文章:Small-Object Detection in Remote Sensing Images with End-to-End Edge-Enhanced GAN and Object Detector Network 摘要 与大物体相比,遥感图像中的小物体检测性能并不理想,尤其是在低分辨率和嘈杂的图像中。一种基于生成对抗网络(GAN)的模型,称为增强超分辨率GAN(ESRGAN),具有出色的图像增强性能,但是重建的图...
近年来,基于深度学习的算法以其强大的特征表示能力在各种视觉识别任务的精度基准中占据了主导地位。得益于此以及一些公开可用的自然图像数据集,如Microsoft Common Objects in Context (MSCOCO)和PASCAL Visual Object Classes (VOC) ,许多基于深度学习的目标检测方法在自然场景图像中取得了巨大的成功。然而,尽管在自然图...
This paper proposes an efficient remote sensing image object detection model (MSA-YOLO) to improve detection performance. First, we propose a Multi-Scale Strip Convolution Attention Mechanism (MSCAM), which can reduce the introduction of background noise and fuse multi-scale features to...
受益于此以及一些公开的自然图像数据集,例如 Microsoft Common Objects in Context (MSCOCO)和 PASCAL Visual Object Classes (VOC),许多深度学习基于目标检测的方法在自然场景图像中取得了巨大成功。 然而,尽管在自然图像方面取得了巨大的成功,将基于深度学习的目标检测方法直接迁移到光学遥感图像是很困难的。众所周知,...
期刊名称:TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING(地球科学与遥感学报) 论文地址:doi.org/10.1109/TGRS.20 中科院分区: 2区 作者: Yin Zhang , Mu Ye , Guiyi Zhu , Yong Liu , Pengyu Guo , and Junhua Yan 单位: 南京航空航天大学 研究背景 为了解决遥感小目标检测任务中特征表示不足、背景混淆等...
SEMI-SUPERVISED OBJECT DETECTION FRAMEWORK WITH OBJECT FIRST MIXUPFOR REMOTE SENSING IMAGES 摘要 本文提出了一个用于遥感图像的简单半监督目标检测框架,该框架被命名为SSOD-RS。SSOD-RS包含两个部分,即改进的自我训练和基于强数据增强的一致性正则化,以及改进的混合。首先,作为一种增强算法,提出了Object First ...
Remote Sensing Image Object Detection Based on Improved YOLOv7 Algorithm Chapter © 2024 Data availability No new data were created during the study.References Jiao L, Zhang F, Liu F et al (2019) A survey of deep learning-based object detection. IEEE Access 7:128837–128868. https://doi...
Ge, Y., Ji, H. & Liu, X. Infrared remote sensing ship image object detection model based on YOLO In multiple environments.SIViP19, 85 (2025). https://doi.org/10.1007/s11760-024-03656-6 Download citation Received25 June 2024 Revised15 August 2024 ...
目标检测是计算机视觉中一项具有挑战性的任务。现在,许多检测网络在应用大型训练数据集时可以获得良好的检测结果。然而,为训练注释足够数量的数据往往很费时间。为了解决这个问题,本文提出了一种基于半监督学习的方法。 半监督学习用少量的注释数据和大量的未注释数据来训练检测网络。 在提出的方法中,生成对抗网络被用来从...
Object detection in optical remote sensing images, being a fundamental but challenging problem in the field of aerial and satellite image analysis, plays an important role for a wide range of applications and is receiving significant attention in recent years. While enormous methods exist, a deep ...