James Patrick Underwood

On the segmentation of 3D LIDAR point clouds

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.

Towards reliable perception for Unmanned Ground Vehicles in challenging conditions

This work aims to promote reliability and integrity in autonomous perceptual systems, with a focus on outdoor unmanned ground vehicle (UGV) autonomy. For this purpose, a comprehensive UGV system, comprising many different exteroceptive and proprioceptive sensors has been built. The first contribution of this work is a large, accurately calibrated and synchronised, multi-modal data-set, gathered in controlled environmental conditions, including the presence of dust, smoke and rain. The data have then been used to analyse the effects of such challenging conditions on perception and to identify common perceptual failures. The second contribution is a presentation of methods for mitigating these failures to promote perceptual integrity in adverse environmental conditions.

A Pipeline for the Segmentation and Classification of 3D Point Clouds

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’s behaviour.

Self-learning classification of radar features for scene understanding

Autonomous driving is a challenging problem in mobile robotics, particularly when the domain is unstructured, as in an outdoor setting. In addition, field scenarios are often characterized by low visibility as well, due to changes in lighting conditions, weather phenomena including fog, rain, snow and hail, or the presence of dust clouds and smoke. Thus, advanced perception systems are primarily required for an off-road robot to sense and understand its environment recognizing artificial and natural structures, topology, vegetation and paths, while ensuring, at the same time, robustness under compromised visibility. In this paper the use of millimeter-wave radar is proposed as a possible solution for all-weather off-road perception. A self-learning approach is developed to train a classifier for radar image interpretation and autonomous navigation. The proposed classifier features two main stages: an adaptive training stage and a classification stage. During the training stage, the system automatically learns to associate the appearance of radar data with class labels. Then, it makes predictions based on past observations. The training set is continuously updated online using the latest radar readings, thus making it feasible to use the system for long range and long duration navigation, over changing environments. Experimental results, obtained with an unmanned ground vehicle operating in a rural environment, are presented to validate this approach. A quantitative comparison with laser data is also included showing good range accuracy and mapping ability as well. Finally, conclusions are drawn on the utility of millimeter-wave radar as a robotic sensor for persistent and accurate perception in natural scenarios.

Scan segments matching for pairwise 3D alignment

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.

Orchard fruit segmentation using multi-spectral feature learning

This paper presents a multi-class image segmentation approach to automate fruit segmentation. A feature learning algorithm combined with a conditional random field is applied to multi-spectral image data. Current classification methods used in agriculture scenarios tend to use hand crafted application-based features. In contrast, our approach uses unsupervised feature learning to automatically capture most relevant features from the data. This property makes our approach robust against variance in canopy trees and therefore has the potential to be applied to different domains. The proposed algorithm is applied to a fruit segmentation problem for a robotic agricultural surveillance mission, aiming to provide yield estimation with high accuracy and robustness against fruit variance. Experimental results with data collected in an almond farm are shown. The segmentation is performed with features extracted from multi-spectral (colour and infrared) data. We achieve a global classification accuracy of 88%.

Radar-based perception for autonomous outdoor vehicles

Autonomous vehicle operations in outdoor environments challenge robotic perception. Construction, mining, agriculture, and planetary exploration environments are examples in which the presence of dust, fog, rain, changing illumination due to low sun angles, and lack of contrast can dramatically degrade conventional stereo and laser sensing. Nonetheless, environment perception can still succeed under compromised visibility through the use of a millimeter-wave radar. Radar also allows for multiple object detection within a single beam, whereas other range sensors are limited to one target return per emission. However, radar has shortcomings as well, such as a large footprint, specularity effects, and limited range resolution, all of which may result in poor environment survey or difficulty in interpretation. This paper presents a novel method for ground segmentation using a millimeter-wave radar mounted on a ground vehicle. Issues relevant to short-range perception in an outdoor environment are described along with field experiments and a quantitative comparison to laser data. The ability to classify the ground is successfully demonstrated in clear and low-visibility conditions, and significant improvement in range accuracy is shown. Finally, conclusions are drawn on the utility of millimeter-wave radar as a robotic sensor for persistent and accurate perception in natural scenarios.

Hybrid elevation maps: 3D surface models for segmentation

This paper presents an algorithm for segmenting 3D point clouds. It extends terrain elevation models by incorporating two types of representations: (1) ground representations based on averaging the height in the point cloud, (2) object models based on a voxelisation of the point cloud. The approach is deployed on Riegl data (dense 3D laser data) acquired in a campus type of environment and compared against six other terrain models. Amongst elevation models, it is 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. We experimentally demonstrate that the resulting model is also applicable to path planning.

Calibration of range sensor pose on mobile platforms

This paper describes a new methodology for calculating the translational and rotational offsets of a range sensor to a reference coordinate frame on the platform to which it is affixed. The technique consists of observing an environment of known or partially known geometry, from which the offsets are determined by minimizing the error between the sensed data and the known structure. Analytic results are presented which derive the necessary conditions for a successful optimisation. Practical results confirm the analysis and show that it is possible to obtain more precise results than those obtained through hand measurement.

A Feature Learning Based Approach for Automated Fruit Yield Estimation

This paper demonstrates a generalised multi-scale feature learning approach to multi-class segmentation, applied to the estimation of fruit yield on treecrops. The learning approach makes the algorithmflexible and adaptable to different classification problems, and hence applicable to a wide variety of tree-crop applications. Extensive experiments were performed on a dataset consisting of 8000 colour images collected in an apple orchard. This paper shows that the algorithm was able to segment apples with different sizes and colours in an outdoor environment with natural lighting conditions, with a single model obtained from images captured using a monocular colour camera. The segmentation results are applied to the problem of fruit counting and the results are compared against manual counting. The results show a squared correlation coefficient of R 2 = 0.81.