Conferences

An Occlusion-aware Feature for Range Images

( bib | pdf )

A. Quadros, J.P. Underwood, and B. Douillard. (ICRA 2012)

This paper presents a novel local feature for 3D range image data called 'the line image'. It is 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. We also propose a strategy for defining keypoints with stable orientations which define regions of interest in the scan for feature computation. The feature is applied to the task of object classification on sparse urban data taken with a Velodyne laser scanner, producing good results.

Scan segments matching for pairwise 3d alignment

( bib | pdf )

B. Douillard, A. Quadros, P. Morton, J.P. Underwood, M. DeDeuge, S. Hugosson, M. Hallstrom, and T.A. Bailey. (ICRA 2012)

This paper presents a method for pairwise 3D alignment which solves data association by matching scan segments across scans. Generating accurate segment associations allows to run a modified version of the Iterative Closest Point (ICP) algorithm where the search for point-to-point correspondences is constrained to associated segments. The novelty of the proposed approach is in the segment matching process which takes into account the proximity of segments, their shape, and the consistency of their relative locations in each scan. Scan segmentation is here assumed to be given (recent studies provide various alternatives [10], [19]). The method is tested on seven sequences of Velodyne scans acquired in urban environments. Unlike various other standard versions of ICP, which fail to recover correct alignment when the displacement between scans increases, the proposed method is shown to be robust to displacements of several meters. In addition, it is shown to lead to savings in computational times which are potentially critical in real-time applications.

A 3D classifier trained without field samples

( bib | pdf )

B. Douillard, A. Quadros, P. Morton, J.P. Underwood, and M. DeDeuge. (ICARCV 2012)

This paper presents a 3D classifier that is shown to maintain performance whether trained with real sensor data from the field or purely trained with 3D geometric (Computer Aided Design, CAD, like) models (downloaded from the Internet for instance). The proposed classifier is a global 3D template matching technique which exploits the location of the ground surface for more accurate alignment. The segmentation and position of the ground is given by the segmentation technique in [7] (which does not assumed the ground to be flat). The proposed classifier outperforms Spin Image and Fast Point Feature Histogram (FPFH) based classifiers by up to 30% (the latter being tested at different scales), in the case of sparse 3D data acquired with a Velodyne sensor. In addition, the experimental results suggest that field samples may not be required in the training set of alignment-based 3D classifiers. This finding implies that the laborious task of gathering hand labelled field data for training may be avoidable for this type of classifier.

On the segmentation of 3d lidar point clouds

( bib | pdf )

B. Douillard, J.P. Underwood, N. Kuntz, V. Vlaskine, A. Quadros, P. Morton, and A. Frenkel. (ICRA 2011)

This paper presents a set of segmentation methods for various types of 3D point clouds. Segmentation of dense 3D data (e.g. Riegl scans) is optimised via a simple yet efficient voxelisation of the space. Prior ground extraction is empirically shown to significantly improve segmentation performance. Segmentation of sparse 3D data (e.g. Velodyne scans) is 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. All the algorithms are tested on several hand labeled data sets using two novel metrics for segmentation evaluation.

A pipeline for the segmentation and classication of 3d point clouds

( bib | pdf )

B. Douillard, J.P. Underwood, V. Vlaskine, A. Quadros, and S.P. Singh. (ISER 2010)

This paper presents algorithms for fast segmentation of 3D point clouds and subsequent classification of the obtained 3D segments. The method jointly determines the ground surface and segments individual objects in 3D, including overhanging structures. When compared to six other terrain modelling techniques, this approach has minimal error between the sensed data and the representation; and is fast (processing a Velodyne scan in approximately 2 seconds). Applications include improved alignment of successive scans by enabling operations in sections (Velodyne scans are aligned 7% sharper compared to an approach using raw points) and more informed decision-making (paths move around overhangs). The use of segmentation to aid classification through 3D features, such as the Spin Image or the Spherical Harmonic Descriptor, is discussed and experimentally compared. Moreover, the segmentation facilitates a novel approach to 3D classification that bypasses feature extraction and directly compares 3D shapes via the ICP algorithm. This technique is shown to achieve accuracy on par with the best feature based classifier (92.1%) while being significantly faster and allowing a clearer understanding of the classifier.

Workshops

Can a 3d classifier be trained without field samples?

( bib | pdf )

B. Douillard, A. Quadros, P. Morton, J.P. Underwood, and M. DeDeuge. (IROS 2011)

This paper presents a 3D classifier that is shown to maintain performance whether trained with real sensor data from the field or purely trained with 3D geometric models (for example, computer aided design (CAD) models downloaded from the internet). It is shown that the proposed 3D classifier outperforms Spin Image and Fast Point Feature Histogram (FPFH) based classifiers by up to 30%. The proposed classifier is a global 3D template matching technique which exploits the knowledge of the position of the ground for more accurate alignment of the objects above. The experimental results suggest that field samples may not be required in the training set of alignment-based 3D classifiers, which potentially has major implications on the way the training of 3D classifiers is approached.