Real-time Estimation of Road Surfaces using Fast Monocular Depth Estimation and Normal Vector Clustering
Estimating a road surface or planes for applying AR(Augmented Reality) or an autonomous vehicle using a camera requires significant computation. Vision sensors have lower accuracy in distance measurement than other types of sensor, and have the difficulty that additional algorithms for estimating da...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Politeknik Negeri Padang
2021-09-01
|
| Series: | JOIV: International Journal on Informatics Visualization |
| Subjects: | |
| Online Access: | https://joiv.org/index.php/joiv/article/view/641 |
| _version_ | 1811159789593427968 |
|---|---|
| author | Chuho Yi Jungwon Cho |
| author_facet | Chuho Yi Jungwon Cho |
| author_sort | Chuho Yi |
| collection | DOAJ |
| description | Estimating a road surface or planes for applying AR(Augmented Reality) or an autonomous vehicle using a camera requires significant computation. Vision sensors have lower accuracy in distance measurement than other types of sensor, and have the difficulty that additional algorithms for estimating data must be included. However, using a camera has the advantage of being able to extract various information such as weather conditions, sign information, and road markings that are difficult to measure with other sensors. Various methods differing in sensor type and configuration have been applied. Many of the existing studies had generally researched by performing the depth estimation after the feature extraction. However, recent studies have suggested using deep learning to skip multiple processes and use a single DNN(Deep Neural Network). Also, a method using a limited single camera instead of a method using a plurality of sensors has been proposed. This paper presents a single-camera method that performs quickly and efficiently by employing a DNN to extract distance information using a single camera, and proposes a modified method for using a depth map to obtain real-time surface characteristics. First, a DNN is used to estimate the depth map, and then for quick operation, normal vector that can connect similar planes to depth is calculated, and a clustering method that can be connected is provided. An experiment is used to show the validity of our method, and to evaluate the calculation time. |
| first_indexed | 2024-04-10T05:47:06Z |
| format | Article |
| id | doaj.art-08e35043b1a34685811b7fcab59af3ba |
| institution | Directory Open Access Journal |
| issn | 2549-9610 2549-9904 |
| language | English |
| last_indexed | 2024-04-10T05:47:06Z |
| publishDate | 2021-09-01 |
| publisher | Politeknik Negeri Padang |
| record_format | Article |
| series | JOIV: International Journal on Informatics Visualization |
| spelling | doaj.art-08e35043b1a34685811b7fcab59af3ba2023-03-05T10:30:14ZengPoliteknik Negeri PadangJOIV: International Journal on Informatics Visualization2549-96102549-99042021-09-015320621110.30630/joiv.5.3.641269Real-time Estimation of Road Surfaces using Fast Monocular Depth Estimation and Normal Vector ClusteringChuho Yi0Jungwon Cho1Department of Software Convergence, Hanyang Women's University, Seoul 04763, South KoreaDepartment of Computer Education, Jeju National University, Jeju 63243, South KoreaEstimating a road surface or planes for applying AR(Augmented Reality) or an autonomous vehicle using a camera requires significant computation. Vision sensors have lower accuracy in distance measurement than other types of sensor, and have the difficulty that additional algorithms for estimating data must be included. However, using a camera has the advantage of being able to extract various information such as weather conditions, sign information, and road markings that are difficult to measure with other sensors. Various methods differing in sensor type and configuration have been applied. Many of the existing studies had generally researched by performing the depth estimation after the feature extraction. However, recent studies have suggested using deep learning to skip multiple processes and use a single DNN(Deep Neural Network). Also, a method using a limited single camera instead of a method using a plurality of sensors has been proposed. This paper presents a single-camera method that performs quickly and efficiently by employing a DNN to extract distance information using a single camera, and proposes a modified method for using a depth map to obtain real-time surface characteristics. First, a DNN is used to estimate the depth map, and then for quick operation, normal vector that can connect similar planes to depth is calculated, and a clustering method that can be connected is provided. An experiment is used to show the validity of our method, and to evaluate the calculation time.https://joiv.org/index.php/joiv/article/view/641real-time estimationdeep neural networkroad surfacesfast monocular depth estimationnormal vector clustering. |
| spellingShingle | Chuho Yi Jungwon Cho Real-time Estimation of Road Surfaces using Fast Monocular Depth Estimation and Normal Vector Clustering JOIV: International Journal on Informatics Visualization real-time estimation deep neural network road surfaces fast monocular depth estimation normal vector clustering. |
| title | Real-time Estimation of Road Surfaces using Fast Monocular Depth Estimation and Normal Vector Clustering |
| title_full | Real-time Estimation of Road Surfaces using Fast Monocular Depth Estimation and Normal Vector Clustering |
| title_fullStr | Real-time Estimation of Road Surfaces using Fast Monocular Depth Estimation and Normal Vector Clustering |
| title_full_unstemmed | Real-time Estimation of Road Surfaces using Fast Monocular Depth Estimation and Normal Vector Clustering |
| title_short | Real-time Estimation of Road Surfaces using Fast Monocular Depth Estimation and Normal Vector Clustering |
| title_sort | real time estimation of road surfaces using fast monocular depth estimation and normal vector clustering |
| topic | real-time estimation deep neural network road surfaces fast monocular depth estimation normal vector clustering. |
| url | https://joiv.org/index.php/joiv/article/view/641 |
| work_keys_str_mv | AT chuhoyi realtimeestimationofroadsurfacesusingfastmonoculardepthestimationandnormalvectorclustering AT jungwoncho realtimeestimationofroadsurfacesusingfastmonoculardepthestimationandnormalvectorclustering |