SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving

06/20/2020
by   Tiago Cortinhal, et al.
1

In this paper, we introduce SalsaNext for the uncertainty-aware semantic segmentation of a full 3D LiDAR point cloud in real-time. SalsaNext is the next version of SalsaNet [1] which has an encoder-decoder architecture where the encoder unit has a set of ResNet blocks and the decoder part combines upsampled features from the residual blocks. In contrast to SalsaNet, we introduce a new context module, replace the ResNet encoder blocks with a new residual dilated convolution stack with gradually increasing receptive fields and add the pixel-shuffle layer in the decoder. Additionally, we switch from stride convolution to average pooling and also apply central dropout treatment. To directly optimize the Jaccard index, we further combine the weighted cross-entropy loss with Lovasz-Softmax loss [2]. We finally inject a Bayesian treatment to compute the epistemic and aleatoric uncertainties for each point in the cloud. We provide a thorough quantitative evaluation on the Semantic-KITTI dataset [3], which demonstrates that the proposed SalsaNext outperforms other state-of-the-art semantic segmentation.

READ FULL TEXT

page 4

page 7

research
03/07/2020

SalsaNext: Fast Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving

In this paper, we introduce SalsaNext for the semantic segmentation of a...
research
08/24/2020

TORNADO-Net: mulTiview tOtal vaRiatioN semAntic segmentation with Diamond inceptiOn module

Semantic segmentation of point clouds is a key component of scene unders...
research
03/15/2021

S3Net: 3D LiDAR Sparse Semantic Segmentation Network

Semantic Segmentation is a crucial component in the perception systems o...
research
07/14/2023

LEST: Large-scale LiDAR Semantic Segmentation with Transformer

Large-scale LiDAR-based point cloud semantic segmentation is a critical ...
research
07/19/2023

U-CE: Uncertainty-aware Cross-Entropy for Semantic Segmentation

Deep neural networks have shown exceptional performance in various tasks...
research
02/13/2020

SegVoxelNet: Exploring Semantic Context and Depth-aware Features for 3D Vehicle Detection from Point Cloud

3D vehicle detection based on point cloud is a challenging task in real-...

Please sign up or login with your details

Forgot password? Click here to reset