OmniSCV: An Omnidirectional Synthetic Image Generator for Computer Vision
Omnidirectional and 360° images are becoming widespread in industry and in consumer society, causing omnidirectional computer vision to gain attention. Their wide field of view allows the gathering of a great amount of information about the environment from only an image. However, the distortion of...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/7/2066 |
| _version_ | 1797571285370273792 |
|---|---|
| author | Bruno Berenguel-Baeta Jesus Bermudez-Cameo Jose J. Guerrero |
| author_facet | Bruno Berenguel-Baeta Jesus Bermudez-Cameo Jose J. Guerrero |
| author_sort | Bruno Berenguel-Baeta |
| collection | DOAJ |
| description | Omnidirectional and 360° images are becoming widespread in industry and in consumer society, causing omnidirectional computer vision to gain attention. Their wide field of view allows the gathering of a great amount of information about the environment from only an image. However, the distortion of these images requires the development of specific algorithms for their treatment and interpretation. Moreover, a high number of images is essential for the correct training of computer vision algorithms based on learning. In this paper, we present a tool for generating datasets of omnidirectional images with semantic and depth information. These images are synthesized from a set of captures that are acquired in a realistic virtual environment for Unreal Engine 4 through an interface plugin. We gather a variety of well-known projection models such as equirectangular and cylindrical panoramas, different fish-eye lenses, catadioptric systems, and empiric models. Furthermore, we include in our tool photorealistic non-central-projection systems as non-central panoramas and non-central catadioptric systems. As far as we know, this is the first reported tool for generating photorealistic non-central images in the literature. Moreover, since the omnidirectional images are made virtually, we provide pixel-wise information about semantics and depth as well as perfect knowledge of the calibration parameters of the cameras. This allows the creation of ground-truth information with pixel precision for training learning algorithms and testing 3D vision approaches. To validate the proposed tool, different computer vision algorithms are tested as line extractions from dioptric and catadioptric central images, 3D Layout recovery and SLAM using equirectangular panoramas, and 3D reconstruction from non-central panoramas. |
| first_indexed | 2024-03-10T20:38:10Z |
| format | Article |
| id | doaj.art-cd2ef450c46944efbc39f816f00386f1 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T20:38:10Z |
| publishDate | 2020-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-cd2ef450c46944efbc39f816f00386f12023-11-19T20:53:39ZengMDPI AGSensors1424-82202020-04-01207206610.3390/s20072066OmniSCV: An Omnidirectional Synthetic Image Generator for Computer VisionBruno Berenguel-Baeta0Jesus Bermudez-Cameo1Jose J. Guerrero2Instituto de Investigación en Ingeniería de Aragón, Universidad de Zaragoza, 50018 Zaragoza, SpainInstituto de Investigación en Ingeniería de Aragón, Universidad de Zaragoza, 50018 Zaragoza, SpainInstituto de Investigación en Ingeniería de Aragón, Universidad de Zaragoza, 50018 Zaragoza, SpainOmnidirectional and 360° images are becoming widespread in industry and in consumer society, causing omnidirectional computer vision to gain attention. Their wide field of view allows the gathering of a great amount of information about the environment from only an image. However, the distortion of these images requires the development of specific algorithms for their treatment and interpretation. Moreover, a high number of images is essential for the correct training of computer vision algorithms based on learning. In this paper, we present a tool for generating datasets of omnidirectional images with semantic and depth information. These images are synthesized from a set of captures that are acquired in a realistic virtual environment for Unreal Engine 4 through an interface plugin. We gather a variety of well-known projection models such as equirectangular and cylindrical panoramas, different fish-eye lenses, catadioptric systems, and empiric models. Furthermore, we include in our tool photorealistic non-central-projection systems as non-central panoramas and non-central catadioptric systems. As far as we know, this is the first reported tool for generating photorealistic non-central images in the literature. Moreover, since the omnidirectional images are made virtually, we provide pixel-wise information about semantics and depth as well as perfect knowledge of the calibration parameters of the cameras. This allows the creation of ground-truth information with pixel precision for training learning algorithms and testing 3D vision approaches. To validate the proposed tool, different computer vision algorithms are tested as line extractions from dioptric and catadioptric central images, 3D Layout recovery and SLAM using equirectangular panoramas, and 3D reconstruction from non-central panoramas.https://www.mdpi.com/1424-8220/20/7/2066computer visionomnidirectional camerasvirtual environmentdeep learningnon-central systemsimage generator |
| spellingShingle | Bruno Berenguel-Baeta Jesus Bermudez-Cameo Jose J. Guerrero OmniSCV: An Omnidirectional Synthetic Image Generator for Computer Vision Sensors computer vision omnidirectional cameras virtual environment deep learning non-central systems image generator |
| title | OmniSCV: An Omnidirectional Synthetic Image Generator for Computer Vision |
| title_full | OmniSCV: An Omnidirectional Synthetic Image Generator for Computer Vision |
| title_fullStr | OmniSCV: An Omnidirectional Synthetic Image Generator for Computer Vision |
| title_full_unstemmed | OmniSCV: An Omnidirectional Synthetic Image Generator for Computer Vision |
| title_short | OmniSCV: An Omnidirectional Synthetic Image Generator for Computer Vision |
| title_sort | omniscv an omnidirectional synthetic image generator for computer vision |
| topic | computer vision omnidirectional cameras virtual environment deep learning non-central systems image generator |
| url | https://www.mdpi.com/1424-8220/20/7/2066 |
| work_keys_str_mv | AT brunoberenguelbaeta omniscvanomnidirectionalsyntheticimagegeneratorforcomputervision AT jesusbermudezcameo omniscvanomnidirectionalsyntheticimagegeneratorforcomputervision AT josejguerrero omniscvanomnidirectionalsyntheticimagegeneratorforcomputervision |