Saved in:
Bibliographic Details
Main Authors: Kondo, Yuki, Ukita, Norimichi, Kanayama, Riku, Yoshida, Yuki, Yamaguchi, Takayuki, Yu, Xiang, Liang, Guang, Liu, Xinyao, Wang, Guan-Zhang, Chu, Wei-Ta, Chuang, Bing-Cheng, Lee, Jia-Hua, Kuo, Pin-Tseng, Chu, I-Hsuan, Hsiao, Yi-Shein, Wu, Cheng-Han, Wu, Po-Yi, Tsou, Jui-Chien, Liu, Hsuan-Chi, Lee, Chun-Yi, Yang, Yuan-Fu, Shigematsu, Kosuke, Shin, Asuka, Tran, Ba
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.12832
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915395289481216
author Kondo, Yuki
Ukita, Norimichi
Kanayama, Riku
Yoshida, Yuki
Yamaguchi, Takayuki
Yu, Xiang
Liang, Guang
Liu, Xinyao
Wang, Guan-Zhang
Chu, Wei-Ta
Chuang, Bing-Cheng
Lee, Jia-Hua
Kuo, Pin-Tseng
Chu, I-Hsuan
Hsiao, Yi-Shein
Wu, Cheng-Han
Wu, Po-Yi
Tsou, Jui-Chien
Liu, Hsuan-Chi
Lee, Chun-Yi
Yang, Yuan-Fu
Shigematsu, Kosuke
Shin, Asuka
Tran, Ba
author_facet Kondo, Yuki
Ukita, Norimichi
Kanayama, Riku
Yoshida, Yuki
Yamaguchi, Takayuki
Yu, Xiang
Liang, Guang
Liu, Xinyao
Wang, Guan-Zhang
Chu, Wei-Ta
Chuang, Bing-Cheng
Lee, Jia-Hua
Kuo, Pin-Tseng
Chu, I-Hsuan
Hsiao, Yi-Shein
Wu, Cheng-Han
Wu, Po-Yi
Tsou, Jui-Chien
Liu, Hsuan-Chi
Lee, Chun-Yi
Yang, Yuan-Fu
Shigematsu, Kosuke
Shin, Asuka
Tran, Ba
contents Small Multi-Object Tracking (SMOT) is particularly challenging when targets occupy only a few dozen pixels, rendering detection and appearance-based association unreliable. Building on the success of the MVA2023 SOD4SB challenge, this paper introduces the SMOT4SB challenge, which leverages temporal information to address limitations of single-frame detection. Our three main contributions are: (1) the SMOT4SB dataset, consisting of 211 UAV video sequences with 108,192 annotated frames under diverse real-world conditions, designed to capture motion entanglement where both camera and targets move freely in 3D; (2) SO-HOTA, a novel metric combining Dot Distance with HOTA to mitigate the sensitivity of IoU-based metrics to small displacements; and (3) a competitive MVA2025 challenge with 78 participants and 308 submissions, where the winning method achieved a 5.1x improvement over the baseline. This work lays a foundation for advancing SMOT in UAV scenarios with applications in bird strike avoidance, agriculture, fisheries, and ecological monitoring.
format Preprint
id arxiv_https___arxiv_org_abs_2507_12832
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MVA 2025 Small Multi-Object Tracking for Spotting Birds Challenge: Dataset, Methods, and Results
Kondo, Yuki
Ukita, Norimichi
Kanayama, Riku
Yoshida, Yuki
Yamaguchi, Takayuki
Yu, Xiang
Liang, Guang
Liu, Xinyao
Wang, Guan-Zhang
Chu, Wei-Ta
Chuang, Bing-Cheng
Lee, Jia-Hua
Kuo, Pin-Tseng
Chu, I-Hsuan
Hsiao, Yi-Shein
Wu, Cheng-Han
Wu, Po-Yi
Tsou, Jui-Chien
Liu, Hsuan-Chi
Lee, Chun-Yi
Yang, Yuan-Fu
Shigematsu, Kosuke
Shin, Asuka
Tran, Ba
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Small Multi-Object Tracking (SMOT) is particularly challenging when targets occupy only a few dozen pixels, rendering detection and appearance-based association unreliable. Building on the success of the MVA2023 SOD4SB challenge, this paper introduces the SMOT4SB challenge, which leverages temporal information to address limitations of single-frame detection. Our three main contributions are: (1) the SMOT4SB dataset, consisting of 211 UAV video sequences with 108,192 annotated frames under diverse real-world conditions, designed to capture motion entanglement where both camera and targets move freely in 3D; (2) SO-HOTA, a novel metric combining Dot Distance with HOTA to mitigate the sensitivity of IoU-based metrics to small displacements; and (3) a competitive MVA2025 challenge with 78 participants and 308 submissions, where the winning method achieved a 5.1x improvement over the baseline. This work lays a foundation for advancing SMOT in UAV scenarios with applications in bird strike avoidance, agriculture, fisheries, and ecological monitoring.
title MVA 2025 Small Multi-Object Tracking for Spotting Birds Challenge: Dataset, Methods, and Results
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2507.12832