Towards consistent reconstructions of indoor spaces based on 6D RGB-D odometry and KinectFusion. Dong, H., Figueroa, N., & El Saddik, A. In 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems, pages 1796-1803, 2014. doi abstract bibtex We focus on generating consistent reconstructions of indoor spaces from a freely moving handheld RGB-D sensor, with the aim of creating virtual models that can be used for measuring and remodeling. We propose a novel 6D RGBD 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. Our algorithm outputs a ready-to-use polygon mesh (highly suitable for creating 3D virtual worlds) without any post-processing steps.
@INPROCEEDINGS{6942798,
author={H. {Dong} and N. {Figueroa} and A. {El Saddik}},
booktitle={2014 IEEE/RSJ International Conference on Intelligent Robots and Systems},
title={Towards consistent reconstructions of indoor spaces based on 6D RGB-D odometry and KinectFusion},
year={2014},
volume={},
number={},
pages={1796-1803},
doi={10.1109/IROS.2014.6942798},
abstract={We focus on generating consistent reconstructions of indoor spaces from a freely moving handheld RGB-D sensor, with the aim of creating virtual models that can be used for measuring and remodeling. We propose a novel 6D RGBD 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. Our algorithm outputs a ready-to-use polygon mesh (highly suitable for creating 3D virtual worlds) without any post-processing steps.}}
Downloads: 0
{"_id":"QyJZssTzKMpT5TkMD","bibbaseid":"dong-figueroa-elsaddik-towardsconsistentreconstructionsofindoorspacesbasedon6drgbdodometryandkinectfusion-2014","downloads":0,"creationDate":"2018-01-25T15:52:37.751Z","title":"Towards consistent reconstructions of indoor spaces based on 6D RGB-D odometry and KinectFusion","author_short":["Dong, H.","Figueroa, N.","El Saddik, A."],"year":2014,"bibtype":"inproceedings","biburl":"https://www.dropbox.com/s/x2bon6vqlc79ekc/FigueroaPublications.bib?dl=1","bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["H."],"propositions":[],"lastnames":["Dong"],"suffixes":[]},{"firstnames":["N."],"propositions":[],"lastnames":["Figueroa"],"suffixes":[]},{"firstnames":["A."],"propositions":[],"lastnames":["El Saddik"],"suffixes":[]}],"booktitle":"2014 IEEE/RSJ International Conference on Intelligent Robots and Systems","title":"Towards consistent reconstructions of indoor spaces based on 6D RGB-D odometry and KinectFusion","year":"2014","volume":"","number":"","pages":"1796-1803","doi":"10.1109/IROS.2014.6942798","abstract":"We focus on generating consistent reconstructions of indoor spaces from a freely moving handheld RGB-D sensor, with the aim of creating virtual models that can be used for measuring and remodeling. We propose a novel 6D RGBD 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. Our algorithm outputs a ready-to-use polygon mesh (highly suitable for creating 3D virtual worlds) without any post-processing steps.","bibtex":"@INPROCEEDINGS{6942798,\n author={H. {Dong} and N. {Figueroa} and A. {El Saddik}},\n booktitle={2014 IEEE/RSJ International Conference on Intelligent Robots and Systems}, \n title={Towards consistent reconstructions of indoor spaces based on 6D RGB-D odometry and KinectFusion}, \n year={2014},\n volume={},\n number={},\n pages={1796-1803},\n doi={10.1109/IROS.2014.6942798}, \n abstract={We focus on generating consistent reconstructions of indoor spaces from a freely moving handheld RGB-D sensor, with the aim of creating virtual models that can be used for measuring and remodeling. We propose a novel 6D RGBD 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. Our algorithm outputs a ready-to-use polygon mesh (highly suitable for creating 3D virtual worlds) without any post-processing steps.}}\n\n","author_short":["Dong, H.","Figueroa, N.","El Saddik, A."],"key":"6942798","id":"6942798","bibbaseid":"dong-figueroa-elsaddik-towardsconsistentreconstructionsofindoorspacesbasedon6drgbdodometryandkinectfusion-2014","role":"author","urls":{},"metadata":{"authorlinks":{"figueroa, n":"https://nbfigueroa.github.io/"}},"downloads":0},"search_terms":["towards","consistent","reconstructions","indoor","spaces","based","rgb","odometry","kinectfusion","dong","figueroa","el saddik"],"keywords":[],"authorIDs":["6weNhrK95SmkxE6z5"],"dataSources":["QscCmn2DGDfW7oiMm","kJNNQTBYdRiDNqEoj","Myci9twJQBkzgwjJt","uKXb3cNPyHxHYR6EG","K8FcWryWvdNmhuTvL","CaGiEo4vZFJvt7iqr"]}