基于三维GMRF的高光谱图像空天融合目标检测

Hyperspectral target detection by airborne and spaceborne image fusion based on 3D GMRF

  • 摘要: 针对传统高光谱目标检测技术仅依靠单一的航空或航天高光谱图像进行目标检测,未能综合利用航空和航天遥感成像各自优势的问题,结合三维高斯马尔科夫随机场(GMRF)模型和D-S证据理论提出了一种空天融合目标检测方法。利用三维GMRF算法分别对航空航天遥感图像进行目标检测,再将检测结果进行决策级D-S证据理论融合,实现空天融合目标检测。实验结果表明,该目标检测技术实现了空天高光谱图像的优势互补,提升了目标检测精度,是一种融合处理空天高光谱遥感图像的目标检测新方法。

     

    Abstract: To solve the problem that traditional hyperspectral target detection is based on either airborne image or spaceborne image, and doesn't utilize the advantage of aerial and space imaging comprehensively, a target detection method for airborne and spaceborne image fusion, which combined 3D GMRF with D-S evidence theory, was proposed in this paper. The 3D GMRF detection results from airborne image and spaceborne image were fused by D-S evidence theory in decision level. The experimental results show that the proposed target detection method complements the advantage of aerial hyperspectral image and space hyperspectral image, and enhances accuracy on target detection. This technology is new target detection method by fusing the aerial and space hyperspectral image.

     

/

返回文章
返回