Natural terrain classification using three‐dimensional ladar data for ground robot mobility

By Jean-François Lalonde, N. Vandapel, Daniel F. Huber, Martial Hebert. J. Field Robotics, 2006

512 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Environmental Engineering, Instrumentation

View Paper: https://www.semanticscholar.org/paper/48c1cbd9b7c059f5f585c003b68ad1ec32606d41

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

1. Hema Swetha Koppula
2. Ashutosh Saxena
3. Jan Dirk Wegner
4. Yizhak Ben-Shabat
5. M. Lindenbaum
6. Anath Fischer
7. Sebastian A. Scherer
8. Thorsten Joachims

In Environmental Engineering

1. Juha Hyyppä
2. Markus Holopainen
3. Mikko Vastaranta
4. Panagiotis Papadakis
5. Konrad Schindler
6. Ashutosh Saxena
7. Jan Dirk Wegner
8. Daniel Maturana

In Instrumentation

1. Panagiotis Papadakis
2. Konrad Schindler
3. Daniel Maturana
4. Sebastian A. Scherer

Citations in the corpus

• Contextually guided semantic labeling and search for three-dimensional point clouds (2013, background): “matrix (Lalonde et al., 2006), active vision for robotics (e.”
• 3D Convolutional Neural Networks for landing zone detection from LiDAR (2015, background): “These include three spectral shape features [30], three directional features and three height-related features [8], shape features from [9] and range variance features from [12].”
• FAST SEMANTIC SEGMENTATION OF 3D POINT CLOUDS WITH STRONGLY VARYING DENSITY (2016, background): “Related work in robotics uses point classification to separate the ground from trees and other obstacles (Lalonde et al., 2006).”
• 3DmFV: Three-Dimensional Point Cloud Classification in Real-Time Using Convolutional Neural Networks (2018, background): “Another approach represents each point by three saliency features (scatter, linear, and surface) [34] which are linear combinations of the eigenvalues of the local point sets’ covariance matrix.”
• Automatic Stem Mapping Using Single-Scan Terrestrial Laser Scanning (2012, background): “In [31], the points are supposed to belong to one of the following”
• Terrain traversability analysis methods for unmanned ground vehicles: A survey (2013, methodology): “By combining features that incorporate domain knowledge (Lalonde et al., 2006), the authors evaluated classifier fusion strategies (experts, stacked generalization and AdaBoost) and showed improved classification scores for road, human and negative obstacle detection, in comparison to single…”
• Contextually Guided Semantic Labeling and Search for 3D Point Clouds (2011, background): “It has been shown that this contextual information significantly improves the performance of image-based object detectors.”
• Shape-based recognition of 3D point clouds in urban environments (2009, unknown): “[16] classify natural terrain into “scatter”, “linear”, and “surface”.”