A fully automatic registration approach based on contour and SIFT for HJ-1 images

To achieve a fully automatic registration between HJ-1 CCD images and HJ-1 infrared images is a difficult task as it must deal with the varying illuminations and resolutions of the images,different perspectives,and the local deformations within the images.In this paper,aimed at those registration issues,a fully automatic registration approach based on contour and SIFT is proposed.The registration technique performs a pre-registration process using contour feature matching algorithm that decides the overlapping region between a reference image and an input image.Once the coarse regions are obtained,it performs a fine registration process based on SIFT detector and a local adaptive matching strategy.In the fine registration process,image blocking theory is used,which not only speeds up the features extraction and matching,but also makes the matching point pairs distributed uniformly in images,and further improves the accuracy of input image rectification.Experiments with visible images and infrared images from HJ-1A/B demonstrate the efficiency and the accuracy of the proposed technique for multisource remote sensing images registration.

Automatic marker-free registration of single tree point-cloud data based on rotating projection

Point-cloud data acquired using a terrestrial laser scanner play an important role in digital forestry research.Multiple scans are generally used to overcome occlusion effects and obtain complete tree structural information.However,the placement of artificial reflectors in a forest with complex terrain for marker-based registration is time-consuming and difficult.In this study,an automatic coarse-to-fine method for the registration of pointcloud data from multiple scans of a single tree was proposed.In coarse registration,point clouds produced by each scan are projected onto a spherical surface to generate a series of two-dimensional(2D)images,which are used to estimate the initial positions of multiple scans.Corresponding feature-point pairs are then extracted from these series of 2D images.In fine registration,point-cloud data slicing and fitting methods are used to extract corresponding central stem and branch centers for use as tie points to calculate fine transformation parameters.To evaluate the accuracy of registration results,we propose a model of error evaluation via calculating the distances between center points from corresponding branches in adjacent scans.For accurate evaluation,we conducted experiments on two simulated trees and six real-world trees.Average registration errors of the proposed method were 0.026 m around on simulated tree point clouds,and 0.049 m around on real-world tree point clouds.