Search

The performance of three-dimensional (3D) point cloud reconstruction is affected by dynamic features such as vegetation. Vegetation can be detected by near-infrared (NIR)-based indices; however, the sensors providing multispectral data are resource intensive. To address this issue, this study proposes a two-stage framework to firstly improve the performance of the 3D point cloud generation of buildings with a two-view SfM algorithm, and secondly, reduce noise caused by vegetation. The proposed framework can also overcome the lack of near-infrared data when identifying vegetation areas for reducing interferences in the SfM process. The first stage includes cross-sensor training, model selection and the evaluation of image-to-image RGB to color infrared (CIR) translation with Generative Adversarial Networks (GANs). The second stage includes feature detection with multiple feature detector operators, feature removal with respect to the NDVI-based vegetation classification, masking, matching, pose estimation and triangulation to generate sparse 3D point clouds. The materials utilized in both stages are a publicly available RGB-NIR dataset, and satellite and UAV imagery. The experimental results indicate that the cross-sensor and category-wise validation achieves an accuracy of 0.9466 and 0.9024, with a kappa coefficient of 0.8932 and 0.9110, respectively. The histogram-based evaluation demonstrates that the predicted NIR band is consistent with the original NIR data of the satellite test dataset. Finally, the test on the UAV RGB and artificially generated NIR with a segmentation-driven two-view SfM proves that the proposed framework can effectively translate RGB to CIR for NDVI calculation. Further, the artificially generated NDVI is able to segment and classify vegetation. As a result, the generated point cloud is less noisy, and the 3D model is enhanced. [ABSTRACT FROM AUTHOR]

This paper presents an image destriping system for correcting striping noise of remote-sensing images. The developed system identifies stripe positions based on edge-detection and line-tracing algorithms. Pixels not affected by striping are used as control points to construct cubic spline functions describing spatial gray level distributions of an image. Detected stripes are corrected by replacing the pixels with more reasonable gray values computed from constructed spline functions. Gray values of clean pixels not affected by stripes are not altered to preserve data genuineness. Several experimental results demonstrate that the developed system can correctly detect stripes in remote-sensing images and effectively repair them. Evaluations of the results based on an quantitative image quality index indicate that the image quality has been improved significantly after destriping. The destriped images are not only visually more plausible but also can provide better interpretability and are more suitable for computerized analysis. Index Terms--Image destriping, image processing, image restoration, noise, noise removal, remote sensing, spline, striping noise.

The large number of spectral bands in hyperspectral data seriously complicates their use for classification. Selection of a useful subset of bands or derived features (spectral ratios, differences, derivatives) is always desirable, strongly affects the accuracy of the classification, and is often a practical necessity to keep the processing speed and memory requirements under control. This paper examines one possible procedure for selecting spectral derivatives to improve supervised classification of hyperspectral images. The procedure is designed to identify derivative features that are more effective at separating target classes and then add them to a base subset of features for classification. The goal is to create the smallest set of features that will result in the best classification result. A key issue in this process is the interplay of the number of features and the size of the training data sets since classification accuracy declines if the dimensionality of the feature space is too large relative to the number of training samples. Index Terms--Computer-aided data analysis, hyperspectral image analysis, spectral derivative.

This paper describes a flexible camera calibration method using refined vanishing points without prior information. Vanishing points are estimated from human-made features like parallel lines and repeated patterns. With the vanishing points extracted from the three mutually orthogonal directions, the interior and exterior orientation parameters can be further calculated using collinearity condition equations. A vanishing point refinement process is proposed to reduce the uncertainty caused by vanishing point localization errors. The fine-tuning algorithm is based on the divergence of grouped feature points projected onto the reference plane, minimizing the standard deviation of each of the grouped collinear points with an O(1) computational complexity. This paper also presents an automated vanishing point estimation approach based on the cascade Hough transform. The experiment results indicate that the vanishing point refinement process can significantly improve camera calibration parameters and the root mean square error (RMSE) of the constructed 3D model can be reduced by about 30%. [ABSTRACT FROM AUTHOR]