Performance and Analysis of Feature Tracking Approaches in Laser Speckle Instrumentation

This paper investigates the application of feature tracking algorithms as an alternative data processing method for laser speckle instrumentation. The approach is capable of determining both the speckle pattern translation and rotation and can therefore be used to detect the in-plane rotation and translation of an object simultaneously. A performance assessment of widely used feature detection and matching algorithms from the computer vision field, for both translation and rotation measurements from laser speckle patterns, is presented. The accuracy of translation measurements using the feature tracking approach was found to be similar to that of correlation-based processing with accuracies of 0.025-0.04 pixels and a typical precision of 0.02-0.09 pixels depending upon the method and image size used. The performance for in-plane rotation measurements are also presented with rotation measurement accuracies of <0.01 degrees found to be achievable over an angle range of +/- 10 degrees and of <0.1 degrees over a range of +/- 25 degrees, with a typical precision between 0.02 and 0.08 degrees depending upon method and image size. The measurement range is found to be limited by the failure to match sufficient speckles at larger rotation angles. An analysis of each stage of the process was conducted to identify the most suitable approaches for use with laser speckle images and areas requiring further improvement. A quantitative approach to assessing different feature tracking methods is described, and reference data sets of experimentally translated and rotated speckle patterns from a range of surface finishes and surface roughness are presented. As a result, three areas that lead to the failure of the matching process are identified as areas for future investigation: the inability to detect the same features in partially decorrelated images leading to unmatchable features, the variance of computed feature orientation between frames leading to different descriptors being calculated for the same feature, and the failure of the matching processes due to the inability to discriminate between different features in speckle images.