We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
RatioNet: Ratio Prediction Network for Object Detection.
- Authors
Zhao, Kuan; Zhao, Boxuan; Wu, Lifang; Jian, Meng; Liu, Xu; Hussain, Zahir M.
- Abstract
In object detection of remote sensing images, anchor-free detectors often suffer from false boxes and sample imbalance, due to the use of single oriented features and the key point-based boxing strategy. This paper presents a simple and effective anchor-free approach-RatioNet with less parameters and higher accuracy for sensing images, which assigns all points in ground-truth boxes as positive samples to alleviate the problem of sample imbalance. In dealing with false boxes from single oriented features, global features of objects is investigated to build a novel regression to predict boxes by predicting width and height of objects and corresponding ratios of l_ratio and t_ratio, which reflect the location of objects. Besides, we introduce ratio-center to assign different weights to pixels, which successfully preserves high-quality boxes and effectively facilitates the performance. On the MS-COCO test–dev set, the proposed RatioNet achieves 49.7% AP.
- Subjects
REMOTE sensing; MULTISPECTRAL imaging; FORECASTING
- Publication
Sensors (14248220), 2021, Vol 21, Issue 5, p1672
- ISSN
1424-8220
- Publication type
Article
- DOI
10.3390/s21051672