INTUITIVE ESTIMATION OF SPEED USING MOTION AND MONOCULAR DEPTH INFORMATION
Advances in deep learning make monocular vision approaches attractive for the autonomous driving domain. This work investigates a method for estimating the speed of the ego-vehicle using state-of-the-art deep neural network based optical flow and single-view depth prediction models. Adopting a stra...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Babes-Bolyai University, Cluj-Napoca
2020-06-01
|
| Series: | Studia Universitatis Babes-Bolyai: Series Informatica |
| Subjects: | |
| Online Access: | http://193.231.18.162/index.php/subbinformatica/article/view/3840 |
| _version_ | 1797322241971585024 |
|---|---|
| author | Róbert Adrian RILL |
| author_facet | Róbert Adrian RILL |
| author_sort | Róbert Adrian RILL |
| collection | DOAJ |
| description |
Advances in deep learning make monocular vision approaches attractive for the autonomous driving domain. This work investigates a method for estimating the speed of the ego-vehicle using state-of-the-art deep neural network based optical flow and single-view depth prediction models. Adopting a straightforward intuitive approach and approximating a single scale factor, several application schemes of the deep networks are evaluated and meaningful conclusions are formulated, such as: combining depth information with optical flow improves speed estimation accuracy as opposed to using optical flow alone; the quality of the deep neural network results influences speed estimation performance; using the depth and optical flow data from smaller crops of wide images degrades performance. With these observations in mind, a RMSE of less than 1 m/s for ego-speed estimation was achieved on the KITTI benchmark using monocular images as input. Limitations and possible future directions are discussed as well.
|
| first_indexed | 2024-03-08T05:11:20Z |
| format | Article |
| id | doaj.art-96e8cd47feff404896a5489688e7db75 |
| institution | Directory Open Access Journal |
| issn | 2065-9601 |
| language | English |
| last_indexed | 2024-03-08T05:11:20Z |
| publishDate | 2020-06-01 |
| publisher | Babes-Bolyai University, Cluj-Napoca |
| record_format | Article |
| series | Studia Universitatis Babes-Bolyai: Series Informatica |
| spelling | doaj.art-96e8cd47feff404896a5489688e7db752024-02-07T10:03:38ZengBabes-Bolyai University, Cluj-NapocaStudia Universitatis Babes-Bolyai: Series Informatica2065-96012020-06-0165110.24193/subbi.2020.1.03INTUITIVE ESTIMATION OF SPEED USING MOTION AND MONOCULAR DEPTH INFORMATIONRóbert Adrian RILL0Faculty of Mathematics and Computer Science, Babe¸s-Bolyai University, Cluj-Napoca, Romania. Email address: rillrobert@cs.ubbcluj.ro Advances in deep learning make monocular vision approaches attractive for the autonomous driving domain. This work investigates a method for estimating the speed of the ego-vehicle using state-of-the-art deep neural network based optical flow and single-view depth prediction models. Adopting a straightforward intuitive approach and approximating a single scale factor, several application schemes of the deep networks are evaluated and meaningful conclusions are formulated, such as: combining depth information with optical flow improves speed estimation accuracy as opposed to using optical flow alone; the quality of the deep neural network results influences speed estimation performance; using the depth and optical flow data from smaller crops of wide images degrades performance. With these observations in mind, a RMSE of less than 1 m/s for ego-speed estimation was achieved on the KITTI benchmark using monocular images as input. Limitations and possible future directions are discussed as well. http://193.231.18.162/index.php/subbinformatica/article/view/3840monocular vision, speed estimation, deep learning, optical flow, single-view depth. |
| spellingShingle | Róbert Adrian RILL INTUITIVE ESTIMATION OF SPEED USING MOTION AND MONOCULAR DEPTH INFORMATION Studia Universitatis Babes-Bolyai: Series Informatica monocular vision, speed estimation, deep learning, optical flow, single-view depth. |
| title | INTUITIVE ESTIMATION OF SPEED USING MOTION AND MONOCULAR DEPTH INFORMATION |
| title_full | INTUITIVE ESTIMATION OF SPEED USING MOTION AND MONOCULAR DEPTH INFORMATION |
| title_fullStr | INTUITIVE ESTIMATION OF SPEED USING MOTION AND MONOCULAR DEPTH INFORMATION |
| title_full_unstemmed | INTUITIVE ESTIMATION OF SPEED USING MOTION AND MONOCULAR DEPTH INFORMATION |
| title_short | INTUITIVE ESTIMATION OF SPEED USING MOTION AND MONOCULAR DEPTH INFORMATION |
| title_sort | intuitive estimation of speed using motion and monocular depth information |
| topic | monocular vision, speed estimation, deep learning, optical flow, single-view depth. |
| url | http://193.231.18.162/index.php/subbinformatica/article/view/3840 |
| work_keys_str_mv | AT robertadrianrill intuitiveestimationofspeedusingmotionandmonoculardepthinformation |