PillarSegNet: Pillar-based Semantic Grid Map Estimation using Sparse LiDAR Data

  title={PillarSegNet: Pillar-based Semantic Grid Map Estimation using Sparse LiDAR Data},
  author={Juncong Fei and Kunyu Peng and Philipp Heidenreich and Frank Bieder and Christoph Stiller},
  journal={2021 IEEE Intelligent Vehicles Symposium (IV)},
Semantic understanding of the surrounding environment is essential for automated vehicles. The recent publication of the SemanticKITTI dataset stimulates the research on semantic segmentation of LiDAR point clouds in urban scenarios. While most existing approaches predict sparse pointwise semantic classes for the sparse input LiDAR scan, we propose PillarSegNet to be able to output a dense semantic grid map. In contrast to a previously proposed grid map method, PillarSegNet uses PointNet to… 

Figures and Tables from this paper

MASS: Multi-Attentional Semantic Segmentation of LiDAR Data for Dense Top-View Understanding
MASS a Multi-Attentional Semantic Segmentation model specifically built for dense top-view understanding of the driving scenes is introduced, and is shown to be very effective for 3D object detection validated on the KITTI-3D dataset.
A Multi-Task Recurrent Neural Network for End-to-End Dynamic Occupancy Grid Mapping
A multi-task recurrent neural network is introduced to predict grid maps providing occupancies, velocity estimates, semantic information and the driveable area and is able to overcome some limitations of a geometric inverse sensor model in terms of representing object shapes and modeling freespace.


Scan-based Semantic Segmentation of LiDAR Point Clouds: An Experimental Study
This work performs a comprehensive experimental study of image-based semantic segmentation architectures for LiDAR point clouds and proposes an improved point cloud projection technique that does not suffer from systematic occlusions and a new kind of convolution layer with a reduced amount of weight-sharing along one of the two spatial dimensions.
Exploiting Multi-Layer Grid Maps for Surround-View Semantic Segmentation of Sparse LiDAR Data
This paper considers the transformation of laser range measurements into a top-view grid map representation to approach the task of LiDAR-only semantic segmentation, and develops a method to combine the semantic information from multiple scans and create dense ground truth grids.
SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences
A large dataset to propel research on laser-based semantic segmentation, which opens the door for the development of more advanced methods, but also provides plentiful data to investigate new research directions.
SemanticVoxels: Sequential Fusion for 3D Pedestrian Detection using LiDAR Point Cloud and Semantic Segmentation
This paper proposes a generalization of PointPainting to be able to apply fusion at different levels and demonstrates its strength in detecting challenging pedestrian cases and outperforms current state-of-the-art approaches.
RangeNet ++: Fast and Accurate LiDAR Semantic Segmentation
This paper proposes a novel post-processing algorithm that deals with problems arising from this intermediate representation of range images as an intermediate representation in combination with a Convolutional Neural Network exploiting the rotating LiDAR sensor model.
Multi-Scale Interaction for Real-Time LiDAR Data Segmentation on an Embedded Platform
The proposed Multi-scale Interaction Network (MINet) uses multiple paths with different scales and balances the computational resources between the scales and outperforms point-based, image- based, and projection-based methods in terms of accuracy, number of parameters, and runtime.
PointPillars: Fast Encoders for Object Detection From Point Clouds
benchmarks suggest that PointPillars is an appropriate encoding for object detection in point clouds, and proposes a lean downstream network.
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
This paper designs a novel type of neural network that directly consumes point clouds, which well respects the permutation invariance of points in the input and provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing.
Object Detection and Classification in Occupancy Grid Maps Using Deep Convolutional Networks
Qualitative and quantitative benchmark results show that robust detection and state of the art accuracy are achieved solely using top-view grid maps from range sensor data.
GndNet: Fast Ground Plane Estimation and Point Cloud Segmentation for Autonomous Vehicles
A novel end-to-end approach that estimates the ground plane elevation information in a grid-based representation and segments the ground points simultaneously in real-time, establishes a new state-of-the-art, achieves a run-time of 55Hz for ground plane estimation and ground point segmentation.