遥感
计算机科学
目标检测
比例(比率)
人工智能
计算机视觉
Boosting(机器学习)
特征提取
特征(语言学)
传感器融合
融合
图像融合
适应性
保险丝(电气)
代表(政治)
对象(语法)
水准点(测量)
遥感应用
融合机制
频道(广播)
模式识别(心理学)
变压器
编码(集合论)
时频分析
稳健性(进化)
作者
Yuanjie Zhi,Gang Zhao,Chao Song,Mingyang Ma,Shaohui Mei
标识
DOI:10.1109/tgrs.2025.3618293
摘要
Deep learning-based object detection algorithms have achieved significant success in the field of computer vision. However, the wide range of target sizes in remote sensing images poses a challenge for single algorithms to detect objects of varying sizes effectively. To address this issue, this paper proposes an end-to-end object detection algorithm for remote sensing images based on Scale Adaptive and Frequency Fusion DETR (SAFF-DETR), which designs a frequency feature enhancement and fusion mechanism to handle targets of varying sizes within a single framework. First, in order to improve the Transformer-based detectors’ ability to small targets, a multibranch representation fusion (MRF) module is proposed to fuse shallow layer frequency representations, boosting the network’s ability to perceive small targets. Furthermore, Cross-layer Spatial and Channel Frequency Attention (CSFA and CCFA) is designed to enable efficient frequency feature interaction across multi-scale features, enhancing the representation capability for targets of different sizes. Moreover, by integrating the two aforementioned attention mechanisms, the Cross-layer Channel-Spatial-wise Frequency Fusion (CCSFF) structure is introduced to realize global feature interactions in one step without repetitive up and down-sampling operations, by which patch division-based Transformer architecture is designed to enhance scale adaptability for object detection. Experimental results over several benchmark datasets demonstrate that the proposed SAFF-DETR can handle extremely varying-size targets and outperforms several SOTA algorithms. The source code will be available at https://github.com/Jianglin-Zhao/SAFF-DETR.
科研通智能强力驱动
Strongly Powered by AbleSci AI