DEVO: Depth-Event Camera Visual Odometry in Challenging Conditions
This work addresses robust visual odometry for robotics or autonomous systems in difficult environments, representing an incremental improvement by adapting existing methods to a new sensor combination.
The authors tackled visual odometry in challenging conditions by developing a real-time framework using a stereo depth-event camera setup, achieving performance comparable to state-of-the-art RGB-D methods in regular conditions and outperforming them in high dynamics or low illumination.
We present a novel real-time visual odometry framework for a stereo setup of a depth and high-resolution event camera. Our framework balances accuracy and robustness against computational efficiency towards strong performance in challenging scenarios. We extend conventional edge-based semi-dense visual odometry towards time-surface maps obtained from event streams. Semi-dense depth maps are generated by warping the corresponding depth values of the extrinsically calibrated depth camera. The tracking module updates the camera pose through efficient, geometric semi-dense 3D-2D edge alignment. Our approach is validated on both public and self-collected datasets captured under various conditions. We show that the proposed method performs comparable to state-of-the-art RGB-D camera-based alternatives in regular conditions, and eventually outperforms in challenging conditions such as high dynamics or low illumination.