CNN for very fast ground segmentation in velodyne LiDAR data

Veľas, Martin; Španěl, Michal; Hradiš, Michal; Herout, Adam

doi:10.1109/icarsc.2018.8374167

Cited by 48 publications

(46 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We also propose alternative networks for full 6DoF visual odometry estimation (including rotation) with results comparable to the state of the art. Our deployment of convolutional neural networks for odometry estimation, together with existing methods for object detection [2] or segmentation [1] also illustrates general usability of CNNs for this type of sparse LiDAR data.…”

Section: Introductionmentioning

confidence: 82%

See 1 more Smart Citation

CNN for IMU assisted odometry estimation using velodyne LiDAR

Veľas

Španěl

Hradiš

et al. 2018

2018 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC)

Self Cite

View full text Add to dashboard Cite

We introduce a novel method for odometry estimation using convolutional neural networks from 3D LiDAR scans. The original sparse data are encoded into 2D matrices for the training of proposed networks and for the prediction. Our networks show significantly better precision in the estimation of translational motion parameters comparing with state of the art method LOAM, while achieving real-time performance. Together with IMU support, high quality odometry estimation and LiDAR data registration is realized. Moreover, we propose alternative CNNs trained for the prediction of rotational motion parameters while achieving results also comparable with state of the art. The proposed method can replace wheel encoders in odometry estimation or supplement missing GPS data, when the GNSS signal absents (e.g. during the indoor mapping). Our solution brings real-time performance and precision which are useful to provide online preview of the mapping results and verification of the map completeness in real time.

show abstract

Section: Introductionmentioning

confidence: 82%

“…TE01020415), and the IT4IXS IT4Innovations Excellence project (LQ1602). 1 http://leica-geosystems.com 2 https://geoslam.com 3 https://www.lidarusa.com, http://www.riegl.com Sequence 08 of KITTI dataset [3] is presented with rotations provided by IMU.…”

Section: Introductionmentioning

confidence: 99%

CNN for IMU assisted odometry estimation using velodyne LiDAR

Veľas

Španěl

Hradiš

et al. 2018

2018 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Another popular approach [6], [11]- [13] to avoid using voxels relies on the inherent two-dimensional nature of lidars. It consists of a bijective mapping from 3D point cloud to a 2D point map, where (x, y, z) coordinates are encoded as azimuth and elevation angles measured from the origin.…”

Section: Related Work a Lidar Processing Using Deep Learningmentioning

confidence: 99%

Deep Generative Modeling of LiDAR Data

Caccia

Hoof

Courville

et al. 2019

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Building models capable of generating structured output is a key challenge for AI and robotics. While generative models have been explored on many types of data, little work has been done on synthesizing lidar scans, which play a key role in robot mapping and localization. In this work, we show that one can adapt deep generative models for this task by unravelling lidar scans into a 2D point map. Our approach can generate high quality samples, while simultaneously learning a meaningful latent representation of the data. We demonstrate significant improvements against state-of-the-art point cloud generation methods. Furthermore, we propose a novel data representation that augments the 2D signal with absolute positional information. We show that this helps robustness to noisy and imputed input; the learned model can recover the underlying lidar scan from seemingly uninformative data.

show abstract

“…In the self-driving context, the road is therefore assimilated to a plane and we use a large threshold to accommodate for any potential curvature. Fast Ground Segmentation extraction methods on Lidar Data with the use of Squeeze-net Architectures are capable of real-time prediction performances [37]. Geometric approximation: Plane extraction methods can be categorized into Hough-based, region growing, or RANSAC-based approaches.…”

Section: Static Background Estimation In 3d-environmentsmentioning

confidence: 99%

Real-Time Dynamic Object Detection for Autonomous Driving Using Prior 3D-Maps

Kiran

Roldão

Irastorza

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Lidar has become an essential sensor for autonomous driving as it provides reliable depth estimation. Lidar is also the primary sensor used in building 3D maps which can be used even in the case of low-cost systems which do not use Lidar. Computation on Lidar point clouds is intensive as it requires processing of millions of points per second. Additionally there are many subsequent tasks such as clustering, detection, tracking and classification which makes real-time execution challenging. In this paper, we discuss real-time dynamic object detection algorithms which leverages previously mapped Lidar point clouds to reduce processing. The prior 3D maps provide a static background model and we formulate dynamic object detection as a background subtraction problem. Computation and modeling challenges in the mapping and online execution pipeline are described. We propose a rejection cascade architecture to subtract road regions and other 3D regions separately. We implemented an initial version of our proposed algorithm and evaluated the accuracy on CARLA simulator.

show abstract

CNN for very fast ground segmentation in velodyne LiDAR data

Cited by 48 publications

References 19 publications

CNN for IMU assisted odometry estimation using velodyne LiDAR

CNN for IMU assisted odometry estimation using velodyne LiDAR

Deep Generative Modeling of LiDAR Data

Real-Time Dynamic Object Detection for Autonomous Driving Using Prior 3D-Maps

Contact Info

Product

Resources

About