研究目的
Investigating the effectiveness of a new low-rank spectral nonlocal approach (LRSNL) for the simultaneous removal of a mixture of different types of noises in hyperspectral images (HSI) to improve their visual quality and the accuracy in target detection or classification.
研究成果
The proposed LRSNL approach is simple and effective for the restoration of hyperspectral images, capable of removing a mixture of different types of noises while preserving the fine spatial structures. The importance of the precleaning step using the LR property is demonstrated.
研究不足
LRSNL treats all spectral bands the same and simply uses the average of all the bands to calculate similarities between patches. An adaptive weighting scheme could be developed for bands of different importance.
1：Experimental Design and Method Selection:
The proposed method (LRSNL) combines the low-rank (LR) property of HSI with a spectral nonlocal (SNL) method for restoration. The LR property is used for precleaning patches, and SNL is applied for final restoration, considering both spectral and spatial information.
2：Sample Selection and Data Sources:
Synthetic and real HSI datasets are used, including an Indian Pine dataset and an EO-1 Hyperion image dataset.
3：List of Experimental Equipment and Materials:
Not explicitly mentioned in the abstract.
4：Experimental Procedures and Operational Workflow:
The HSI cube is divided into small patches, precleaned using the LR property, and then restored using SNL by calculating weights based on spectral and spatial similarities.
5：Data Analysis Methods:
Performance is evaluated visually and quantitatively using the improved signal to noise ratio (ISNR) for each spectral band.
独家科研数据包，助您复现前沿成果，加速创新突破
获取完整内容
