mlsanityData to 14 Oct 2026

A Near Sensor Edge Computing System for Point Cloud Semantic Segmentation

arXiv 2207.05888 ↗First posted 12 Jul 2022cs.CV cs.ARcited by 0

Not on the map. Why?

Abstract (arXiv)

Point cloud semantic segmentation has attracted attentions due to its robustness to light condition. This makes it an ideal semantic solution for autonomous driving. However, considering the large computation burden and bandwidth demanding of neural networks, putting all the computing into vehicle Electronic Control Unit (ECU) is not efficient or practical. In this paper, we proposed a light weighted point cloud semantic segmentation network based on range view. Due to its simple pre-processing and standard convolution, it is efficient when running on deep learning accelerator like DPU. Furthermore, a near sensor computing system is built for autonomous vehicles. In this system, a FPGA-based deep learning accelerator core (DPU) is placed next to the LiDAR sensor, to perform point cloud pre-processing and segmentation neural network. By leaving only the post-processing step to ECU, this solution heavily alleviate the computation burden of ECU and consequently shortens the decision making and vehicles reaction latency. Our semantic segmentation network achieved 10 frame per second (fps) on Xilinx DPU with computation efficiency 42.5 GOP/W.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 31 of its 39 references that are in the map. First posted on arXiv 12 Jul 2022.

Builds on

31 of 39 references.

References · 31

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  3. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  5. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,262
  6. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
  7. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  8. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  9. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 997
  10. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  11. 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
  12. 2018Rethinking the Value of Network Pruningcited by 599
19 more
  1. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 585
  2. 2020Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentationcited by 389
  3. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 385
  4. 2020PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentationcited by 275
  5. 2017ICNet for Real-Time Semantic Segmentation on High-Resolution Imagescited by 261
  6. 2017SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloudcited by 232
  7. 2018SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloudcited by 228
  8. 2017SEGCloud: Semantic Segmentation of 3D Point Cloudscited by 179
  9. 2021RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentationcited by 173
  10. 2020SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentationcited by 170
  11. 2018SPLATNet: Sparse Lattice Networks for Point Cloud Processingcited by 158
  12. 2020AMVNet: Assertion-based Multi-View Fusion Network for LiDAR Semantic Segmentationcited by 87
  13. 2017Deep Projective 3D Semantic Segmentationcited by 81
  14. 20203D-MiniNet: Learning a 2D Representation from Point Clouds for Fast and Efficient 3D LIDAR Semantic Segmentationcited by 58
  15. 2021FIDNet: LiDAR Point Cloud Semantic Segmentation with Fully Interpolation Decodingcited by 46
  16. 2019LatticeNet: Fast Point Cloud Segmentation Using Permutohedral Latticescited by 38
  17. 2020TORNADO-Net: mulTiview tOtal vaRiatioN semAntic segmentation with Diamond inceptiOn modulecited by 36
  18. 2018PointSeg: Real-Time Semantic Segmentation Based on 3D LiDAR Point Cloudcited by 19
  19. 2021A Surface Geometry Model for LiDAR Depth Completioncited by 18

Built on by

Not cited yet.