Authors: Shou Xiang Zhang

Abstract: An unmanned mining technology for the fully mechanized longwall face automation production is proposed and studied. The essential technology will bring the longwall face production into visualization through the Virtual Reality (VR) and Augmented Reality (AR) union. Based on the visual theoretical model of the longwall face, the combination of virtual and reality, the real-time interactive and the 3D registration function were realized. The Key technology and Alpha channel are used to the combination of the real long wall face and the virtual user.

388

Authors: Xi Fan Shi, Xiang Hua Chen

Abstract: It is of great significance to digitize ancient paintings and calligraphy. A typical way to acquire them is photographing the painting block by block and then stitching the photos together. Currently, all the algorithms to register photos are based on affine transformation parameters estimation. But these kinds of solutions have great error when the painting is rugged and scanned at high definition. A ruggedness of only 5 millimeters and 300 PPI scanning will cause the stitching error of 17 pixels for the adjacent photos. In this paper, first, the correctness of affine transformation of corresponding point on photos of a planar object is proved. Then, for non-planar object, the error equation is conducted. After that, an algorithm to correct the error due to perspective projection is proposed. The key to correction algorithm is to compute the difference between the perspective projection and parallel projection. With it, a virtual photo of infinite focal length is generated and the error is eliminated.

1173

Authors: Hua Ying Liu, Chen Chen, Fang Zhou Zhang, Miao Gong, Xu Yan Wang

Abstract: There are several transformation methods between different coordinate system. This article adopts affine transformation and least square principle, deduces from conversion between geographic coordinates system and the pixel coordinate system theoretically, and conducts a better control aiming at the error. Finally, an example was demonstrated in this article to prove the rationality and practical value of this algorithm.

2400

Abstract: This paper presents a closed-form solution to determination of the position and orientation of a perspective camera with two unknown effective focal lengths for the noncoplanar perspective four point (P4P) problem. Given four noncoplanar 3D points and their correspondences in image coordinate, we convert perspective transformation to affine transformation, and formulate the problem using invariance to 3D affine transformation and arrive to a closed-form solution. We show how the noncoplanar P4P problem is cast into the problem of solving an eighth degree polynomial equation in one unknown. This result shows the noncoplanar P4P problem with two unknown effective focal lengths has at most 8 solutions. Last, we confirm the conclusion by an example. Although developed as part of landmark-guided navigation, the solution might well be used for landmark-based tracking problem, hand-eye coordination, and for fast determination of interior and exterior camera parameters. Because our method is based on closed-form solution, its speed makes it a potential candidate for solving above problems.

6

Authors: Zi Ming Xiong, Gang Wan

Abstract: In this paper, we propose an approach to automatic great-scene 3D reconstruction based on UAV sequence images. In this method, Harris feature point and SIFT feature vector is used to distill image feature, achieving images match; quasi-perspective projection model and factorization is employed to calibrate the uncalibrated image sequences automatically; Efficient suboptimal solutions to the optimal triangulation is plied to obtain the coordinate of 3D points; quasi-dense diffusing algorithm is bestowed to make 3D point denseness; the algorithm of bundle adjustment is taken to improve the precision of 3D points; the approach of Possion surface reconstruction is used to make 3D points gridded. This paper introduces the theory and technology of computer vision into great-scene 3D reconstruction, provides a new way for the construction of 3D scene, and provides a new thinking for the appliance of UAV sequence images.

2294