- Advanced Image Fusion Techniques
- Urban Heat Island Mitigation
- Remote Sensing in Agriculture
- Calibration and Measurement Techniques
- Image and Signal Denoising Methods
- Advanced Image Processing Techniques
- Land Use and Ecosystem Services
- Advanced SAR Imaging Techniques
- Underwater Acoustics Research
- Building Energy and Comfort Optimization
- Generative Adversarial Networks and Image Synthesis
- Remote-Sensing Image Classification
- Synthetic Aperture Radar (SAR) Applications and Techniques
- Remote Sensing and LiDAR Applications
- Infrared Target Detection Methodologies
Xiamen University
2018-2020
Compact polarimetric synthetic aperture radar (CP SAR), as a new technique or observation system, has attracted much attention in recent years. Compared with quad-polarization SAR (QP CP provides an wider swath, while, compared linear dual-polarization SAR, retains more polarization information observations. These characteristics make useful tool marine environmental applications. Previous studies showed the potential of images for ship detection. However, false alarms, caused by ocean...
Landsat 4-5, built at the same time and with design, carrying Multispectral Scanner System (MSS) Thematic Mapper (TM) simultaneously, jointly provided observation service for about 30 years (1982–2013). Considering importance of data continuity series analyses, investigations on 4-5 MSS TM are required. In this paper, characterization differences between were initially discussed using synthesized reflectance records generated from a collection Hyperion hyperspectral profiles which well...
Because of impacts resulted from sensor malfunction and clouds, there is usually a great deal missing regions (pixels) in remotely sensed imagery. To make full use the imagery affected, different algorithms for remote sensing images inpainting have been proposed. In this paper, an unsupervised convolutional neural network (CNN) context generate model was modified to recover affected (or un-recorded) pixels single image without auxiliary information. Unlike existing nonparametric which...
The Landsat 1-5 multispectral scanner system (MSS) collected records of land surface mainly during 1972-1992. Investigations on MSS have been relatively limited compared with the numerous investigations its successors, such as Thematic Mapper (TM) and Enhanced TM Plus (ETM+). benefits program are not fully accomplished without inclusion archives. channel reflectance characteristics wereperformed followed by derived vegetation spectral indices Tasseled Cap (TC) transformed features using a...
Abstract. A PRELIMINARY INVESTIGATION ON COMPARISON AND TRANSFORMATION OF SENTINEL-2 MSI LANDSAT 8 OLI Timely and accurate earth observation with short revisit interval is usually necessary, especially for emergency response. Currently, several new generation sensors provided similar channel characteristics have been operated onboard different satellite platforms, including Sentinel-2 Landsat 8. Joint use of the observations by offers an opportunity to meet demands requirements. For example,...
Pan-sharpening is used to fuse multispectral images with low spatial resolution and a panchromatic (Pan) image high generate synthesized featured properties. The pan-sharpened are assumed valuable for further application. However, there have been few investigations on the effectiveness of products in practice (i.e. object detection), compared fact many algorithms pan-sharpening developed. In this paper, improvements contributed by process detection imagery were investigated. Original along...
It is widely recognized that the deeper networks or with more feature maps have better performance. Existing studies mainly focus on extending network depth and increasing of networks. At same time, horizontal expansion (e.g. Inception Model) as an alternative way to improve performance has not been fully investigated. Accordingly, we proposed NeuroTreeNet (NTN), a new extension through combination random forest Model. Based tree structure, in which each branch represents root node features...
In this paper, the impact of radiometric calibration on land surface temperature (LST) retrieval from a single thermal channel, particularly over urban areas, was investigated. To measure impact, an error coefficient (EC) defined as ratio LST to uncertainty. The EC estimated based sensitivity model, with focusing HJ-1B channel. Generally, under moderate condition, 0.1 (W·m <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">-2</sup> ·sr...