딥러닝 기반 영상 주행기록계와 단안 깊이 추정 및 기술을 위한 벤치마크
Benchmark for Deep Learning based Visual Odometry and Monocular Depth Estimation
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This paper presents a new benchmark system for visual odometry (VO) and monocular depth estimation (MDE). As deep learning has become a key technology in computer vision, many researchers are trying to apply deep learning to VO and MDE. Just a couple of years ago, they were independently studied in a supervised way, but now they are coupled and trained together in an unsupervised way. However, before designing fancy models and losses, we have to customize datasets to use them for training and testing. After training, the model has to be compared with the existing models, which is also a huge burden. The benchmark provides input dataset ready-to-use for VO and MDE research in ‘tfrecords’ format and output dataset that includes model checkpoints and inference results of the existing models. It also provides various tools for data formatting, training, and evaluation. In the experiments, the exsiting models were evaluated to verify their performances presented in the corresponding papers and we found that the evaluation result is inferior to the presented performances.
Abstract
This paper presents a new benchmark system for visual odometry (VO) and monocular depth estimation (MDE). As deep learning has become a key technology in computer vision, many researchers are trying to apply deep learning to VO and MDE. Just a couple of years ago, they were independently studied in a supervised way, but now they are coupled and trained together in an unsupervised way. However, before designing fancy models and losses, we have to customize datasets to use them for training and testing. After training, the model has to be compared with the existing models, which is also a huge burden. The benchmark provides input dataset ready-to-use for VO and MDE research in ‘tfrecords’ format and output dataset that includes model checkpoints and inference results of the existing models. It also provides various tools for data formatting, training, and evaluation. In the experiments, the exsiting models were evaluated to verify their performances presented in the corresponding papers and we found that the evaluation result is inferior to the presented performances.
참고문헌 (19)
- L. Deng, "Deep Learning : Methods and Applications", Now Foundations and Trends, 7(3), pp.197~387 (2014)
- Y. LeCun, "Deep learning", Nature, 521, pp.436~444 (2015)
- S. Wang, "Deepvo: Towards end-to-end visual odometry with deep recurrent convolutional neural networks", 2017 IEEE International Conference on Robotics and Automation (ICRA), pp.2043~2050 (2017)
- R. Li, "EE International Conference on Robotics and Automation(ICRA), Brisbane, QLD, Australia, pp", 2018IEEE International Conference on Robotics and Automation (ICRA), pp.7286~7291 (2018)
- T. Zhou, "Unsupervised learning of depth and ego-motion from video", 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
- H. Zhan, "Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction", 2018 IEEE, 2018, 340~349
- Z. Yin, "GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose", 2018 IEEE, 2018, ~
- J. Fuentes-Pacheco, "Visual simultaneous localization and mapping: a survey", Artificial Intelligence Review, 43(1), pp.55~81 (2015)
- T. Taketomi, "Visual SLAM algorithms: a survey from 2010 to 2016", IPSJ Transactions on Computer Vision and Applications, 9(16) (2017)[DOI]
- R. Mur-Artal, "ORBSLAM : a versatile and accurate monocular SLAM system", IEEE Transactions on Robotics, 31(5), pp.1147~1163 (2015)
- J. Engel, "LSD-SLAM: Largescale direct monocular SLAM", European Conference on Computer Vision, pp.834~849 (2014)
- R. Mahjourian, "Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraints", 2018 IEEE, 2018, 5667~5675
- A. Saxena, "Learning depth from single monocular images", 18th International Conference on Neural Information Processing Systems, pp.1161~1168 (2005)
- A. Geiger, "Vision meets robotics: The KITTI dataset", The International Journal of Robotics Research, 32(11), pp.1231~1237 (2013)
- D. Eigen, "Depth map prediction from a single image using a multi-scale deep network", ~ (2014)
- R. Mur-Artal, "Orb-slam2: An open-source slam system for monocular, stereo, and rgb-d cameras", IEEE Transactions on Robotics, 33(5), pp.1255~1262 (2017)
- J. Engel, "Direct sparse odometry", ~ (2016)
- J. Engel, "Large-scale direct SLAM with stereo cameras", 2015 IEEE, 2015, 1935~1942
- J. Sturm, "A benchmark for the evaluation of RGB-D SLAM systems", 2012 IEEE, 2012, 573~580