Small-Scale Pedestrian Detection Based on Topological Line Localization and Temporal Feature Aggregation
Abstract
A critical issue in pedestrian detection is to detect small-scale objects that will introduce feeble contrast and motion blur in images and videos, which in our opinion should partially resort to deep-rooted annotation bias. Motivated by this, we propose a novel method integrated with somatic topological line localization (TLL) and temporal feature aggregation for detecting multi-scale pedestrians, which works particularly well with small-scale pedestrians that are relatively far from the camera. Moreover, a post-processing scheme based on Markov Ran- dom Field (MRF) is introduced to eliminate ambiguities in occlusion cases. Applying with these methodologies comprehensively, we achieve best detection performance on Caltech benchmark and improve performance of small-scale objects signicantly (miss rate decreases from 74.53% to 60.79%). Beyond this, we also achieve competitive performance on CityPersons dataset and show the existence of annotation bias in KITTI dataset.
Cite
Text
Song et al. "Small-Scale Pedestrian Detection Based on Topological Line Localization and Temporal Feature Aggregation." Proceedings of the European Conference on Computer Vision (ECCV), 2018. doi:10.1007/978-3-030-01234-2_33Markdown
[Song et al. "Small-Scale Pedestrian Detection Based on Topological Line Localization and Temporal Feature Aggregation." Proceedings of the European Conference on Computer Vision (ECCV), 2018.](https://mlanthology.org/eccv/2018/song2018eccv-smallscale/) doi:10.1007/978-3-030-01234-2_33BibTeX
@inproceedings{song2018eccv-smallscale,
title = {{Small-Scale Pedestrian Detection Based on Topological Line Localization and Temporal Feature Aggregation}},
author = {Song, Tao and Sun, Leiyu and Xie, Di and Sun, Haiming and Pu, Shiliang},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2018},
doi = {10.1007/978-3-030-01234-2_33},
url = {https://mlanthology.org/eccv/2018/song2018eccv-smallscale/}
}