Semantic SuperPoint: A Deep Semantic Descriptor

Several SLAM methods benefit from the use of semantic information. Most integrate photometric methods with high-level semantics such as object detection and semantic segmentation. We propose that adding a semantic segmentation decoder in a shared encoder architecture would help the descriptor decode...

Full description

Saved in:
Bibliographic Details
Published in2022 Latin American Robotics Symposium (LARS), 2022 Brazilian Symposium on Robotics (SBR), and 2022 Workshop on Robotics in Education (WRE) pp. 294 - 299
Main Authors Gama, Gabriel Soares, Dos Santos Rosa, Nicolas, Grassi, Valdir
Format Conference Proceeding
LanguageEnglish
Published IEEE 18.10.2022
Subjects
Computer Vision
Feature extraction
Measurement
Multitasking
Object detection
Semantic segmentation
Semantics
Simultaneous localization and mapping
Visual Odometry
Online AccessGet full text

Cover

More Information
Summary:Several SLAM methods benefit from the use of semantic information. Most integrate photometric methods with high-level semantics such as object detection and semantic segmentation. We propose that adding a semantic segmentation decoder in a shared encoder architecture would help the descriptor decoder learn semantic information, improving the feature extractor. This would be a more robust approach than only using high-level semantic information since it would be intrinsically learned in the descriptor and would not depend on the final quality of the semantic prediction. To add this information, we take advantage of multi-task learning methods to improve accuracy and balance the performance of each task. The proposed models are evaluated according to detection and matching metrics on the HPatches dataset. The results show that the Semantic SuperPoint model performs better than the baseline one.
ISSN:2643-685X
DOI:10.1109/LARS/SBR/WRE56824.2022.9996027