Automatic data driven vegetation modeling for lidar simulation

Deschaud, Jean-Emmanuel; Prasser, David; Dias, M. Freddie; Browning, Brett; Rander, Peter

doi:10.1109/icra.2012.6225269

Cited by 12 publications

(9 citation statements)

References 15 publications

(20 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, we have observed that our simple model of range sensing is not very accurate for vegetation, despite being quite reasonable for solid objects. This has also been observed by Deschaud et al [27].…”

Section: A Overviewsupporting

confidence: 84%

3D Convolutional Neural Networks for landing zone detection from LiDAR

Maturana

Scherer

2015

2015 IEEE International Conference on Robotics and Automation (ICRA)

192

105

View full text Add to dashboard Cite

We present a system for the detection of small and potentially obscured obstacles in vegetated terrain. The key novelty of this system is the coupling of a volumetric occupancy map with a 3D Convolutional Neural Network (CNN), which to the best of our knowledge has not been previously done. This architecture allows us to train an extremely efficient and highly accurate system for detection tasks from raw occupancy data. We apply this method to the problem of detecting safe landing zones for autonomous helicopters from LiDAR point clouds. Current methods for this problem rely on heuristic rules and use simple geometric features. These heuristics break down in the presence of low vegetation, as they do not distinguish between vegetation that may be landed on and solid objects that should be avoided. We evaluate the system with a combination of real and synthetic range data. We show our system outperforms various benchmarks, including a system integrating various hand-crafted point cloud features from the literature.

show abstract

Section: A Overviewsupporting

confidence: 84%

3D Convolutional Neural Networks for landing zone detection from LiDAR

Maturana

Scherer

2015

2015 IEEE International Conference on Robotics and Automation (ICRA)

192

105

View full text Add to dashboard Cite

show abstract

“…These range from software that simply replays modified data collected in previous experiments to complex models developed from field data. For example, a realistic simulation of a Velodyne HDL-64E interacting with vegetation was developed by quantifying the statistics of LIDAR-vegetation interaction for a sensor in a particular environment and then digitizing the environment based on those statistics [23,40]. More recently, much attention has been given to Waymo's Carcraft simulator, which uses a mixture of real and simulated data to virtualize previously measured events [27].…”

Section: Discussionmentioning

confidence: 99%

Enabling Off-Road Autonomous Navigation-Simulation of LIDAR in Dense Vegetation

et al. 2018

View full text Add to dashboard Cite

Machine learning techniques have accelerated the development of autonomous navigation algorithms in recent years, especially algorithms for on-road autonomous navigation. However, off-road navigation in unstructured environments continues to challenge autonomous ground vehicles. Many off-road navigation systems rely on LIDAR to sense and classify the environment, but LIDAR sensors often fail to distinguish navigable vegetation from non-navigable solid obstacles. While other areas of autonomy have benefited from the use of simulation, there has not been a real-time LIDAR simulator that accounted for LIDAR–vegetation interaction. In this work, we outline the development of a real-time, physics-based LIDAR simulator for densely vegetated environments that can be used in the development of LIDAR processing algorithms for off-road autonomous navigation. We present a multi-step qualitative validation of the simulator, which includes the development of an improved statistical model for the range distribution of LIDAR returns in grass. As a demonstration of the simulator’s capability, we show an example of the simulator being used to evaluate autonomous navigation through vegetation. The results demonstrate the potential for using the simulation in the development and testing of algorithms for autonomous off-road navigation.

show abstract

“…For buildings or objects with welldefined surfaces, traditional 3D scene reconstruction algorithms can be employed to generate the surface models. However, reconstructing trees from scan point data is difficult because small geometries, such as leaves and twigs, reflect only a portion of the beam, thus enabling the beam to propagate further and generate additional returns [22], [23]. In addition, the topology cannot be detected easily.…”

Section: Scan-based Studiesmentioning

confidence: 98%

Data-Driven Synthetic Modeling of Trees

Zhang

Dai

et al. 2014

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

In this paper, we develop a data-driven technique to model trees from a single laser scan. A multi-layer representation of the tree structure is proposed to guide the modeling process. In this process, a marching cylinder algorithm is first developed to construct visible branches from the laser scan data. Three levels of crown feature points are then extracted from the scan data to synthesize three layers of non-visible branches. Based on the hierarchical particle flow technique, the branch synthesis method has the advantage of producing visually convincing tree models that are consistent with scan data. User intervention is extremely limited. The robustness of this technique has been validated on both conifer and broadleaf trees.

show abstract

Automatic data driven vegetation modeling for lidar simulation

Cited by 12 publications

References 15 publications

3D Convolutional Neural Networks for landing zone detection from LiDAR

3D Convolutional Neural Networks for landing zone detection from LiDAR

Enabling Off-Road Autonomous Navigation-Simulation of LIDAR in Dense Vegetation

Data-Driven Synthetic Modeling of Trees

Contact Info

Product

Resources

About