Birds eye view look-up table estimation with semantic segmentation
In this work, a study was carried out to estimate a look-up table (LUT) that converts a camera image plane to a birds eye view (BEV) plane using a single camera. The traditional camera pose estimation fields require high costs in researching and manufacturing autonomous vehicles for the future and m...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/153942 |
| _version_ | 1811691297673576448 |
|---|---|
| author | Lee, Dongkyu Tay, Wee Peng Kee, Seok-Cheol |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Lee, Dongkyu Tay, Wee Peng Kee, Seok-Cheol |
| author_sort | Lee, Dongkyu |
| collection | NTU |
| description | In this work, a study was carried out to estimate a look-up table (LUT) that converts a camera image plane to a birds eye view (BEV) plane using a single camera. The traditional camera pose estimation fields require high costs in researching and manufacturing autonomous vehicles for the future and may require pre-configured infra. This paper proposes an autonomous vehicle driving camera calibration system that is low cost and utilizes low infra. A network that outputs an image in the form of an LUT that converts the image into a BEV by estimating the camera pose under urban road driving conditions using a single camera was studied. We propose a network that predicts human-like poses from a single image. We collected synthetic data using a simulator, made BEV and LUT as ground truth, and utilized the proposed network and ground truth to train pose estimation function. In the progress, it predicts the pose by deciphering the semantic segmentation feature and increases its performance by attaching a layer that handles the overall direction of the network. The network outputs camera angle (roll/pitch/yaw) on the 3D coordinate system so that the user can monitor learning. Since the network's output is a LUT, there is no need for additional calculation, and real-time performance is improved. |
| first_indexed | 2024-10-01T06:17:39Z |
| format | Journal Article |
| id | ntu-10356/153942 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:17:39Z |
| publishDate | 2022 |
| record_format | dspace |
| spelling | ntu-10356/1539422022-01-10T08:42:59Z Birds eye view look-up table estimation with semantic segmentation Lee, Dongkyu Tay, Wee Peng Kee, Seok-Cheol School of Electrical and Electronic Engineering Engineering::Computer science and engineering Birds Eye View Look-Up Table In this work, a study was carried out to estimate a look-up table (LUT) that converts a camera image plane to a birds eye view (BEV) plane using a single camera. The traditional camera pose estimation fields require high costs in researching and manufacturing autonomous vehicles for the future and may require pre-configured infra. This paper proposes an autonomous vehicle driving camera calibration system that is low cost and utilizes low infra. A network that outputs an image in the form of an LUT that converts the image into a BEV by estimating the camera pose under urban road driving conditions using a single camera was studied. We propose a network that predicts human-like poses from a single image. We collected synthetic data using a simulator, made BEV and LUT as ground truth, and utilized the proposed network and ground truth to train pose estimation function. In the progress, it predicts the pose by deciphering the semantic segmentation feature and increases its performance by attaching a layer that handles the overall direction of the network. The network outputs camera angle (roll/pitch/yaw) on the 3D coordinate system so that the user can monitor learning. Since the network's output is a LUT, there is no need for additional calculation, and real-time performance is improved. Published version This research was supported by the MOTIE (Ministry of Trade, Industry, and Energy) in Korea, under the Fostering Global Talents for Innovative Growth Program (P0008751) supervised by the Korea Institute for Advancement of Technology (KIAT). This research was supported by the MSIT (Ministry of Science and ICT), Korea, under the Grand Information Technology Research Center support program (IITP-2021-2020-0-01462) supervised by the IITP (Institute for Information & communications Technology Planning & Evaluation. 2022-01-10T08:42:59Z 2022-01-10T08:42:59Z 2021 Journal Article Lee, D., Tay, W. P. & Kee, S. (2021). Birds eye view look-up table estimation with semantic segmentation. Applied Sciences, 11(17), 8047-. https://dx.doi.org/10.3390/app11178047 2076-3417 https://hdl.handle.net/10356/153942 10.3390/app11178047 2-s2.0-85114263699 17 11 8047 en Applied Sciences © 2021 The Author(s). Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). application/pdf |
| spellingShingle | Engineering::Computer science and engineering Birds Eye View Look-Up Table Lee, Dongkyu Tay, Wee Peng Kee, Seok-Cheol Birds eye view look-up table estimation with semantic segmentation |
| title | Birds eye view look-up table estimation with semantic segmentation |
| title_full | Birds eye view look-up table estimation with semantic segmentation |
| title_fullStr | Birds eye view look-up table estimation with semantic segmentation |
| title_full_unstemmed | Birds eye view look-up table estimation with semantic segmentation |
| title_short | Birds eye view look-up table estimation with semantic segmentation |
| title_sort | birds eye view look up table estimation with semantic segmentation |
| topic | Engineering::Computer science and engineering Birds Eye View Look-Up Table |
| url | https://hdl.handle.net/10356/153942 |
| work_keys_str_mv | AT leedongkyu birdseyeviewlookuptableestimationwithsemanticsegmentation AT tayweepeng birdseyeviewlookuptableestimationwithsemanticsegmentation AT keeseokcheol birdseyeviewlookuptableestimationwithsemanticsegmentation |