Machine learning techniques, namely convolutional neural networks (CNN) and regression forests, have recently shown great promise in performing 6-DoF localization of monocular images. However, in most cases image-sequences, rather only single images, are readily available. To this extent, none of the proposed learning-based approaches exploit the valuable constraint of temporal smoothness, often leading to situations where the per-frame error is larger than the camera motion. In this paper we propose a recurrent model for performing 6-DoF localization of video-clips. We find that, even by considering only short sequences (20 frames), the pose estimates are smoothed and the localization error can be drastically reduced. Finally, we consider means of obtaining probabilistic pose estimates from our model. We evaluate our method on openly-available real-world autonomous driving and indoor localization datasets.
|Title of host publication||2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)|
|Number of pages||9|
|Publication status||Published - 21 Jul 2017|
Clark, R., Wang, S., Markham, A., Trigoni, N., & Wen, H. (2017). VidLoc: A Deep Spatio-Temporal Model for 6-DoF Videoclip Relocalization. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 1-9). IEEE.