Instrumental variables (IVs) are widely used for estimating causal effects. There are two main challenges when using instrumental variables. First of all, using IV without additional assumptions such as linearity, the causal effect may still not be identifiable. Second, when selecting an IV, the validity of the selected IV is typically not testable since the causal graph is not identifiable from observational data. In this paper, we propose a method for bounding the causal effect with instrumental variables under weak confounding. In addition, we present a novel criterion to falsify the IV with side information about the confounder. We demonstrate the utility of the proposed method with simulated and real-world datasets.

Causal effect estimation has been studied by many researchers when only observational data is available. Sound and complete algorithms have been developed for pointwise estimation of identifiable causal queries. For non-identifiable causal queries, researchers developed polynomial programs to estimate tight bounds on causal effect. However, these are computationally difficult to optimize for variables with large support sizes. In this paper, we analyze the effect of "weak confounding'" on causal estimands. More specifically, under the assumption that the unobserved confounders that render a query non-identifiable have small entropy, we propose an efficient linear program to derive the upper and lower bounds of the causal effect. We show that our bounds are consistent in the sense that as the entropy of unobserved confounders goes to zero, the gap between the upper and lower bound vanishes. Finally, we conduct synthetic and real data simulations to compare our bounds with the bounds obtained by the existing work that cannot incorporate such entropy constraints and show that our bounds are tighter for the setting with weak confounders.

A method of rapid distortion correction for UAV (unmanned aerial vehicle) images based on GPU-CPU co-processing technology is introduced in this paper. Firstly, the GPU-CPU co-processing technique is used to accelerate the process of image distortion correction, then the efficiency of image distortion correction is further improved by selecting the best grid configuration and multi-level memory optimization and other strategies. Experimental results show that this method can not only obtain the same results as CPU serial computation, but also obtain a good acceleration effect that the maximum acceleration ratio of distortion correction computing process is 170.13 times, and the acceleration ratio of the whole process reaches 6.6 times. Hence, the method provided in this paper can meet the demand of fast distortion correction for large series of UAV images.

In order to realize automatic detection of tensile deformations in orthophoto which was made from satellite images, and improve the efficiency of orthophoto's production and inspection, an automatic detection method for tensile deformations in optical satellite orthophoto is proposed. Firstly, the size and range of orthophoto after ortho rectification were obtained by iterative solution based on original satellite images, DEM and the corrected RPC (Rational Polynomial Coefficient) parameters. Secondly, the image point coordinates on the original satellite image of each pixel on orthophoto were calculated by using the rational function model (RFM) and RPC parameters. Thirdly, the overlap times of the original satellite images corresponding to every pixel and its neighboring pixels were counted to determine whether the pixel was a tensile deformed pixel. If a pixel was deformed, it was marked with 255 on the binary image, otherwise with 0. Finally, the vector data of tensile deformations in orthophoto was obtained by image erosion, image expansion and vectorization of the binary image.