CUED Publications database

PoseNet: A convolutional network for real-time 6-dof camera relocalization

Kendall, A and Grimes, M and Cipolla, R (2015) PoseNet: A convolutional network for real-time 6-dof camera relocalization. In: UNSPECIFIED pp. 2938-2946..

Full text not available from this repository.


© 2015 IEEE. We present a robust and real-time monocular six degree of freedom relocalization system. Our system trains a convolutional neural network to regress the 6-DOF camera pose from a single RGB image in an end-to-end manner with no need of additional engineering or graph optimisation. The algorithm can operate indoors and outdoors in real time, taking 5ms per frame to compute. It obtains approximately 2m and 3 degrees accuracy for large scale outdoor scenes and 0.5m and 5 degrees accuracy indoors. This is achieved using an efficient 23 layer deep convnet, demonstrating that convnets can be used to solve complicated out of image plane regression problems. This was made possible by leveraging transfer learning from large scale classification data. We show that the PoseNet localizes from high level features and is robust to difficult lighting, motion blur and different camera intrinsics where point based SIFT registration fails. Furthermore we show how the pose feature that is produced generalizes to other scenes allowing us to regress pose with only a few dozen training examples.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Divisions: Div F > Machine Intelligence
Depositing User: Cron Job
Date Deposited: 17 Jul 2017 18:57
Last Modified: 21 Jun 2018 02:36