Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2402.18320 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916199252623360 |
|---|---|
| author | Li, Bing Zhang, Dong Huang, Cheng Xian, Yun Li, Ming Lee, Dah-Jye |
| author_facet | Li, Bing Zhang, Dong Huang, Cheng Xian, Yun Li, Ming Lee, Dah-Jye |
| contents | Camera with a fisheye or ultra-wide lens covers a wide field of view that cannot be modeled by the perspective projection. Serious fisheye lens distortion in the peripheral region of the image leads to degraded performance of the existing head pose estimation models trained on undistorted images. This paper presents a new approach for head pose estimation that uses the knowledge of head location in the image to reduce the negative effect of fisheye distortion. We develop an end-to-end convolutional neural network to estimate the head pose with the multi-task learning of head pose and head location. Our proposed network estimates the head pose directly from the fisheye image without the operation of rectification or calibration. We also created a fisheye-distorted version of the three popular head pose estimation datasets, BIWI, 300W-LP, and AFLW2000 for our experiments. Experiments results show that our network remarkably improves the accuracy of head pose estimation compared with other state-of-the-art one-stage and two-stage methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_18320 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Location-guided Head Pose Estimation for Fisheye Image Li, Bing Zhang, Dong Huang, Cheng Xian, Yun Li, Ming Lee, Dah-Jye Computer Vision and Pattern Recognition Artificial Intelligence Camera with a fisheye or ultra-wide lens covers a wide field of view that cannot be modeled by the perspective projection. Serious fisheye lens distortion in the peripheral region of the image leads to degraded performance of the existing head pose estimation models trained on undistorted images. This paper presents a new approach for head pose estimation that uses the knowledge of head location in the image to reduce the negative effect of fisheye distortion. We develop an end-to-end convolutional neural network to estimate the head pose with the multi-task learning of head pose and head location. Our proposed network estimates the head pose directly from the fisheye image without the operation of rectification or calibration. We also created a fisheye-distorted version of the three popular head pose estimation datasets, BIWI, 300W-LP, and AFLW2000 for our experiments. Experiments results show that our network remarkably improves the accuracy of head pose estimation compared with other state-of-the-art one-stage and two-stage methods. |
| title | Location-guided Head Pose Estimation for Fisheye Image |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2402.18320 |