Improving the Accuracy of Stereo Visual Odometry Using Visual Illumination Estimation
In the absence of reliable and accurate GPS, visual odometry (VO) has emerged as an effective means of estimating the egomotion of robotic vehicles. Like any dead-reckoning technique, VO suffers from unbounded accumulation of drift error over time, but this accumulation can be limited by incorporating absolute orientation information from, for example, a sun sensor. In this paper, we leverage recent work on visual outdoor illumination estimation to show that estimation error in a stereo VO pipeline can be reduced by inferring the sun position from the same image stream used to compute VO, thereby gaining the benefits of sun sensing without requiring a dedicated sun sensor or the sun to be visible to the camera. We compare sun estimation methods based on hand-crafted visual cues and Convolutional Neural Networks (CNNs) and demonstrate our approach on a combined 7.8 Km of urban driving from the popular KITTI dataset, achieving up to a 43 % reduction in translational average root mean squared error (ARMSE) and a 59 % reduction in final translational drift error compared to pure VO alone.
KeywordsVisual Odometry Illumination estimation Sun sensing Robot navigation
- 1.Agarwal, S., Mierle, K.: Ceres solver. http://ceres-solver.org
- 3.Eisenman, A.R., Liebe, C.C., Perez, R.: Sun sensing on the mars exploration rovers. In: Aerospace Conference Proceedings, vol. 5, pp. 5-2249–5-2262. IEEE (2002)Google Scholar
- 8.Geiger, A., Ziegler, J., Stiller, C.: StereoScan: dense 3D reconstruction in real-time. In: Proceedings of Intelligent Vehicles Symposium (IV), pp. 963–968. IEEE, June 2011Google Scholar
- 12.Ma, W.-C., Wang, S., Brubaker, M.A., Fidler, S., Urtasun, R.: Find your way by observing the sun and other semantic cues. 23 June 2016. arXiv:1606.07415