arXiv (Cornell University) · 2019 · 14 citations · 27 references
EngineeringComputer ScienceRobotics EngineeringComputer VisionMachine VisionRobot VisionRobotic VisionScene UnderstandingVisual OdometryVisual TrackingBenchmark DatasetsDeep Learning-based TrackingMonocular Visual OdometryRgb-d Visual Odometry
Most previous learning-based visual odometry (VO) methods take VO as a pure tracking problem. In contrast, we present a VO framework by incorporating two additional components called Memory and Refining. The Memory component preserves global information by employing an adaptive and efficient selection strategy. The Refining component ameliorates previous results with the contexts stored in the Memory by adopting a spatial-temporal attention mechanism for feature distilling. Experiments on the KITTI and TUM-RGBD benchmark datasets demonstrate that our method outperforms state-of-the-art learning-based methods by a large margin and produces competitive results against classic monocular VO approaches. Especially, our model achieves outstanding performance in challenging scenarios such as texture-less regions and abrupt motions, where classic VO algorithms tend to fail.
27
Sepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 98.1K citations
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2015 · 18.8K citations
Are we ready for autonomous driving? The KITTI vision benchmark suite
Andreas Geiger, P Lenz, R. Urtasun · 2012 · 14.4K citations
ORB: An efficient alternative to SIFT or SURF
Ethan Rublee, Vincent Rabaud, Kurt Konolige et al. · 2011 · 10.4K citations
Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
Xingjian Shi, Zhourong Chen, Hao Wang et al. · arXiv (Cornell University) · 2015 · 6.6K citations · Full text