DA4AD: End-to-End Deep Attention-based Visual Localization for Autonomous Driving
This work addresses the need for robust, low-cost localization in autonomous driving, though it appears incremental by improving upon existing feature-based methods with deep learning enhancements.
The paper tackles visual localization for autonomous driving by introducing a deep attention-based framework that achieves centimeter-level accuracy, demonstrating competitive performance against LiDAR-based solutions in challenging scenarios.
We present a visual localization framework based on novel deep attention aware features for autonomous driving that achieves centimeter level localization accuracy. Conventional approaches to the visual localization problem rely on handcrafted features or human-made objects on the road. They are known to be either prone to unstable matching caused by severe appearance or lighting changes, or too scarce to deliver constant and robust localization results in challenging scenarios. In this work, we seek to exploit the deep attention mechanism to search for salient, distinctive and stable features that are good for long-term matching in the scene through a novel end-to-end deep neural network. Furthermore, our learned feature descriptors are demonstrated to be competent to establish robust matches and therefore successfully estimate the optimal camera poses with high precision. We comprehensively validate the effectiveness of our method using a freshly collected dataset with high-quality ground truth trajectories and hardware synchronization between sensors. Results demonstrate that our method achieves a competitive localization accuracy when compared to the LiDAR-based localization solutions under various challenging circumstances, leading to a potential low-cost localization solution for autonomous driving.