.png){kind=icon}
.png){kind=icon}
Return
A Triple Dynamic Optimization-Based Multiscale Object Detection Network
.png){kind=icon}
OA
AI
DOI：10.1109/JSTARS.2025.3610623.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The object detection in high-resolution remote sensing images is affected by the uniqueness of imaging perspectives and the complexity of detection targets. Existing models face core challenges such as feature degradation of small objects, extreme scale variations, and intricate, dynamic backgrounds. To address these issues, this article proposes a triple dynamic optimization framework for remote sensing target detection (TDO-YOLO). First, construct the deformable reparameterized feature module, which utilizes multibranch feature fusion and structural reparameterization techniques to achieve refined capture of tiny and multiscale targets. Second, we design an adaptive receptive field fusion (ARFF) module that overcomes fixed receptive field limitations in traditional convolutions through parallel multiscale kernel extraction and geometry-aware feature reorganization, significantly improving multiscale object detection accuracy. Third, we propose a convolutional dynamic position-encoding residual attention mechanism, leveraging long-range dependency modeling and background suppression to effectively mitigate complex background interference and reduce false detection rates. Finally, we introduce a multiscale-aware IoU loss function specifically designed for remote sensing images, incorporating multiscale perception mechanisms and dynamic weighting to enhance detection precision. Experimental results on the RSOD and DIOR datasets demonstrate that TDO-YOLO achieves mAP$_{50}$ scores of 96.6% and 68.7%, representing improvements of 3.87% and 3.15%, respectively, over the baseline model YOLOv11. Compared to current state-of-the-art networks, TDO-YOLO exhibits superior detection accuracy.
Keywords:
Multiscale object
object detection
remote sensing image
YOLO network
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
5.3
Papers:
1.3K
Citations:
3.0W
Organization
View more organizations