Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2401.07370 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916091564916736 |
|---|---|
| author | Seib, Viktor Roosen, Malte Germann, Ida Wirtz, Stefan Paulus, Dietrich |
| author_facet | Seib, Viktor Roosen, Malte Germann, Ida Wirtz, Stefan Paulus, Dietrich |
| contents | Creating annotated datasets demands a substantial amount of manual effort. In this proof-of-concept work, we address this issue by proposing a novel image generation pipeline. The pipeline consists of three distinct generative adversarial networks (previously published), combined in a novel way to augment a dataset for pedestrian detection. Despite the fact that the generated images are not always visually pleasant to the human eye, our detection benchmark reveals that the results substantially surpass the baseline. The presented proof-of-concept work was done in 2020 and is now published as a technical report after a three years retention period. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_07370 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Generation of Synthetic Images for Pedestrian Detection Using a Sequence of GANs Seib, Viktor Roosen, Malte Germann, Ida Wirtz, Stefan Paulus, Dietrich Computer Vision and Pattern Recognition Creating annotated datasets demands a substantial amount of manual effort. In this proof-of-concept work, we address this issue by proposing a novel image generation pipeline. The pipeline consists of three distinct generative adversarial networks (previously published), combined in a novel way to augment a dataset for pedestrian detection. Despite the fact that the generated images are not always visually pleasant to the human eye, our detection benchmark reveals that the results substantially surpass the baseline. The presented proof-of-concept work was done in 2020 and is now published as a technical report after a three years retention period. |
| title | Generation of Synthetic Images for Pedestrian Detection Using a Sequence of GANs |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.07370 |