EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

RGB-D-Based Stair Detection and Estimation Using Deep Learning

Chen Wang iD, Zhongcai Pei iD, Shuang Qiu iD, Zhiyong Tang iD

Sensors · 15.02.2023 · 23 (4) · 2175

DOI: 10.3390/s23042175 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 15.02.2023. Verfasst von Chen Wang und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Automation Science and Electrical Engineering, Beihang University, Beijing 100191, China. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Stairs are common vertical traffic structures in buildings, and stair detection tasks are important in environmental perception for autonomous mobile robots. Most existing algorithms have difficulty combining the visual information from binocular sensors effectively and ensuring reliable detection at night and in the case of extremely fuzzy visual clues. To solve these problems, we propose a stair detection network with red-green-blue (RGB) and depth inputs. Specifically, we design a selective module, which can make the network learn the complementary relationship between the RGB feature maps and the depth feature maps and fuse the features effectively in different scenes. In addition, we propose several postprocessing algorithms, including a stair line clustering algorithm and a coordinate transformation algorithm, to obtain the stair geometric parameters. Experiments show that our method has better performance than existing the state-of-the-art deep learning method, and the accuracy, recall, and runtime are improved by 5.64%, 7.97%, and 3.81 ms, respectively. The improved indexes show the effectiveness of the multimodal inputs and the selective module. The estimation values of stair geometric parameters have root mean square errors within 15 mm when ascending stairs and 25 mm when descending stairs. Our method also has extremely fast detection speed, which can meet the requirements of most real-time applications.

Schlagwörter

Stichwörter der Autor:innen

RGB-Ddeep learningmultimodalitystair detectionstair geometric parameter estimation

Autor:innen und Institutionen

  • School of Automation Science and Electrical Engineering, Beihang University, Beijing 100191, China.

ORCID-Profile: Chen Wang, Zhongcai Pei, Shuang Qiu, Zhiyong Tang

Zitieren

APA

Wang, C., Pei, Z., Qiu, S., & Tang, Z. (2023). RGB-D-Based Stair Detection and Estimation Using Deep Learning. Sensors, 23(4), 2175. https://doi.org/10.3390/s23042175

Vancouver

Wang C, Pei Z, Qiu S, Tang Z. RGB-D-Based Stair Detection and Estimation Using Deep Learning. Sensors. 2023;23(4):2175. doi:10.3390/s23042175

BibTeX
@article{Wang2023,
  author = {Wang, Chen and Pei, Zhongcai and Qiu, Shuang and Tang, Zhiyong},
  title = {RGB-D-Based Stair Detection and Estimation Using Deep Learning},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {4},
  pages = {2175},
  doi = {10.3390/s23042175}
}
Kostenlos starten →