Multi-Scale PIIFD for Registration of Multi-Source Remote Sensing Images

This paper aims at providing multi-source remote sensing images registered in geometric space for image fusion.Focusing on the characteristics and differences of multi-source remote sensing images,a feature-based registration algorithm is implemented.The key technologies include image scale-space for implementing multi-scale properties,Harris corner detection for keypoints extraction,and partial intensity invariant feature descriptor(PIIFD)for keypoints description.Eventually,a multi-scale Harris-PIIFD image registration algorithm framework is proposed.The experimental results of fifteen sets of representative real data show that the algorithm has excellent,stable performance in multi-source remote sensing image registration,and can achieve accurate spatial alignment,which has strong practical application value and certain generalization ability.

Accuracy Analysis on the Automatic Registration of Multi-Source Remote Sensing Images Based on the Software of ERDAS Imagine

The automatic registration of multi-source remote sensing images (RSI) is a research hotspot of remote sensing image preprocessing currently. A special automatic image registration module named the Image Autosync has been embedded into the ERDAS IMAGINE software of version 9.0 and above. The registration accuracies of the module verified for the remote sensing images obtained from different platforms or their different spatial resolution. Four tested registration experiments are discussed in this article to analyze the accuracy differences based on the remote sensing data which have different spatial resolution. The impact factors inducing the differences of registration accuracy are also analyzed.

Multi-source Remote Sensing Image Registration Based on Contourlet Transform and Multiple Feature Fusion

Image registration is an indispensable component in multi-source remote sensing image processing. In this paper, we put forward a remote sensing image registration method by including an improved multi-scale and multi-direction Harris algorithm and a novel compound feature. Multi-scale circle Gaussian combined invariant moments and multi-direction gray level co-occurrence matrix are extracted as features for image matching. The proposed algorithm is evaluated on numerous multi-source remote sensor images with noise and illumination changes. Extensive experimental studies prove that our proposed method is capable of receiving stable and even distribution of key points as well as obtaining robust and accurate correspondence matches. It is a promising scheme in multi-source remote sensing image registration.

Generation of daily snow depth from multi-source satellite images and in situ observations

Snow depth （SD） is a key parameter for research into global climate changes and land surface processes. A method was developed to obtain daily SD images at a higher 4 km spatial resolution and higher precision with SD measurements from in situ observations and passive microwave remote sensing of Advanced Microwave Scanning Radiometer-EOS （AMSR-E） and snow cover measurements of the Interactive Multisensor Snow and Ice Mapping System （IMS）. AMSR-E SD at 25 km spatial resolution was retrieved from AMSR-E products of snow density and snow water equivalent and then corrected using the SD from in situ observations and IMS snow cover. Corrected AMSR-E SD images were then resampled to act as ＂virtual＂ in situ observations to combine with the real in situ observations to interpolate at 4 km spatial resolution SD using the Cressman method. Finally, daily SD data generation for several regions of China demonstrated that the method is well suited to the generation of higher spatial resolution SD data in regions with a lower Digital Elevation Model （DEM） but not so well suited to regions at high altitude and with an undulating terrain, such as the Tibetan Plateau. Analysis of the longer time period SD data generation for January between 2003 and 2010 in northern Xinjiang also demonstrated the feasibility of the method.

深度学习在遥感影像目标识别与定位中的应用研究

长期以来,遥感影像的目标识别与定位主要依靠目视判读和人工手段,误判和漏判情况严重,且检测精度较低。文章介绍了基于深度学习的目标检测算法,探讨了将深度学习应用于遥感影像目标识别与定位需要的关键技术,并对深度学习在目标识别与定位中的应用进行了前景展望。

应用型本科高校遥感数字图像处理课程教学探讨

在广东财经大学成为首批普通本科高校向应用型本科高校转变试点单位的新形势下,本文针对面向自然地理与资源环境本科生的专业课程"遥感数字图像处理",分析教学现状中存在的问题,探索性地提出以培养应用型人才为导向的课程内容设计和课程教学方法,旨在提高课程教学质量,促进学生遥感应用能力的培养。

多源遥感影像配准中的SIFT特征匹配改进

针对尺度不变特征变换算法应用于多源遥感影像配准时面临的低效率和误匹配问题,从特征点提取和特征点匹配两个方面对其进行改进。在特征点提取阶段,通过控制特征点数量和分布情况获取均匀分布的特征点;在特征点匹配阶段,采用特征点仿射变换粗匹配、精匹配和误匹配点剔除策略,由粗到精地获取准确的同名点。对多源遥感影像进行配准实验,结果表明,此方法在匹配效率及匹配性能上均优于原始SIFT算法,且配准精度更高。