Su, Y. and Wang, Z., 2018. 3D reconstruction of submarine landscape ecological security pattern based on virtual reality. In: Liu, Z.L. and Mi, C. (eds.), Advances in Sustainable Port and Ocean Engineering. Journal of Coastal Research, Special Issue No. 83, pp. 615–620. Coconut Creek (Florida), ISSN 0749-0208.
The conventional 3D reconstruction method cannot provide precise estimation of pose of the camera, which leads to long reconstruction time and sparse reconstructed point cloud data during modeling of ecological security pattern of submarine landscape. This paper proposes a 3D reconstruction method of submarine landscape ecological security pattern based on virtual reality. The motion method is adopted to track the pose of the camera and obtain the landscape image of the seafloor. The Harris corner extraction algorithm and Canny edge extraction algorithm are used to extract the landscape image of the seafloor. The matching of the feature points of the broad baseline image in the extracted image is achieved by using the pole constraint, and the stable matching points are obtained. Intensive reconstruction of scene objects is achieved by using multi-vision intensive matching method. The experimental results show that the proposed method has the advantages of dense reconstructed point cloud data, short reconstruction run time and strong robustness.