Distorted Building Image Matching with Automatic Viewpoint Rectification and Fusion.

Building image-matching plays a critical role in the urban applications. However, finding reliable and sufficient feature correspondences between the real-world urban building images that were captured in widely separate views are still challenging. In this paper, we propose a distorted image matching method combining the idea of viewpoint rectification and fusion. Firstly, the distorted images are rectified to the standard view with the transform invariant low-rank textures (TILT) algorithm. A local symmetry feature graph is extracted from the building images, followed by multi-level clustering using the mean shift algorithm, to automatically detect the low-rank texture region. After the viewpoint rectification, the Oriented FAST and Rotated BRIEF (ORB) feature is used to match the images. The grid-based motion statistics (GMS) and RANSAC techniques are introduced to remove the outliers and preserve the correct matching points to deal with the mismatched pairs. Finally, the matching results for the rectified views are projected to the original viewpoint space, and the matches before and after distortion rectification are fused to further determine the final matches. The experimental results show that both the number of matching pairs and the matching precision for the distorted building images can be significantly improved while using the proposed method.

Investigation of the spatially varying relationships of PM2.5 with meteorology, topography, and emissions over China in 2015 by using modified geographically weighted regression.

PM2.5 pollution is caused by multiple factors and determining how these factors affect PM2.5 pollution is important for haze control. In this study, we modified the geographically weighted regression (GWR) model and investigated the relationships between PM2.5 and its influencing factors. Experiments covering 368 cities and 9 urban agglomerations were conducted in China in 2015 and more than 20 factors were considered. The modified GWR coefficients (MGCs) were calculated for six variables, including two emission factors (SO2 and NO2 concentrations), two meteorological factors (relative humidity and lifted index), and two topographical factors (woodland percentage and elevation). Then the spatial distribution of MGCs was analyzed at city, cluster, and region scales. Results showed that the relationships between PM2.5 and the different factors varied with location. SO2 emission positively affected PM2.5, and the impact was the strongest in the Beijing-Tianjin-Hebei (BTH) region. The impact of NO2 was generally smaller than that of SO2 and could be important in coastal areas. The impact of meteorological factors on PM2.5 was complicated in terms of spatial variations, with relative humidity and lifted index exerting a strong positive impact on PM2.5 in Pearl River Delta and Central China, respectively. Woodland percentage mainly influenced PM2.5 in regions of or near deserts, and elevation was important in BTH and Sichuan. The findings of this study can improve our understanding of haze formation and provide useful information for policy-making.

The relationships between PM2.5 and aerosol optical depth (AOD) in mainland China: About and behind the spatio-temporal variations.

Satellite aerosol products have been widely used to retrieve ground PM2.5 concentration because of their wide coverage and continuous spatial distribution. While more and more studies have focused on the retrieval algorithms, the foundation for the retrieval-relationship between PM2.5 and satellite aerosol optical depth (AOD) has not been fully investigated. In this study, the relationships between PM2.5 and AOD were investigated in 368 cities in mainland China from February 2013 to December 2017, at different temporal and regional scales. Pearson correlation coefficients and the PM2.5/AOD ratio were used as indicators. Firstly, we established the relationship between PM2.5 and AOD in terms of the spatio-temporal variations, and discuss the impact of some potential factors for a better understanding of the spatio-temporal variations. Spatially, we found that the correlation is higher in the Beijing-Tianjin-Hebei and Chengyu regions and weaker in coastal areas. The PM2.5/AOD ratio shows an obvious north-south difference, with the ratio in North China higher than South China. Temporally, the correlation coefficient tends to be higher in May and September, with the PM2.5/AOD ratio higher in winter and lower in summer. As for interannual variations, we detected a decreasing tendency for the PM2.5-AOD correlation and PM2.5/AOD ratio for recent years. Then, to determine the impact of the weakening of the PM2.5-AOD relationship on PM2.5 remote sensing retrieval performance, a geographically weighted regression (GWR) retrieval experiment was conducted. The results showed that the performance of retrievals is also decreasing while PM2.5-AOD relationship getting weaker. Our study investigated the PM2.5-AOD relationship over a large extent at the city scale, and investigated the temporal variations in terms of interannual variations. The results will be useful for the satellite retrieval of PM2.5 concentration and will help us to further understand the PM2.5 pollution situation in mainland China.

Adaptive Norm Selection for Regularized Image Restoration and Super-Resolution.

In the commonly employed regularization models of image restoration and super-resolution (SR), the norm determination is often challenging. This paper proposes a method to adaptively determine the optimal norms for both fidelity term and regularization term in the (SR) restoration model. Inspired by a generalized likelihood ratio test, a piecewise function is proposed to solve the norm of the fidelity term. This function can find the stable norm value in a certain number of iterations, regardless of whether the noise type is Gaussian, impulse, or mixed. For the regularization norm, the main advantage of the proposed method is that it is locally adaptive. Specifically, it assigns different norms for different pixel locations, according to the local activity measured by a structure tensor metric. The proposed method was tested using different types of images. The experimental results and error analyses verify the efficacy of the method.