Pop-up SLAM: Semantic monocular plane SLAM for low-texture environments

By Shichao Yang, Yu Song, Michael Kaess, Sebastian A. Scherer. 2016

143 citations recorded by the source corpus.

Existing simultaneous localization and mapping (SLAM) algorithms are not robust in challenging low-texture environments because there are only few salient features. The resulting sparse or semi-dense map also conveys little information for motion planning. Though some work utilize plane or scene layout for dense map regularization, they require decent state estimation from other sources. In this paper, we propose real-time monocular plane SLAM to demonstrate that scene understanding could improve both state estimation and dense mapping especially in low-texture environments. The plane measurements come from a pop-up 3D plane model applied to each single image. We also combine planes with point based SLAM to improve robustness. On a public TUM dataset, our algorithm generates a dense semantic 3D model with pixel depth error of 6.2 cm while existing SLAM algorithms fail. On a 60 m long dataset with loops, our method creates a much better 3D model with state estimation error of 0.67%.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Geology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

1. Baofu Wu
2. Sidi Lu
3. Ren Zhong
4. Qingyan Zhang
5. Yongtao Yao
6. Weisong Shi
7. Lei Tai
8. Liangkai Liu

In Computer Vision and Pattern Recognition

1. Baofu Wu
2. Sidi Lu
3. Ren Zhong
4. Qingyan Zhang
5. Yongtao Yao
6. Weisong Shi
7. Lei Tai
8. Liangkai Liu

In Geology

1. Lei Tai

Citations in the corpus

• Deep-learning in Mobile Robotics - from Perception to Control Systems: A Survey on Why and Why not (2016, methodology): “Based on the success of Fully Convolutional Networks ( FCN ) (Long et al., 2015) on semantics segmentation, Yang et al. (2016a) built a CNN model to extract the ground and wall planes from a single image.”
• Computing Systems for Autonomous Driving: State of the Art and Challenges (2020, methodology): “Besides the above methods, deep learning methods are also utilized in solving feature extraction [130], motion estimation [131], and”