Robust foreground segmentation and image registration for optical detection of GEO objects

Abstract With the rapid growth in space utilisation, the probability of collisions between space assets and orbital debris also increases substantially. To support the safe utilisation of space and prevent disruptions to satellite-based services, maintaining space situational awareness (SSA) is crucial. A vital first step in achieving SSA is detecting the man-made objects in orbit, such as space-crafts and debris. We focus on the surveillance of Geo-stationary (GEO) orbital band, due to the prevalence of major assets in GEO. Detecting objects in GEO is challenging, due to the objects being significantly distant (hence fainter) and slow moving relative to the observer (e.g., a ground station or an observing satellite). In this paper, we introduce a new detection technique called GP-ICP to detect GEO objects using optical sensors that is applicable for both ground and space-based observations. Our technique is based on mathematically principled methods from computer vision (robust point set registration and line fitting) and machine learning (Gaussian process regression). We demonstrate the superior performance of our technique in detecting objects in GEO.

[1]  Jorge Núñez,et al.  Improving space debris detection in GEO ring using image deconvolution , 2015 .

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

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

[4]  Pavel Krsek,et al.  The Trimmed Iterative Closest Point algorithm , 2002, Object recognition supported by user interaction for service robots.

[5]  Radu Danescu,et al.  Long Baseline Stereovision for Automatic Detection and Ranging of Moving Objects in the Night Sky , 2012, Sensors.

[6]  Scot S. Olivier,et al.  The Space-based Telescopes for Actionable Refinement of Ephemeris (STARE) mission , 2013 .

[7]  Jayant Sharma,et al.  The Space-Based Visible Program , 2000 .

[8]  Radu Danescu,et al.  A Low Cost Automatic Detection and Ranging System for Space Surveillance in the Medium Earth Orbit Region and Beyond , 2014, Sensors.

[9]  Martin Matoušek,et al.  RANSACing Optical Image Sequences for GEO and near-GEO Objects , 2013 .

[10]  Hirohisa Kurosaki,et al.  Automatic Detection Algorithm for Small Moving Objects , 2005 .

[11]  D. J. Salmond,et al.  A particle filter for track-before-detect , 2001, Proceedings of the 2001 American Control Conference. (Cat. No.01CH37148).

[12]  Radim Sara,et al.  FAINT STREAK DETECTION WITH CERTIFICATE BY ADAPTIVE MULTI-LEVEL BAYESIAN INFERENCE , 2017 .

[13]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[14]  Paul J. Besl,et al.  A Method for Registration of 3-D Shapes , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Toshiya Hanada,et al.  Detection of Faint GEO Objects Using Population and Motion Prediction , 2010 .

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

[17]  S. C. Pohlig,et al.  An algorithm for detection of moving optical targets , 1989 .

[18]  Andrew Zisserman,et al.  Multiple View Geometry in Computer Vision (2nd ed) , 2003 .

[19]  Sylvie Buteau,et al.  Image processing technique for automatic detection of satellite streaks , 2007 .

[20]  J. Rice,et al.  TAOS: The Taiwanese–American Occultation Survey , 2003 .

[21]  Hirohisa Kurosaki,et al.  Activities of JAXA's Innovative Technology Center on Space Debris Observation , 2006 .

[22]  Hirohisa Kurosaki,et al.  Optical Observation, Image-processing, and Detection of Space Debris in Geosynchronous Earth Orbit , 2014 .

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

[24]  Nello Cristianini,et al.  Kernel Methods for Pattern Analysis , 2003, ICTAI.

[25]  E. Bertin,et al.  SExtractor: Software for source extraction , 1996 .

[26]  V. V. Kouprianov,et al.  Distinguishing features of CCD astrometry of faint GEO objects , 2008 .

[27]  Tim Flohrer,et al.  Space-Based Optical Observations of Space Debris , 2005 .

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

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

[30]  Chandrika Kamath,et al.  Blind Detection of Ultra-faint Streaks with a Maximum Likelihood Method , 2016 .

[31]  Thomas Schildknecht,et al.  Optical surveys for space debris , 2007 .

[32]  Neil J. Gordon,et al.  Recursive track-before-detect with target amplitude fluctuations , 2005 .