Image-Based Automated Change Detection for Synthetic Aperture Sonar by Multistage Coregistration and Canonical Correlation Analysis

In this paper, an automated change detection technique is presented that compares new and historical seafloor images created with sidescan synthetic aperture sonar (SAS) for changes occurring over time. The method consists of a four-stage process: a coarse navigational alignment that relates and approximates pixel locations of reference and repeat–pass data sets; fine-scale coregistration using the scale-invariant feature transform (SIFT) algorithm to match features between overlapping data sets; local coregistration that improves phase coherence; and finally, change detection utilizing a canonical correlation analysis (CCA) algorithm to detect changes. The method was tested using data collected with a high-frequency SAS in a sandy shallow-water environment. Successful results of this multistage change detection method are presented here, and the robustness of the techniques that exploit phase and amplitude levels of the backscattered signals is discussed. It is shown that the coherent nature of the SAS data can be exploited and utilized in this environment over time scales ranging from hours through several days. Robustness of the coregistration methods and analysis of scene coherence over time is characterized by analysis of repeat pass as well as synthetically modified data sets.