A 3D Map Reconstruction Algorithm in Indoor Environment Based on RGB-D Information

In this paper, we proposed an improved Iterative Closest Point (ICP) algorithm which based on features with the discrete selection mechanism for motion estimation to reconstruct 3D map in indoor environment. We started with detecting, descripting and matching SURF features in consecutive RGB images. Moreover, due to the registration accuracy would be influenced by the initial pose of features in original ICP algorithm based on features, we did initial registration using RANdom Sample Consensus (RANSAC) algorithm to optimize the initial pose of features and remove the outliers. Furthermore, we presented a secondary registration method to calculate the refined transformation between point-clouds in the different coordinate systems with features selected by discrete selection mechanism. Finally, we optimized the global map using General Gragh Optimization (G2O) framework combining with key frames, and reconstructed the 3D map. We tested the performance of our proposed algorithm in six public datasets. The results demonstrate that the algorithm is feasible and effectively.