A Robust Laser Stripe Extraction Method for Structured-Light Vision Sensing
Environmental sensing is a key technology for the development of unmanned cars, drones and robots. Many vision sensors cannot work normally in an environment with insufficient light, and the cost of using multiline LiDAR is relatively high. In this paper, a novel and inexpensive visual navigation se...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-08-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/20/16/4544 |
id |
doaj-aa8eb393337c4dbf85f1bfcb35ae4fef |
---|---|
record_format |
Article |
spelling |
doaj-aa8eb393337c4dbf85f1bfcb35ae4fef2020-11-25T03:52:34ZengMDPI AGSensors1424-82202020-08-01204544454410.3390/s20164544A Robust Laser Stripe Extraction Method for Structured-Light Vision SensingCongyang Zhao0Jianing Yang1Fuqiang Zhou2Junhua Sun3Xiaosong Li4Wentao Xie5Key Laboratory of Precision Opto-mechatronics Technology, Ministry of Education, Beihang University, Beijing 100191, ChinaKey Laboratory of Precision Opto-mechatronics Technology, Ministry of Education, Beihang University, Beijing 100191, ChinaKey Laboratory of Precision Opto-mechatronics Technology, Ministry of Education, Beihang University, Beijing 100191, ChinaKey Laboratory of Precision Opto-mechatronics Technology, Ministry of Education, Beihang University, Beijing 100191, ChinaKey Laboratory of Precision Opto-mechatronics Technology, Ministry of Education, Beihang University, Beijing 100191, ChinaKey Laboratory of Precision Opto-mechatronics Technology, Ministry of Education, Beihang University, Beijing 100191, ChinaEnvironmental sensing is a key technology for the development of unmanned cars, drones and robots. Many vision sensors cannot work normally in an environment with insufficient light, and the cost of using multiline LiDAR is relatively high. In this paper, a novel and inexpensive visual navigation sensor based on structured-light vision is proposed for environment sensing. The main research contents of this project include: First, we propose a laser-stripe-detection neural network (LSDNN) that can eliminate the interference of reflective noise and haze noise and realize the highly robust extraction of laser stripes region. Then we use a gray-gravity approach to extract the center of laser stripe and used structured-light model to reconstruct the point clouds of laser center. Then, we design a single-line structured-light sensor, select the optimal parameters for it and build a car–platform for experimental evaluation. This approach was shown to be effective in our experiments and the experimental results show that this method is more accurate and robust in complex environment.https://www.mdpi.com/1424-8220/20/16/4544structured-light vision sensorlaser stripe extractionsemantic segmentation |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Congyang Zhao Jianing Yang Fuqiang Zhou Junhua Sun Xiaosong Li Wentao Xie |
spellingShingle |
Congyang Zhao Jianing Yang Fuqiang Zhou Junhua Sun Xiaosong Li Wentao Xie A Robust Laser Stripe Extraction Method for Structured-Light Vision Sensing Sensors structured-light vision sensor laser stripe extraction semantic segmentation |
author_facet |
Congyang Zhao Jianing Yang Fuqiang Zhou Junhua Sun Xiaosong Li Wentao Xie |
author_sort |
Congyang Zhao |
title |
A Robust Laser Stripe Extraction Method for Structured-Light Vision Sensing |
title_short |
A Robust Laser Stripe Extraction Method for Structured-Light Vision Sensing |
title_full |
A Robust Laser Stripe Extraction Method for Structured-Light Vision Sensing |
title_fullStr |
A Robust Laser Stripe Extraction Method for Structured-Light Vision Sensing |
title_full_unstemmed |
A Robust Laser Stripe Extraction Method for Structured-Light Vision Sensing |
title_sort |
robust laser stripe extraction method for structured-light vision sensing |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2020-08-01 |
description |
Environmental sensing is a key technology for the development of unmanned cars, drones and robots. Many vision sensors cannot work normally in an environment with insufficient light, and the cost of using multiline LiDAR is relatively high. In this paper, a novel and inexpensive visual navigation sensor based on structured-light vision is proposed for environment sensing. The main research contents of this project include: First, we propose a laser-stripe-detection neural network (LSDNN) that can eliminate the interference of reflective noise and haze noise and realize the highly robust extraction of laser stripes region. Then we use a gray-gravity approach to extract the center of laser stripe and used structured-light model to reconstruct the point clouds of laser center. Then, we design a single-line structured-light sensor, select the optimal parameters for it and build a car–platform for experimental evaluation. This approach was shown to be effective in our experiments and the experimental results show that this method is more accurate and robust in complex environment. |
topic |
structured-light vision sensor laser stripe extraction semantic segmentation |
url |
https://www.mdpi.com/1424-8220/20/16/4544 |
work_keys_str_mv |
AT congyangzhao arobustlaserstripeextractionmethodforstructuredlightvisionsensing AT jianingyang arobustlaserstripeextractionmethodforstructuredlightvisionsensing AT fuqiangzhou arobustlaserstripeextractionmethodforstructuredlightvisionsensing AT junhuasun arobustlaserstripeextractionmethodforstructuredlightvisionsensing AT xiaosongli arobustlaserstripeextractionmethodforstructuredlightvisionsensing AT wentaoxie arobustlaserstripeextractionmethodforstructuredlightvisionsensing AT congyangzhao robustlaserstripeextractionmethodforstructuredlightvisionsensing AT jianingyang robustlaserstripeextractionmethodforstructuredlightvisionsensing AT fuqiangzhou robustlaserstripeextractionmethodforstructuredlightvisionsensing AT junhuasun robustlaserstripeextractionmethodforstructuredlightvisionsensing AT xiaosongli robustlaserstripeextractionmethodforstructuredlightvisionsensing AT wentaoxie robustlaserstripeextractionmethodforstructuredlightvisionsensing |
_version_ |
1724482175124897792 |