FAINT STREAK DETECTION WITH CERTIFICATE BY ADAPTIVE MULTI-LEVEL BAYESIAN INFERENCE

It is known that detecting straight streaks from fast moving celestial objects in optical images is an easy problem as long as the streaks are sufficiently long and/or their signal-to-background (SBR) is sufficiently high. At low SBR the situation is different. Since the SBR can be arbitrarily small in practice, a good detection procedure has to provide a detection certificate which is a yes/no answer to the question “does the image contain a streak?” In this paper we pose detection with certificate as a Multi-Level Bayesian Inference (MLBI) problem which is based on Bayesian model selection. We describe the algorithm and show an experimental proof of good behavior on synthetic streaks over real image data. A systematic performance evaluation shows that MLBI confirms and partially exceeds results of state-of-the art methods. In particular, in the class of difficult problem instances with SBR of 0 dB to −5 dB and streak length 10 to 500 pixels, we achieved AUC ≈ 0.97, which means that the Bayesian detection certificate is wrong in just 3% of cases.

[1]  Thomas Schildknecht,et al.  Streak detection algorithm for space debris detection on optical images. , 2015 .

[2]  Alexander M. Bronstein,et al.  Inverting RANSAC: Global model detection via inlier rate estimation , 2015, CVPR.

[3]  Radu Danescu,et al.  Automatic detection of MEO satellite streaks from single long exposure astronomic images , 2014, 2014 International Conference on Computer Vision Theory and Applications (VISAPP).

[4]  A. E. Kolessa.  Detection of Faint Space Debris Elements with Unknown Orbits , 2013 .

[5]  Toshiya Hanada,et al.  Comparison Between Four Detection Algorithms For GEO Objects , 2012 .

[6]  Hirohisa Kurosaki,et al.  Orbital objects detection algorithm using faint streaks , 2016 .

[7]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[8]  Gerald Sommer,et al.  The Signal Multi-Vector , 2010, Journal of Mathematical Imaging and Vision.

[9]  Ross Marchant,et al.  Feature Detection from the Maximal Response to a Spherical Quadrature Filter Set , 2012, 2012 International Conference on Digital Image Computing Techniques and Applications (DICTA).

[10]  Tero Säntti,et al.  Streak detection and analysis pipeline for space-debris optical images , 2016 .

[11]  Atsushi Nakajima,et al.  Detection of Small LEO Debris with Line Detection Method , 2005 .

[12]  David J. C. MacKay,et al.  Information Theory, Inference, and Learning Algorithms , 2004, IEEE Transactions on Information Theory.

[13]  Peter S. Gural,et al.  Matched Filter Processing for Asteroid Detection , 2005 .

[14]  Michael Felsberg,et al.  The monogenic signal , 2001, IEEE Trans. Signal Process..

[15]  Hirohisa Kurosaki,et al.  The stacking method: The technique to detect small size of GEO debris and asteroids , 2003 .

[16]  N. Ikoma,et al.  Faint Debris Detection by Particle Based Track-Before-Detect Method , 2014 .

[17]  John T. McGraw,et al.  GPU-accelerated Faint Streak Detection for Uncued Surveillance of LEO , 2013 .

[18]  Jia-Guu Leu.  A computer vision process to detect and track space debris using ground-based optical telephoto images , 1992, [1992] Proceedings. 11th IAPR International Conference on Pattern Recognition.