• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

一种基于纵向主动视觉的障碍物检测方法。

An Obstacle Detection Method Based on Longitudinal Active Vision.

作者信息

Shi Shuyue, Ni Juan, Kong Xiangcun, Zhu Huajian, Zhan Jiaze, Sun Qintao, Xu Yi

机构信息

School of Transportation and Vehicle Engineering, Shandong University of Technology, Zibo 255000, China.

Qingte Group Co., Ltd., Qingdao 266106, China.

出版信息

Sensors (Basel). 2024 Jul 7;24(13):4407. doi: 10.3390/s24134407.

DOI:10.3390/s24134407
PMID:39001185
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11244351/
Abstract

The types of obstacles encountered in the road environment are complex and diverse, and accurate and reliable detection of obstacles is the key to improving traffic safety. Traditional obstacle detection methods are limited by the type of samples and therefore cannot detect others comprehensively. Therefore, this paper proposes an obstacle detection method based on longitudinal active vision. The obstacles are recognized according to the height difference characteristics between the obstacle imaging points and the ground points in the image, and the obstacle detection in the target area is realized without accurately distinguishing the obstacle categories, which reduces the spatial and temporal complexity of the road environment perception. The method of this paper is compared and analyzed with the obstacle detection methods based on VIDAR (vision-IMU based detection and range method), VIDAR + MSER, and YOLOv8s. The experimental results show that the method in this paper has high detection accuracy and verifies the feasibility of obstacle detection in road environments where unknown obstacles exist.

摘要

道路环境中遇到的障碍物类型复杂多样，准确可靠地检测障碍物是提高交通安全的关键。传统的障碍物检测方法受样本类型限制，因此无法全面检测其他障碍物。因此，本文提出一种基于纵向主动视觉的障碍物检测方法。根据图像中障碍物成像点与地面点之间的高度差特征识别障碍物，无需精确区分障碍物类别即可实现目标区域内的障碍物检测，降低了道路环境感知的时空复杂度。将本文方法与基于VIDAR（基于视觉-惯性测量单元的检测与测距方法）、VIDAR+MSER和YOLOv8s的障碍物检测方法进行了比较分析。实验结果表明，本文方法具有较高的检测精度，验证了在存在未知障碍物的道路环境中进行障碍物检测的可行性。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d8c6/11244351/14a21323d9de/sensors-24-04407-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d8c6/11244351/b19ecdcfd1e8/sensors-24-04407-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d8c6/11244351/f553486effdf/sensors-24-04407-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d8c6/11244351/5ef9159ad01e/sensors-24-04407-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d8c6/11244351/836338ea00c5/sensors-24-04407-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d8c6/11244351/69310d852354/sensors-24-04407-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d8c6/11244351/f5f80fd051fb/sensors-24-04407-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d8c6/11244351/50690c27c9cc/sensors-24-04407-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d8c6/11244351/b6673625e2d9/sensors-24-04407-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d8c6/11244351/1d546b7823cc/sensors-24-04407-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d8c6/11244351/b5188f195eeb/sensors-24-04407-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d8c6/11244351/f017819bb969/sensors-24-04407-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d8c6/11244351/f62f7abe15d1/sensors-24-04407-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d8c6/11244351/83b1ca534717/sensors-24-04407-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d8c6/11244351/9b072e4d59a2/sensors-24-04407-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d8c6/11244351/14a21323d9de/sensors-24-04407-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d8c6/11244351/b19ecdcfd1e8/sensors-24-04407-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d8c6/11244351/f553486effdf/sensors-24-04407-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d8c6/11244351/5ef9159ad01e/sensors-24-04407-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d8c6/11244351/836338ea00c5/sensors-24-04407-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d8c6/11244351/69310d852354/sensors-24-04407-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d8c6/11244351/f5f80fd051fb/sensors-24-04407-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d8c6/11244351/50690c27c9cc/sensors-24-04407-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d8c6/11244351/b6673625e2d9/sensors-24-04407-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d8c6/11244351/1d546b7823cc/sensors-24-04407-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d8c6/11244351/b5188f195eeb/sensors-24-04407-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d8c6/11244351/f017819bb969/sensors-24-04407-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d8c6/11244351/f62f7abe15d1/sensors-24-04407-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d8c6/11244351/83b1ca534717/sensors-24-04407-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d8c6/11244351/9b072e4d59a2/sensors-24-04407-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d8c6/11244351/14a21323d9de/sensors-24-04407-g015.jpg

相似文献

1
An Obstacle Detection Method Based on Longitudinal Active Vision.一种基于纵向主动视觉的障碍物检测方法。
Sensors (Basel). 2024 Jul 7;24(13):4407. doi: 10.3390/s24134407.
2
Obstacle Detection Method Based on RSU and Vehicle Camera Fusion.基于 RSU 和车载相机融合的障碍物检测方法。
Sensors (Basel). 2023 May 19;23(10):4920. doi: 10.3390/s23104920.
3
VIDAR-Based Road-Surface-Pothole-Detection Method.基于VIDAR的路面坑洼检测方法
Sensors (Basel). 2023 Aug 28;23(17):7468. doi: 10.3390/s23177468.
4
A Review of Vision-Based On-Board Obstacle Detection and Distance Estimation in Railways.铁路中基于视觉的车载障碍物检测与距离估计综述
Sensors (Basel). 2021 May 15;21(10):3452. doi: 10.3390/s21103452.
5
Obstacle Avoidance of Multi-Sensor Intelligent Robot Based on Road Sign Detection.基于路标检测的多传感器智能机器人避障。
Sensors (Basel). 2021 Oct 12;21(20):6777. doi: 10.3390/s21206777.
6
Efficient Obstacle Detection and Tracking Using RGB-D Sensor Data in Dynamic Environments for Robotic Applications.利用动态环境中的 RGB-D 传感器数据进行机器人应用中的高效障碍物检测和跟踪。
Sensors (Basel). 2022 Aug 30;22(17):6537. doi: 10.3390/s22176537.
7
Adaptive Obstacle Detection for Mobile Robots in Urban Environments Using Downward-Looking 2D LiDAR.使用下视二维激光雷达的城市环境中移动机器人自适应障碍物检测
Sensors (Basel). 2018 May 29;18(6):1749. doi: 10.3390/s18061749.
8
Integrating millimeter wave radar with a monocular vision sensor for on-road obstacle detection applications.将毫米波雷达与单目视觉传感器集成，用于道路障碍物检测应用。
Sensors (Basel). 2011;11(9):8992-9008. doi: 10.3390/s110908992. Epub 2011 Sep 21.
9
Construction and Application Research of the Visual Image Obstacle Type Recognition Model Based on the Computer-Expanded Convolutional Neural Network.基于计算机扩展卷积神经网络的视觉图像障碍类型识别模型的构建与应用研究。
Comput Intell Neurosci. 2022 Sep 21;2022:3123448. doi: 10.1155/2022/3123448. eCollection 2022.
10
Research on Driving Obstacle Detection Technology in Foggy Weather Based on GCANet and Feature Fusion Training.基于 GCANet 和特征融合训练的雾天行车障碍物检测技术研究。
Sensors (Basel). 2023 Mar 4;23(5):2822. doi: 10.3390/s23052822.

本文引用的文献

1
Dynamic obstacle detection method based on U-V disparity and residual optical flow for autonomous driving.基于 U-V 视差和残差光流的自主驾驶动态障碍物检测方法。
Sci Rep. 2023 May 10;13(1):7630. doi: 10.1038/s41598-023-34777-6.
2
Research on Driving Obstacle Detection Technology in Foggy Weather Based on GCANet and Feature Fusion Training.基于 GCANet 和特征融合训练的雾天行车障碍物检测技术研究。
Sensors (Basel). 2023 Mar 4;23(5):2822. doi: 10.3390/s23052822.
3
ROSEBUD: A Deep Fluvial Segmentation Dataset for Monocular Vision-Based River Navigation and Obstacle Avoidance.
ROSEBUD：一种基于单目视觉的河流导航和避障用深度河流分割数据集。
Sensors (Basel). 2022 Jun 21;22(13):4681. doi: 10.3390/s22134681.