In order to improve the precision and speed of the three-dimensional point cloud registration, it is suggested the three-dimensional point cloud registration based on ICP algorithm employing k-d tree optimization in this paper. First of all, the centre superposition method is adopted to realize the point cloud coarse registration, and then improve the traditional ICP where the K-D tree is used to quickly search the closest pair of points to enhance the speed of the point cloud registration. Finally the Three dimensional point cloud coarse registration is completed precisely. The method overcomes the defects of the traditional ICP algorithm using Euclidean distance to determine the closest pair of points which is time-consuming and plains lots of work. On the basis of this method, the experiment can be verified through different density Bunny Stanford point cloud data. The result shows that using K-d tree optimization of ICP algorithm, the precision, speed and stability of the point cloud registration is improved when the centre superposition method is adopted to realize the three dimensional point cloud coarse registration.
Based on a few ground control points, the affine transform model, a polynomial model and rational function model are adopted to correct the ZY-3 remote sensing imagery. Because of the traffic and economic issues only 7 ground control points (GCPs) are collected with high location accuracy, and they all only employed to solve the coefficient of the geometrical transformation model. So there are no residual GCP for the evaluation of the correction accuracy and an intuitive and effective accuracy evaluation method is presented for correction result superimposed with topographic maps to verify the geometric correction accuracy. The experimental result shows that having difficulty in obtaining sufficient quantity of the control points, rational function model could be recommended to correct the ZY-3 imagery and obtain the corrective result with relatively high accuracy, which has certain application value, and it is a good method in absence of GCP to use topographic map to evaluate the correction accuracy.
Considering the problem in monitoring agricultural condition in the semi-arid areas of Northwest of China, we propose a new method for estimation of crop planting area, using the single phase optical and microwave remote sensing data collaboratively, which have demonstrated their respective advantages in the extraction of surface features. In the model, the ASAR backscatter coefficient is normalized by the incident angle at first, then the classifier based on Bayesian network is developed, and the VV, VH polarization of ASAR and all the 7 TM bands are taken as the input of the classifier to get the class labels of each pixel of the images. Moreover the crop planting areas can be extracted by the classification results. At last, the model is validated for the necessities of normalization by the incident angle and integration of TM and ASAR respectively. It results that the estimation accuracy of crop planting area of corn and other crops garden are 98.47% and 78.25% respectively using the proposed method, with an improvement of estimation accuracy of about 3.28% and 4.18% relative to single TM classification. These illustrate that synthesis of optical and microwave remote sensing data is efficient and potential in estimation crop planting area.