Saved in:
Bibliographic Details
Main Authors: Wakai, Nobuhiko, Sato, Satoshi, Ishii, Yasunori, Yamashita, Takayoshi
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.14228
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914281975447552
author Wakai, Nobuhiko
Sato, Satoshi
Ishii, Yasunori
Yamashita, Takayoshi
author_facet Wakai, Nobuhiko
Sato, Satoshi
Ishii, Yasunori
Yamashita, Takayoshi
contents Person detection in overhead fisheye images is challenging due to person rotation and small persons. Prior work has mainly addressed person rotation, leaving the small-person problem underexplored. We remap fisheye images to equirectangular panoramas to handle rotation and exploit panoramic geometry to handle small persons more effectively. Conventional detection methods tend to favor larger persons because they dominate the attention maps, causing smaller persons to be missed. In hemispherical equirectangular panoramas, we find that apparent person height decreases approximately linearly with the vertical angle near the top of the image. Using this finding, we introduce panoramic distortion-aware tokenization to enhance the detection of small persons. This tokenization procedure divides panoramic features using self-similar figures that enable the determination of optimal divisions without gaps, and we leverage the maximum significance values in each tile of the token groups to preserve the significance areas of smaller persons. We propose a transformer-based person detection and localization method that combines panoramic-image remapping and the tokenization procedure. Extensive experiments demonstrated that our method outperforms conventional methods on large-scale datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2503_14228
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Panoramic Distortion-Aware Tokenization for Person Detection and Localization in Overhead Fisheye Images
Wakai, Nobuhiko
Sato, Satoshi
Ishii, Yasunori
Yamashita, Takayoshi
Computer Vision and Pattern Recognition
Artificial Intelligence
Person detection in overhead fisheye images is challenging due to person rotation and small persons. Prior work has mainly addressed person rotation, leaving the small-person problem underexplored. We remap fisheye images to equirectangular panoramas to handle rotation and exploit panoramic geometry to handle small persons more effectively. Conventional detection methods tend to favor larger persons because they dominate the attention maps, causing smaller persons to be missed. In hemispherical equirectangular panoramas, we find that apparent person height decreases approximately linearly with the vertical angle near the top of the image. Using this finding, we introduce panoramic distortion-aware tokenization to enhance the detection of small persons. This tokenization procedure divides panoramic features using self-similar figures that enable the determination of optimal divisions without gaps, and we leverage the maximum significance values in each tile of the token groups to preserve the significance areas of smaller persons. We propose a transformer-based person detection and localization method that combines panoramic-image remapping and the tokenization procedure. Extensive experiments demonstrated that our method outperforms conventional methods on large-scale datasets.
title Panoramic Distortion-Aware Tokenization for Person Detection and Localization in Overhead Fisheye Images
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2503.14228