A
A. Quadros
Researcher at University of Sydney
Publications - 5
Citations - 674
A. Quadros is an academic researcher from University of Sydney. The author has contributed to research in topics: Image segmentation & Segmentation. The author has an hindex of 5, co-authored 5 publications receiving 600 citations.
Papers
More filters
Proceedings ArticleDOI
On the segmentation of 3D LIDAR point clouds
Bertrand Douillard,James Underwood,N. Kuntz,Vsevolod Vlaskine,A. Quadros,Peter Morton,A. Frenkel +6 more
TL;DR: This paper presents a set of segmentation methods for various types of 3D point clouds addressed using ground models of non-constant resolution either providing a continuous probabilistic surface or a terrain mesh built from the structure of a range image, both representations providing close to real-time performance.
Proceedings ArticleDOI
Scan segments matching for pairwise 3D alignment
Bertrand Douillard,A. Quadros,Peter Morton,James Underwood,M. De Deuge,S. Hugosson,M. Hallstrom,Timothy S. Bailey +7 more
TL;DR: A method for pairwise 3D alignment which solves data association by matching scan segments across scans by taking into account the proximity of segments, their shape, and the consistency of their relative locations in each scan is presented.
Proceedings ArticleDOI
Hybrid elevation maps: 3D surface models for segmentation
Bertrand Douillard,James Underwood,Narek Melkumyan,Surya P. N. Singh,Shrihari Vasudevan,Christopher Brunner,A. Quadros +6 more
TL;DR: An algorithm for segmenting 3D point clouds is presented, shown to provide the best fit to the data as well as being unique in the sense that it jointly performs ground extraction, overhang representation and 3D segmentation.
Proceedings ArticleDOI
An occlusion-aware feature for range images
TL;DR: A novel local feature for 3D range image data called `the line image' is presented, designed to be highly viewpoint invariant by exploiting the range image to efficiently detect 3D occupancy, producing a representation of the surface, occlusions and empty spaces.
Proceedings ArticleDOI
A 3D classifier trained without field samples
TL;DR: The experimental results suggest that field samples may not be required in the training set of alignment-based 3D classifiers, implying that the laborious task of gathering hand labelled field data for training may be avoidable for this type of classifier.