Performance Analysis of 3D-SIFT and ICP Algorithms for Pose Estimation: *Note: Sub-titles are not captured in Xplore and should not be used

The performance of 3D Scale-Invariant Feature Transform (SIFT) and Iterative Closest Point (ICP) algorithms is crucial for pose estimation, particularly in applications such as satellite docking. Despite extensive research on individual algorithms, integrating these methods to enhance overall performance remains underexplored. This study develops and integrates both 3D SIFT and ICP algorithms to improve pose estimation accuracy. The 3D SIFT algorithm converts 2D RGB images to grayscale, performs edge detection, and reconstructs surfaces. The GrabCut method isolates foreground points for feature detection and matching. Depth maps then transform 3D data into 2D data for analysis. ICP algorithm processes source and target point cloud data, using Euclidean distance to compute minimum distances and evaluate error, accuracy, and robustness. Keypoints are detected in the depth image and are matched with the scaled image. Using the continues alignment approach, the source and target are completely converged