EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Learning geometric Jensen-Shannon divergence for tiny object detection in remote sensing images

Shuyan Ni, Cunbao Lin, Haining Wang, Yang Li, Yurong Liao, Na Li

Frontiers in Neurorobotics · 09.11.2023 · 17

DOI: 10.3389/fnbot.2023.1273251 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Neurorobotics, online erschienen am 09.11.2023. Verfasst von Shuyan Ni und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electronic and Optical Engineering, Space Engineering University, Beijing, China. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Tiny objects in remote sensing images only have a few pixels, and the detection difficulty is much higher than that of regular objects. General object detectors lack effective extraction of tiny object features, and are sensitive to the Intersection-over-Union (IoU) calculation and the threshold setting in the prediction stage. Therefore, it is particularly important to design a tiny-object-specific detector that can avoid the above problems. This article proposes the network JSDNet by learning the geometric Jensen-Shannon (JS) divergence representation between Gaussian distributions. First, the Swin Transformer model is integrated into the feature extraction stage as the backbone to improve the feature extraction capability of JSDNet for tiny objects. Second, the anchor box and ground-truth are modeled as two two-dimensional (2D) Gaussian distributions, so that the tiny object is represented as a statistical distribution model. Then, in view of the sensitivity problem faced by the IoU calculation for tiny objects, the JSDM module is designed as a regression sub-network, and the geometric JS divergence between two Gaussian distributions is derived from the perspective of information geometry to guide the regression prediction of anchor boxes. Experiments on the AI-TOD and DOTA datasets show that JSDNet can achieve superior detection performance for tiny objects compared to state-of-the-art general object detectors.

Schlagwörter

Stichwörter der Autor:innen

Gaussian distributionJensen-Shannon divergencedeep learningremote sensing imagestiny object detection

Autor:innen und Institutionen

  • Department of Electronic and Optical Engineering, Space Engineering University, Beijing, China.
  • Institute of Artificial Intelligence, Beihang University, Beijing, China.
  • Aerospace Optical-Microwave Integrated Precision Intelligent Sensing, Key Laboratory of Ministry of Industry and Information Technology, Beihang University, Beijing, China.

Zitieren

APA

Ni, S., Lin, C., Wang, H., Li, Y., Liao, Y., & Li, N. (2023). Learning geometric Jensen-Shannon divergence for tiny object detection in remote sensing images. Frontiers in Neurorobotics, 17. https://doi.org/10.3389/fnbot.2023.1273251

Vancouver

Ni S, Lin C, Wang H, Li Y, Liao Y, Li N. Learning geometric Jensen-Shannon divergence for tiny object detection in remote sensing images. Frontiers in Neurorobotics. 2023;17. doi:10.3389/fnbot.2023.1273251

BibTeX
@article{Ni2023,
  author = {Ni, Shuyan and Lin, Cunbao and Wang, Haining and Li, Yang and Liao, Yurong and Li, Na},
  title = {Learning geometric Jensen-Shannon divergence for tiny object detection in remote sensing images},
  journal = {Frontiers in Neurorobotics},
  year = {2023},
  volume = {17},
  doi = {10.3389/fnbot.2023.1273251}
}
Kostenlos starten →