Analysis of the Effectiveness of the Robust Contrast Feature Detector

The paper presents a robust algorithm for detecting of features, the effectiveness of the robust detector of bright and dark features analyzed in the processing of natural scene images. Images in computer vision systems are often exposed to noise, such action causes detector performance degradation and increases of rate false alarms. Research shows that the effectiveness of the features detection weakly dependent on the mathematical moments of the analyzed image and determined the rate of false alarm. The level of false alarm rate in the test of the detector does not depend on a priori unknown mean and standard deviation of the background process.

[1]  Larry H. Matthies,et al.  The Mars Exploration Rovers Descent Image Motion Estimation System , 2004, IEEE Intell. Syst..

[2]  Konstantin Rumyantsev,et al.  An analysis of feature detection efficiency on images with a priori unknown and changing viewing conditions , 2016, 2016 5th International Conference on Informatics, Electronics and Vision (ICIEV).

[3]  J.R. Gabriel,et al.  On the relationship between the GLRT and UMPI tests for the detection of signals with unknown parameters , 2005, IEEE Transactions on Signal Processing.

[4]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[5]  Danilo Orlando,et al.  A Unifying Framework for Adaptive Radar Detection in Homogeneous Plus Structured Interference— Part I: On the Maximal Invariant Statistic , 2015, IEEE Transactions on Signal Processing.

[6]  Petrov Dmitry,et al.  Robust algorithm for detection of image features , 2016 .

[7]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[8]  Konstantin Rumyantsev,et al.  Universal robust algorithm for detection of image features , 2016, 2016 12th World Congress on Intelligent Control and Automation (WCICA).

[9]  Mukund Desai,et al.  Robust non-Gaussian matched subspace detectors , 2002, 2002 11th European Signal Processing Conference.

[10]  William A. Gardner,et al.  Signal interception: a unifying theoretical framework for feature detection , 1988, IEEE Trans. Commun..

[11]  Petrov Dmitry,et al.  Detection of feature points on the three-dimensional scene under varying conditions of observation , 2015, 2015 34th Chinese Control Conference (CCC).