  Structures of fuel sprays in diesel engines , 1990 .

[11]  Jesús Benajes,et al.  Planar Laser-Induced Fluorescence fuel concentration measurements in isothermal Diesel sprays. , 2002, Optics express.

[12]  Tomohisa Dan,et al.  Effect of Nozzle Configurations for Characteristics of Non-Reacting Diesel Fuel Spray , 1997 .

[13]  Patrick V. Farrell,et al.  A Study on the Effects of Fuel Viscosity and Nozzle Geometry on High Injection Pressure Diesel Spray Characteristics , 1997 .

[14]  Stephen C. Bates.  Further insights into SI four-stroke combustion using flame imaging , 1991 .

[15]  Takashi Sasaki,et al.  Application of Image Converter Camera to Measure Flame Propagation in S.I. Engine , 1989 .

[16]  Dennis L. Siebers,et al.  Measurements of fuel effects on liquid-phase penetration in DI sprays , 1999 .

[17]  J.-H. Lee,et al.  Comparison of colour transformations for image segmentation , 1994 .

[18]  V. Barranco-Lopez,et al.  Entropic texture-edge detection for image segmentation , 1995 .

[19]  Makoto Abe,et al.  Measurement of Droplet Size, Shape and Velocity in Diesel Sprays using a Single and Double Nano-Spark Photography Method , 1998 .

[20]  José M. Desantes,et al.  Analysis of the Combustion Process in a EURO III Heavy-Duty Direct Injection Diesel Engine , 2002 .

[21]  Rolf D. Reitz,et al.  An Experimental and Numerical Study of Sprays from a Common Rail Injection System for Use in an HSDI Diesel Engine , 1998 .

[22]  Michael Wensing,et al.  Spray formation of high-pressure swirl gasoline injectors investigated by two-dimensional Mie and LIEF techniques , 1999 .

[23]  Frederic Truchetet,et al.  Karhunen-Loeve transform applied to region- based segmentation of color aerial images , 2001 .