Heavy metal pollution in Topsoil is increasingly serious. In the paper, we present a novel analysis method for heavy metal pollution in Topsoil using Back-propagation (BP) Algorithm and genetic algorithm (GA). Usually there were many methods, including differential equation, but accuracy of these algorithms is not high. To acquire position and analysis of heavy metal pollution, we introduce GA and BP neural network. First, we build BP model and acquire the optimal weights and thresholds of BP through optimization of GA. At last, we search for global optima position of heavy metal pollution sources by GA. Experimental results show that better performance can be obtained by combining GA-based BP and GA-Based optimization.

3D reconstruction is used in applications such as virtual reality, digital cinematography and urban planning .The 3D registration is the important part of 3D reconstruction, which is one of outstanding and very basic problems in computer vision. In the paper, considering that there often exist a great number of planes in scenes, we show a planar-feature-based registration method. The planar features from the range image are extracted. Then, we can compute the transformation by SVD between the two coordinate systems and achieve the registration of these two range images.