Small Object Detection (SOD) is an important machine vision topic because (i) a variety of real-world applications require object detection for distant objects and (ii) SOD is a challenging task due to the noisy, blurred, and less-informative image appearances of small objects. This paper proposes a new SOD dataset consisting of 39,070 images including 137,121 bird instances, which is called the Small Object Detection for Spotting Birds (SOD4SB) dataset. The detail of the challenge with the SOD4SB dataset is introduced in this paper. In total, 223 participants joined this challenge. This paper briefly introduces the award-winning methods. The dataset, the baseline code, and the website for evaluation on the public testset are publicly available.
@article{arxiv.2307.09143,
title = {MVA2023 Small Object Detection Challenge for Spotting Birds: Dataset, Methods, and Results},
author = {Yuki Kondo and Norimichi Ukita and Takayuki Yamaguchi and Hao-Yu Hou and Mu-Yi Shen and Chia-Chi Hsu and En-Ming Huang and Yu-Chen Huang and Yu-Cheng Xia and Chien-Yao Wang and Chun-Yi Lee and Da Huo and Marc A. Kastner and Tingwei Liu and Yasutomo Kawanishi and Takatsugu Hirayama and Takahiro Komamizu and Ichiro Ide and Yosuke Shinya and Xinyao Liu and Guang Liang and Syusuke Yasui},
journal= {arXiv preprint arXiv:2307.09143},
year = {2023}
}
Comments
This paper is included in the proceedings of the 18th International Conference on Machine Vision Applications (MVA2023). It will be officially published at a later date. Project page : https://www.mva-org.jp/mva2023/challenge