Relative Total Variation Structure Analysis-Based Fusion Method for Hyperspectral and LiDAR Data Classification

The fusion of the hyperspectral image (HSI) and the light detecting and ranging (LiDAR) data has a wide range of applications. This paper proposes a novel feature fusion method for urban area classification, namely the relative total variation structure analysis (RTVSA), to combine various features derived from HSI and LiDAR data. In the feature extraction stage, a variety of high-performance methods including the extended multi-attribute profile, Gabor filter, and local binary pattern are used to extract the features of the input data. The relative total variation is then applied to remove useless texture information of the processed data. Finally, nonparametric weighted feature extraction is adopted to reduce the dimensions. Random forest and convolutional neural networks are utilized to evaluate the fusion images. Experiments conducted on two urban Houston University datasets (including Houston 2012 and the training portion of Houston 2017) demonstrate that the proposed method can extract the structural correlation from heterogeneous data, withstand a noise well, and improve the land cover classification accuracy.

Performance Evaluation of Dorsal Vein Network of Hand Imaging Using Relative Total Variation-Based Regularization for Smoothing Technique in a Miniaturized Vein Imaging System: A Pilot Study

Vein puncture is commonly used for blood sampling, and accurately locating the blood vessel is an important challenge in the field of diagnostic tests. Imaging systems based on near-infrared (NIR) light are widely used for accurate human vein puncture. In particular, segmentation of a region of interest using the obtained NIR image is an important field, and research for improving the image quality by removing noise and enhancing the image contrast is being widely conducted. In this paper, we propose an effective model in which the relative total variation (RTV) regularization algorithm and contrast-limited adaptive histogram equalization (CLAHE) are combined, whereby some major edge information can be better preserved. In our previous study, we developed a miniaturized NIR imaging system using light with a wavelength of 720–1100 nm. We evaluated the usefulness of the proposed algorithm by applying it to images acquired by the developed NIR imaging system. Compared with the conventional algorithm, when the proposed method was applied to the NIR image, the visual evaluation performance and quantitative evaluation performance were enhanced. In particular, when the proposed algorithm was applied, the coefficient of variation was improved by a factor of 15.77 compared with the basic image. The main advantages of our algorithm are the high noise reduction efficiency, which is beneficial for reducing the amount of undesirable information, and better contrast. In conclusion, the applicability and usefulness of the algorithm combining the RTV approach and CLAHE for NIR images were demonstrated, and the proposed model can achieve a high image quality.

An Image Enhancement Algorithm Based on Fractional-Order Phase Stretch Transform and Relative Total Variation

The main purpose of image enhancement technology is to improve the quality of the image to better assist those activities of daily life that are widely dependent on it like healthcare, industries, education, and surveillance. Due to the influence of complex environments, there are risks of insufficient detail and low contrast in some images. Existing enhancement algorithms are prone to overexposure and improper detail processing. This paper attempts to improve the treatment effect of Phase Stretch Transform (PST) on the information of low and medium frequencies. For this purpose, an image enhancement algorithm on the basis of fractional-order PST and relative total variation (FOPSTRTV) is developed to address the task. In this algorithm, the noise in the original image is removed by low-pass filtering, the edges of images are extracted by fractional-order PST, and then the images are fused with extracted edges through RTV. Finally, extensive experiments were used to verify the effect of the proposed algorithm with different datasets.