Unsupervised Learning of Depth and Camera Pose with Feature Map Warping
Estimating the depth of image and egomotion of agent are important for autonomous and robot in understanding the surrounding environment and avoiding collision. Most existing unsupervised methods estimate depth and camera egomotion by minimizing photometric error between adjacent frames. However, th...
Main Authors: | Ente Guo, Zhifeng Chen, Yanlin Zhou, Dapeng Oliver Wu |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-01-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/3/923 |
Similar Items
-
Occlusion-Aware Unsupervised Learning of Monocular Depth, Optical Flow and Camera Pose with Geometric Constraints
by: Qianru Teng, et al.
Published: (2018-09-01) -
Unsupervised Monocular Training Method for Depth Estimation Using Statistical Masks
by: Xiangtong Wang, et al.
Published: (2020-01-01) -
Predicting Depth from Single RGB Images with Pyramidal Three-Streamed Networks
by: Songnan Chen, et al.
Published: (2019-02-01) -
Depth from a Motion Algorithm and a Hardware Architecture for Smart Cameras
by: Abiel Aguilar-González, et al.
Published: (2018-12-01) -
Reduced egomotion estimation drift using omnidirectional views
by: Yalin Bastanlar
Published: (2014-09-01)