# Capsule Neural Network based Height Classification using Low-Cost Automotive Ultrasonic Sensors

arXiv: https://arxiv.org/abs/1902.09839 · HTML: https://mlsanity.com/paper/1902.09839/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Feb 2019.

## Built on by (most cited first, 5 of 5)

- [SynWoodScape: Synthetic Surround-view Fisheye Camera Dataset for Autonomous Driving](https://mlsanity.com/paper/2203.05056/) (2022)
- [Near-field Perception for Low-Speed Vehicle Automation using Surround-view Fisheye Cameras](https://mlsanity.com/paper/2103.17001/) (2021)
- [Woodscape Fisheye Semantic Segmentation for Autonomous Driving -- CVPR 2021 OmniCV Workshop Challenge](https://mlsanity.com/paper/2107.08246/) (2021)
- [DaF-BEVSeg: Distortion-aware Fisheye Camera based Bird's Eye View Segmentation with Occlusion Reasoning](https://mlsanity.com/paper/2404.06352/) (2024)
- [Impact of Video Compression Artifacts on Fisheye Camera Visual Perception Tasks](https://mlsanity.com/paper/2403.16338/) (2024)

## Abstract (arXiv)

High performance ultrasonic sensor hardware is mainly used in medical applications. Although, the development in automotive scenarios is towards autonomous driving, the ultrasonic sensor hardware still stays low-cost and low-performance, respectively. To overcome the strict hardware limitations, we propose to use capsule neural networks. By the high classification capability of this network architecture, we can achieve outstanding results for performing a detailed height analysis of detected objects. We apply a novel resorting and reshaping method to feed the neural network with ultrasonic data. This increases classification performance and computation speed. We tested the approach under different environmental conditions to verify that the proposed method is working independent of external parameters that is needed for autonomous driving.