Abstract
Vision-based localization is susceptible to interference from dynamic objects in the environment, resulting in decreased localization accuracy and even tracking loss. Hence, sensor fusion with IMUs or motor encoders has been widely adopted to improve positioning accuracy and robustness in dynamic environments. Commonly used loose coupling fusion localization methods cannot completely eliminate the error introduced by dynamic objects. In this paper, we propose a novel adaptive visual inertial odometry via interference quantization, namely IQ-VIO. To quantify the confidence of pose estimation through vision frames analysis, we firstly introduce the feature coverage and the dynamic scene interference index based on image information entropy. Then, based on the interference index, we further establish the IQ-VIO multi-sensor fusion model, which can adaptively adjust the measurement error covariance matrix of an extended Kalman filter to suppress and eliminate the impact of dynamic objects on localization. We verify IQ-VIO algorithm on KAIST Urban dataset and actual scenes. Results show that our method achieves favorable performance against other algorithms. Especially under challenging scenes such as low texture, the RPE of our algorithm decreases at least twenty percent. Our approach can effectively eliminate the impact of dynamic objects in the scenes and obtain higher positioning accuracy and robustness than conventional methods.
Similar content being viewed by others
Data availability
The authors make sure that all data and materials as well as software application or custom code support their published claims and comply with field standards.
References
Mur-Artal R, Tardós JD (2017) Orb-slam2: an open-source slam system for monocular, stereo, and rgb-d cameras. IEEE Trans Rob 33(5):1255–1262. https://doi.org/10.1109/TRO.2017.2705103
van Goor P, Mahony R (2021) An equivariant filter for visual inertial odometry. In: 2021 IEEE international conference on robotics and automation (ICRA). IEEE, pp 14432–14438. https://doi.org/10.1109/ICRA48506.2021.9561769
Shao X, Zhang L, Zhang T, Shen Y, Li H, Zhou Y (2020) A tightly-coupled semantic SLAM system with visual, inertial and surround-view sensors for autonomous indoor parking. In: Proceedings of the 28th ACM international conference on multimedia, pp 2691–2699. https://doi.org/10.1145/3394171.3413867
Song S, Lim H, Lee AJ, Myung H (2022) DynaVINS: a visual-inertial SLAM for dynamic environments. IEEE Robot Autom Lett 7(4):11523–11530. https://doi.org/10.1109/LRA.2022.3203231
Bescos B, Fácil JM, Civera J, Neira J (2018) DynaSLAM: tracking, mapping, and inpainting in dynamic scenes. IEEE Robot Autom Lett 3(4):4076–4083. https://doi.org/10.1109/LRA.2018.2860039
Zou D, Tan P (2012) Coslam: collaborative visual slam in dynamic environments. IEEE Trans Pattern Anal Mach Intell 35(2):354–366. https://doi.org/10.1109/TPAMI.2012.104
Su P, Luo S, Huang X (2022) Real-time dynamic SLAM algorithm based on deep learning. IEEE Access 10:87754–87766. https://doi.org/10.1109/ACCESS.2022.3199350
Hartley R, Zisserman A (2003) Multiple view geometry in computer vision, vol 30. Cambridge University Press, Cambridge, pp 1333–1341
Tan W, Liu H, Dong Z, Zhang G, Bao H (2013) Robust monocular SLAM in dynamic environments. In: 2013 IEEE international symposium on mixed and augmented reality (ISMAR), pp 209–218. https://doi.org/10.1109/ISMAR.2013.6671781
Alcantarilla PF, Yebes JJ, Almazán J, Bergasa LM (2012) On combining visual SLAM and dense scene flow to increase the robustness of localization and mapping in dynamic environments. In: 2012 IEEE international conference on robotics and automation, pp 1290–1297. https://doi.org/10.1109/ICRA.2012.6224690
Li S, Lee D (2017) RGB-D SLAM in dynamic environments using static point weighting. IEEE Robot Autom Lett 2(4):2263–2270. https://doi.org/10.1109/LRA.2017.2724759
Atashgah MAA, Malaek SMB (2011) A simulation environment for path and image generation in an aerial single-camera vision system. Proc Inst Mech Eng Part G J Aerosp Eng 225(5):541–558. https://doi.org/10.1177/0954410012450107
Atashgah MAA, Malaek SMB (2013) Prediction of aerial-image motion blurs due to the flying vehicle dynamics and camera characteristics in a virtual environment. Proc Inst Mech Eng Part G J Aerosp Eng 227(7):1055–1067. https://doi.org/10.1243/09544100JAERO813
Derome M, Plyer A, Sanfourche M, Besnerais GLJUS (2015) Moving object detection in real-time using stereo from a mobile platform. Unmanned Syst 3(04):253–266. https://doi.org/10.1142/S2301385015400026
Wang Y, Huang S (2014) Towards dense moving object segmentation based robust dense RGB-D SLAM in dynamic scenarios. In: 13th international conference on control automation robotics and vision (ICARCV), pp 1841–1846. https://doi.org/10.1109/ICARCV.2014.7064596
Kerl C, Sturm J, Cremers D (2013) Dense visual SLAM for RGB-D cameras. In: 2013 IEEE/RSJ international conference on intelligent robots and systems, pp 2100–2106. https://doi.org/10.1109/IROS.2013.6696650
Alcantarilla PF, Yebes JJ, Almazán J, Bergasa LM (2012) On combining visual SLAM and dense scene flow to increase the robustness of localization and mapping in dynamic environments. In: 2012 IEEE international conference on robotics and automation, pp 1290–1297. https://doi.org/10.1109/ICRA.2012.6224690
Yu C et al. (2018) DS-SLAM: a semantic visual SLAM towards dynamic environments. In: 2018 IEEE/RSJ international conference on intelligent robots and systems (IROS), pp 1168–1174. https://doi.org/10.1109/IROS.2018.8593691
Zhong F, Wang S, Zhang Z, Chen C, Wang Y (2018) Detect-SLAM: making object detection and SLAM mutually beneficial. In: 2018 IEEE winter conference on applications of computer vision (WACV), pp 1001–1010. https://doi.org/10.1109/WACV.2018.00115
Xiao L, Wang J, Qiu X, Rong Z, Zou XJR, Systems A (2019) Dynamic-SLAM: semantic monocular visual localization and mapping based on deep learning in dynamic environment. Robot Auton Syst 117:1–16. https://doi.org/10.1016/j.robot.2019.03.012
Hu Z, Zhao J, Luo Y, Ou J (2022) Semantic SLAM based on improved DeepLabv3\(^+\) in dynamic scenarios. IEEE Access 10:21160–21168. https://doi.org/10.1109/ACCESS.2022.3154086
Ballester I, Fontán A, Civera J, Strobl KH, Triebel R (2021) DOT: dynamic object tracking for visual SLAM. In: 2021 IEEE international conference on robotics and automation (ICRA). IEEE, pp 11705–11711, https://doi.org/10.1109/ICRA48506.2021.9561452
Yin Z, Shi J (2018) GeoNet: unsupervised learning of dense depth optical flow and camera pose. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1983–1992
Wang S, Clark R, Wen H, Trigoni N (2017) DeepVO: towards end-to-end visual odometry with deep recurrent convolutional neural networks. In: 2017 IEEE international conference on robotics and automation (ICRA), pp 2043–2050. https://doi.org/10.1109/ICRA.2017.7989236
Labbe M, Michaud F (2019) RTAB-Map as an open-source lidar and visual simultaneous localization and mapping library for large-scale and long-term online operation. J Field Robot 36(2):416–446. https://doi.org/10.1002/rob.21831
Qin T, Li P, Shen S (2018) VINS-mono: a robust and versatile monocular visual-inertial state estimator. IEEE Trans Rob 34(4):1004–1020. https://doi.org/10.1109/TRO.2018.2853729
Babu BPW, Cyganski D, Duckworth J, Kim S (2018) Detection and resolution of motion conflict in visual inertial odometry. In: 2018 IEEE international conference on robotics and automation (ICRA), pp 996–1002. https://doi.org/10.1109/ICRA.2018.8460870
Minoda K, Schilling F, Wüest V, Floreano D, Yairi T (2021) Viode: a simulated dataset to address the challenges of visual-inertial odometry in dynamic environments. IEEE Robot Autom Lett 6(2):1343–1350. https://doi.org/10.1109/LRA.2021.3058073
Wu J, Xiong J, Guo H (2022) Improving robustness of line features for VIO in dynamic scene. Meas Sci Technol 33(6):065204. https://doi.org/10.1088/1361-6501/ac547f
Wei H, Zhang T, Zhang L (2021) GMSK-SLAM: a new RGB-D SLAM method with dynamic areas detection towards dynamic environments. Multimed Tools Appl 80(21):31729–31751. https://doi.org/10.1007/s11042-021-11168-5
Huang C, Lin H, Lin H, Liu H, Gao Z, Huang L (2021) YO-VIO: robust multi-sensor semantic fusion localization in dynamic indoor environments. In: 2021 international conference on indoor positioning and indoor navigation (IPIN). IEEE, pp 1–6. https://doi.org/10.1109/IPIN51156.2021.9662614
Yao J, Zhang P, Wang Y, Luo Z, Ren X (2019) An adaptive uniform distribution ORB based on improved quadtree. IEEE Access 7:143471–143478. https://doi.org/10.1109/ACCESS.2019.2940995
Hero AO, Ma B, Michel OJ, Gorman J (2002) Applications of entropic spanning graphs. IEEE Signal Process Mag 19(5):85–95. https://doi.org/10.1109/MSP.2002.1028355
Hero AO, Ma B, Michel O, Gorman J (2001) Alpha-divergence for classification, indexing and retrieval. Communications and Signal Processing Laboratory (CSPL), Department of EECS, University of Michigan, Ann Arbor, Technical Report 328. http://www.eecs.umich.edu/ hero/detest.html
Bochkovskiy A, Wang CY, Liao HYM (2020) Yolov4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934
Shan T, Englot B, Meyers D, Wang W, Ratti C, Rus D (2020) Lio-sam: tightly-coupled lidar inertial odometry via smoothing and mapping. In: 2020 IEEE/RSJ international conference on intelligent robots and systems (IROS). IEEE, pp 5135–5142. https://doi.org/10.1109/IROS45743.2020.9341176
Jeong J, Cho Y, Shin YS, Roh H, Kim A (2018) Complex urban lidar data set. In: 2018 IEEE international conference on robotics and automation (ICRA). IEEE, pp 6344–6351. https://doi.org/10.1109/ICRA.2018.8460834
Funding
This work was supported by Department of science and technology of Guangdong Province (No:2021B01420003).
Author information
Authors and Affiliations
Contributions
All authors contributed to the study conception and design. Material preparation, data collection and analysis were performed by HZ, KL and JX. The first draft of the manuscript was written by HZ and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Conflict of interest
The authors have no relevant financial or non-financial interests to disclose.
Ethical statement and informed consent
Informed consent was obtained from all individual participants included in the study.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zhang, H., Ye, F., Lai, Y. et al. IQ-VIO: adaptive visual inertial odometry via interference quantization under dynamic environments. Intel Serv Robotics 16, 565–581 (2023). https://doi.org/10.1007/s11370-023-00478-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11370-023-00478-2