Performance Evaluation of Feature Matching Techniques for Detecting Reinforced Soil Retaining Wall Displacement

Image registration technology is widely applied in various matching methods. In this study, we aim to evaluate the feature performance and find an optimal technique for detecting three types of behaviors—facing displacement, settlement, combined displacement—in reinforced soil retaining walls (RSWs). For a single block with artificial target multiblock structure natural targets, five popular detectors descriptors—KAZE, SURF, MinEigen, ORB, BRISK—were used resolution performance. comparison, repeatability, score, inlier features were analyzed based on number extracted matched features. The axial error (ARE) was verify accuracy methods by comparing position between estimated real results showed that KAZE method best detector descriptor RSWs (block shape target), highest probability successfully experiment, as similar attached. Therefore, behaviors RSW blocks can be using without installing target.