EUVIMEDEUVIMED entdecken
Crossref

SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothing

Xue Yang, Junchi Yan, Wenlong Liao, Xiaokang Yang, Jin Tang, Tao He

IEEE Transactions on Pattern Analysis and Machine Intelligence · 01.02.2023 · 45 (2) · 2384-2399

DOI: 10.1109/tpami.2022.3166956 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, erschienen am 01.02.2023. Verfasst von Xue Yang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 325-mal zitiert (Crossref) und nennt 83 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Shanghai Municipal Science and Technology Major Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Small and cluttered objects are common in real-world which are challenging for detection. The difficulty is further pronounced when the objects are rotated, as traditional detectors often routinely locate the objects in horizontal bounding box such that the region of interest is contaminated with background or nearby interleaved objects. In this paper, we first innovatively introduce the idea of denoising to object detection. Instance-level denoising on the feature map is performed to enhance the detection to small and cluttered objects. To handle the rotation variation, we also add a novel IoU constant factor to the smooth L1 loss to address the long standing boundary problem, which to our analysis, is mainly caused by the periodicity of angular (PoA) and exchangeability of edges (EoE). By combing these two features, our proposed detector is termed as SCRDet++. Extensive experiments are performed on large aerial images public datasets DOTA, DIOR, UCAS-AOD as well as natural image dataset COCO, scene text dataset ICDAR2015, small traffic light dataset BSTLD and our released S 2 TLD by this paper. The results show the effectiveness of our approach. The released dataset S 2 TLD is made public available, which contains 5,786 images with 14,130 traffic light instances across five categories.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Shanghai Municipal Science and Technology Major Project
  • Chengdu Municipal Science and Technology Project
  • Wu Wen Jun Honorary Doctoral Scholarship
  • AI Institute
  • Shanghai Jiao Tong University

Zitieren

APA

Yang, X., Yan, J., Liao, W., Yang, X., Tang, J., & He, T. (2023). SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothing. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(2), 2384-2399. https://doi.org/10.1109/tpami.2022.3166956

Vancouver

Yang X, Yan J, Liao W, Yang X, Tang J, He T. SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothing. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2023;45(2):2384-2399. doi:10.1109/tpami.2022.3166956

BibTeX
@article{Yang2023,
  author = {Yang, Xue and Yan, Junchi and Liao, Wenlong and Yang, Xiaokang and Tang, Jin and He, Tao},
  title = {SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothing},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2023},
  volume = {45},
  number = {2},
  pages = {2384--2399},
  doi = {10.1109/tpami.2022.3166956}
}
Kostenlos starten →