A Combined Approach Toward Consistent Reconstructions of Indoor Spaces Based on 6D RGB-D Odometry and KinectFusion. Figueroa, N., Dong, H., & El Saddik, A. ACM Trans. Intell. Syst. Technol., Association for Computing Machinery, New York, NY, USA, March, 2015.
A Combined Approach Toward Consistent Reconstructions of Indoor Spaces Based on 6D RGB-D Odometry and KinectFusion [link]Paper  doi  abstract   bibtex   1 download  
We propose a 6D RGB-D odometry approach that finds the relative camera pose between consecutive RGB-D frames by keypoint extraction and feature matching both on the RGB and depth image planes. Furthermore, we feed the estimated pose to the highly accurate KinectFusion algorithm, which uses a fast ICP (Iterative Closest Point) to fine-tune the frame-to-frame relative pose and fuse the depth data into a global implicit surface. We evaluate our method on a publicly available RGB-D SLAM benchmark dataset by Sturm et al. The experimental results show that our proposed reconstruction method solely based on visual odometry and KinectFusion outperforms the state-of-the-art RGB-D SLAM system accuracy. Moreover, our algorithm outputs a ready-to-use polygon mesh (highly suitable for creating 3D virtual worlds) without any postprocessing steps.
@article{10.1145/2629673, author = {Figueroa, Nadia and Dong, Haiwei and El Saddik, Abdulmotaleb}, title = {A Combined Approach Toward Consistent Reconstructions of Indoor Spaces Based on 6D RGB-D Odometry and KinectFusion}, year = {2015}, issue_date = {May 2015}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, volume = {6}, number = {2}, issn = {2157-6904}, url = {https://doi.org/10.1145/2629673}, doi = {10.1145/2629673}, abstract = {We propose a 6D RGB-D odometry approach that finds the relative camera pose between consecutive RGB-D frames by keypoint extraction and feature matching both on the RGB and depth image planes. Furthermore, we feed the estimated pose to the highly accurate KinectFusion algorithm, which uses a fast ICP (Iterative Closest Point) to fine-tune the frame-to-frame relative pose and fuse the depth data into a global implicit surface. We evaluate our method on a publicly available RGB-D SLAM benchmark dataset by Sturm et al. The experimental results show that our proposed reconstruction method solely based on visual odometry and KinectFusion outperforms the state-of-the-art RGB-D SLAM system accuracy. Moreover, our algorithm outputs a ready-to-use polygon mesh (highly suitable for creating 3D virtual worlds) without any postprocessing steps.}, journal = {ACM Trans. Intell. Syst. Technol.}, month = mar, articleno = {14}, numpages = {10}, keywords = {Indoor mapping, kinect, benchmark datasets, evaluation} }

Downloads: 1