A method for detecting objects in dense scenes
Abstract: Recent object detectors have achieved excellent performance in accuracy and speed. Even with such impressive results, the most advanced detectors are challenging in dense scenes. In this article, we analyze and find the reasons for the decrease in detection accuracy in dense scenes. We started our work in terms of region proposal and location loss. We found that low-quality proposal regions during the training process are the main factors affecting detection accuracy. To prove our research, we established and trained a dense detection model based on Cascade R-CNN. The model achieves an accuracy of mAP 0.413 on the SKU-110K sub-dataset. Our results show that improving the quality of recommended regions can effectively improve the detection accuracy in dense scenes.
- Location
-
Deutsche Nationalbibliothek Frankfurt am Main
- Extent
-
Online-Ressource
- Language
-
Englisch
- Bibliographic citation
-
A method for detecting objects in dense scenes ; volume:12 ; number:1 ; year:2022 ; pages:75-82 ; extent:8
Open computer science ; 12, Heft 1 (2022), 75-82 (gesamt 8)
- Creator
-
Xu, Chuanyun
Zheng, Yu
Zhang, Yang
Li, Gang
Wang, Ying
- DOI
-
10.1515/comp-2022-0231
- URN
-
urn:nbn:de:101:1-2022072714041719405168
- Rights
-
Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
- Last update
-
15.08.2025, 7:34 AM CEST
Data provider
Deutsche Nationalbibliothek. If you have any questions about the object, please contact the data provider.
Associated
- Xu, Chuanyun
- Zheng, Yu
- Zhang, Yang
- Li, Gang
- Wang, Ying