Image sequence and point cloud data fusion method for solving occlusion and error mapping

Abstract

The invention discloses an image sequence and point cloud data fusion method for solving occlusion and error mapping. The method is characterized by comprising the following steps: acquiring an imagein an image sequence and a laser point cloud corresponding to the image; determining a projection relationship between laser point cloud points and image pixel points according to the image and the laser point cloud; determining an index map corresponding to the image according to the projection relationship between the laser point cloud points and the image pixel points and the laser point cloud;determining a fusion image corresponding to the image according to the index map, the image and the laser point cloud; and splicing the fused images respectively corresponding to all images in the image sequence to obtain a spliced image. As the fused images corresponding to the images in the image sequence are spliced, the problems of shielding and error mapping caused by a single image are solved. 本发明公开了一种解决遮挡与错误映射的影像序列与点云数据融合的方法，其特征在于，包括步骤：获取影像序列中影像和所述影像对应的激光点云；根据所述影像和所述激光点云，确定激光点云点与影像像素点的投影关系；根据所述激光点云点与影像像素点的投影关系以及所述激光点云，确定所述影像对应的索引图；根据所述索引图、所述影像以及所述激光点云，确定所述影像对应的融合影像；对所述影像序列中所有影像各自分别对应的融合影像拼接，得到拼接图像。由于将影像序列中各影像各自分别对应的融合影像进行拼接，不会出现因单张影像导致的遮挡和错误映射的问题。