Paper Info
Title
Novel Dominant Plant Detection Algorithm for Image Sequence
Abstract
Dominant plane is an important geometric feature and can be used in a wide range of applications. In this paper, we develop a robust technology for dominant plane detection using the progressive structure from motion and dominant plane fitting algorithms. Firstly, we propose a progressive structure from motion algorithm to reconstruct the real scene from the image sequences, and obtain the information of three-dimensional points in the scene. In the following, based on the least median square (LMedSq) estimation and ransac theory, we present a novel plane fitting algorithm to find the dominant plane near the scene surface from the reconstructive points. Experimental results from different outdoor scenarios show that the proposed reconstruction algorithm obtains dense 3D point cloud, and achieves satisfactory recovery from image sequence. Then, the plane fitting algorithm accurately detects the dominant plane region from the reconstructive points. The detected plane is the approximation for local surface and meets the actual scene. These tests verify that the proposed method is effective, accurate and robust.
Year
DOI
Venue
2013
10.1109/ICIG.2013.68
ICIG
Keywords
Field
DocType
local surface approximation,outdoor scenarios,plane fitting algorithm,dominant plane fitting algorithms,dominant plane region,reconstructive point,approximation theory,fitting algorithm,least median square estimation,reconstruction algorithm,scene surface,novel plane fitting algorithm,ransac theory,computational geometry,lmedsq,three-dimensional points information,progressive structure,estimation theory,image reconstruction,image sequence,dominant plane detection,motion algorithm,image sequences,reconstructive points,dense 3d point cloud,natural scenes,geometric feature,dominant plane,real scene reconstruction,novel dominant plant detection,iterative methods,actual scene,image motion analysis,estimation,fitting,robustness
Structure from motion,Iterative reconstruction,Computer vision,Feature detection (computer vision),Computer science,RANSAC,Image plane,Computational geometry,Algorithm,Reconstruction algorithm,Artificial intelligence,Point cloud
Conference
Citations 
PageRank 
References 
0
0.34
0
Authors
2
Name
Order
Citations
PageRank
Baojie Fan14110.48
Yingkui Du2177.23