EUVIMEDEUVIMED entdecken
Crossref

RGB-T Semantic Segmentation With Location, Activation, and Sharpening

Gongyang Li, Yike Wang, Zhi Liu, Xinpeng Zhang, Dan Zeng

IEEE Transactions on Circuits and Systems for Video Technology · 2023-03 · 33 (3) · 1223-1235

DOI: 10.1109/tcsvt.2022.3208833 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2023-03. Verfasst von Gongyang Li und 4 weiteren Autor:innen. Die Arbeit wurde bisher 195-mal zitiert (Crossref) und nennt 68 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Science and Technology Commission of Shanghai Municipality.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Semantic segmentation is important for scene understanding. To address the scenes of adverse illumination conditions of natural images, thermal infrared (TIR) images are introduced. Most existing RGB-T semantic segmentation methods follow three cross-modal fusion paradigms, i. e., encoder fusion, decoder fusion, and feature fusion. Some methods, unfortunately, ignore the properties of RGB and TIR features or the properties of features at different levels. In this paper, we propose a novel feature fusion-based network for RGB-T semantic segmentation, named LASNet, which follows three steps of location, activation, and sharpening. The highlight of LASNet is that we fully consider the characteristics of cross-modal features at different levels, and accordingly propose three specific modules for better segmentation. Concretely, we propose a Collaborative Location Module (CLM) for high-level semantic features, aiming to locate all potential objects. We propose a Complementary Activation Module for middle-level features, aiming to activate exact regions of different objects. We propose an Edge Sharpening Module (ESM) for low-level texture features, aiming to sharpen the edges of objects. Furthermore, in the training phase, we attach a location supervision and an edge supervision after CLM and ESM, respectively, and impose two semantic supervisions in the decoder part to facilitate network convergence. Experimental results on two public datasets demonstrate that the superiority of our LASNet over relevant state-of-the-art methods. The code and results of our method are available at https://github.com/MathLee/LASNet.

Förderung

  • National Natural Science Foundation of China
  • Science and Technology Commission of Shanghai Municipality

Zitieren

APA

Li, G., Wang, Y., Liu, Z., Zhang, X., & Zeng, D. (2023). RGB-T Semantic Segmentation With Location, Activation, and Sharpening. IEEE Transactions on Circuits and Systems for Video Technology, 33(3), 1223-1235. https://doi.org/10.1109/tcsvt.2022.3208833

Vancouver

Li G, Wang Y, Liu Z, Zhang X, Zeng D. RGB-T Semantic Segmentation With Location, Activation, and Sharpening. IEEE Transactions on Circuits and Systems for Video Technology. 2023;33(3):1223-1235. doi:10.1109/tcsvt.2022.3208833

BibTeX
@article{Li2023,
  author = {Li, Gongyang and Wang, Yike and Liu, Zhi and Zhang, Xinpeng and Zeng, Dan},
  title = {RGB-T Semantic Segmentation With Location, Activation, and Sharpening},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2023},
  volume = {33},
  number = {3},
  pages = {1223--1235},
  doi = {10.1109/tcsvt.2022.3208833}
}
Kostenlos starten →