Achieving RGB-D Level Segmentation Performance from a Single ToF Camera
Sharma P, Katrolia JS, Rambach J, Mirbach B, Stricker D (2024)
Publication Type: Conference contribution
Publication year: 2024
Publisher: Science and Technology Publications, Lda
Book Volume: 1
Pages Range: 171-178
Conference Proceedings Title: International Conference on Pattern Recognition Applications and Methods
Event location: Rome, ITA
ISBN: 9789897586842
Abstract
Depth is a very important modality in computer vision, typically used as complementary information to RGB, provided by RGB-D cameras. In this work, we show that it is possible to obtain the same level of accuracy as RGB-D cameras on a semantic segmentation task using infrared (IR) and depth images from a single Timeof-Flight (ToF) camera. In order to fuse the IR and depth modalities of the ToF camera, we introduce a method utilizing depth-specific convolutions in a multi-task learning framework. In our evaluation on an incar segmentation dataset, we demonstrate the competitiveness of our method against the more costly RGB-D approaches.
Authors with CRIS profile
Involved external institutions
Germany (DE)How to cite
APA:
Sharma, P., Katrolia, J.S., Rambach, J., Mirbach, B., & Stricker, D. (2024). Achieving RGB-D Level Segmentation Performance from a Single ToF Camera. In Modesto Castrillon-Santana, Maria De Marsico, Ana Fred (Eds.), International Conference on Pattern Recognition Applications and Methods (pp. 171-178). Rome, ITA: Science and Technology Publications, Lda.
MLA:
Sharma, Pranav, et al. "Achieving RGB-D Level Segmentation Performance from a Single ToF Camera." Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2024, Rome, ITA Ed. Modesto Castrillon-Santana, Maria De Marsico, Ana Fred, Science and Technology Publications, Lda, 2024. 171-178.
BibTeX: Download