The 1st Tiny Object Detection Challenge: Methods and Results

Yu, Xuehui; Han, Zhenjun; Gong, Yuqi; Jan, Nan; Zhao, Jian; Ye, Qixiang; Chen, Jie; Feng, Yuan; Zhang, Bin; Wang, Xiaodi; Xin, Ying; Liu, Jingwei; Mao, Mingyuan; Xu, Sheng; Zhang, Baochang; Han, Shumin; Gao, Cheng; Tang, Wei; Jin, Lei; Hong, Mingbo; Yang, Yuchao; Li, Shuiwang; Luo, Haipeng; Zhao, Qijun

doi:10.1007/978-3-030-68238-5_23

Cited by 27 publications

(13 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite the great success of the generic object detection methods trained on ground-to-ground images, a huge performance drop is observed when they are directly applied to images captured by UAVs [36], [171]. Examples of the performance drop of state-of-the-art detectors are illustrated in Fig.…”

Section: Challenges For Aerial Human Detectionmentioning

confidence: 99%

“…The Cascade R-CNN [17] drops the performance by 50% in the aerial VisDrone [187] dataset compared with the ground-based COCO and Pascal VOC datasets [36]. The Faster R-CNN [117] also drops the performance by 30% in the aerial TinyPersons [173] dataset compared with the ground-based COCO and Pascal VOC datasets [171].…”

Section: Challenges For Aerial Human Detectionmentioning

confidence: 99%

“…The challenges "Vision meets drones" [36] including detection, tracking and crowd counting have been organized in the last four consecutive years in ECCV 2018, ICCV 2019, ECCV 2020 and ICCV 2021 using the VisDrone dataset. The TinyPerson challenges [171], organized in ICCV 2019 and ECCV 2020, focus on the persons from a very long distance with a wide view using the TinyPerson dataset. Details of these datasets can be found in Appendix § B.…”

Section: Datasets For Aerial Human Detectionmentioning

confidence: 99%

See 2 more Smart Citations

The State of Aerial Surveillance: A Survey

Nguyen¹,

Fookes²,

Sridharan³

et al. 2022

Preprint

View full text Add to dashboard Cite

The rapid emergence of airborne platforms and imaging sensors are enabling new forms of aerial surveillance due to their unprecedented advantages in scale, mobility, deployment and covert observation capabilities. This paper provides a comprehensive overview of human-centric aerial surveillance tasks from a computer vision and pattern recognition perspective. It aims to provide readers with an in-depth systematic review and technical analysis of the current state of aerial surveillance tasks using drones, UAVs and other airborne platforms. The main object of interest is humans, where single or multiple subjects are to be detected, identified, tracked, re-identified and have their behavior analyzed. More specifically, for each of these four tasks, we first discuss unique challenges in performing these tasks in an aerial setting compared to a ground-based setting. We then review and analyze the aerial datasets publicly available for each task, and delve deep into the approaches in the aerial literature and investigate how they presently address the aerial challenges. We conclude the paper with discussion on the missing gaps and open research questions to inform future research avenues.

show abstract

Section: Challenges For Aerial Human Detectionmentioning

confidence: 99%

Section: Challenges For Aerial Human Detectionmentioning

confidence: 99%

Section: Datasets For Aerial Human Detectionmentioning

confidence: 99%

See 1 more Smart Citation

The State of Aerial Surveillance: A Survey

Nguyen¹,

Fookes²,

Sridharan³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In a recent survey [42], the authors categorize numerous approaches to CNN-based object detection as one-stage [59] vs. two-stage [39] architectures, single-scale [59] vs. pyramid feature networks [38], and anchor-based [44] vs. anchor-free [19,6,80,18] tech- niques. These approaches focus on model refinement for a single detector, but their performance is often stifled by their model's capacity for realistic tasks [74].…”

Section: Introductionmentioning

confidence: 99%

“…As demonstrated by numerous engineering attempts and visual object detection contests [74], single detector approaches still do not perform well enough for real applications. It is our belief, however that detector ensemble approaches can push the boundaries of object detection performance to acceptable levels.…”

Section: Introductionmentioning

confidence: 99%

Probabilistic Ranking-Aware Ensembles for Enhanced Object Detections

Mao,

Zhang,

Doermann

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Model ensembles are becoming one of the most effective approaches for improving object detection performance already optimized for a single detector. Conventional methods directly fuse bounding boxes but typically fail to consider proposal qualities when combining detectors. This leads to a new problem of confidence discrepancy for the detector ensembles. The confidence has little effect on single detectors but significantly affects detector ensembles. To address this issue, we propose a novel ensemble called the Probabilistic Ranking Aware Ensemble (PRAE) that refines the confidence of bounding boxes from detectors. By simultaneously considering the category and the location on the same validation set, we obtain a more reliable confidence based on statistical probability. We can then rank the detected bounding boxes for assembly. We also introduce a bandit approach to address the confidence imbalance problem caused by the need to deal with different numbers of boxes at different confidence levels. We use our PRAE-based nonmaximum suppression (P-NMS) to replace the conventional NMS method in ensemble learning. Experiments on the PASCAL VOC and COCO2017 datasets demonstrate that our PRAE method consistently outperforms state-of-the-art methods by significant margins.

show abstract

A unified representation framework for the evaluation of Optical Music Recognition systems

Torras,

Biswas,

Fornés

2024

IJDAR

View full text Add to dashboard Cite

Modern-day Optical Music Recognition (OMR) is a fairly fragmented field. Most OMR approaches use datasets that are independent and incompatible between each other, making it difficult to both combine them and compare recognition systems built upon them. In this paper we identify the need of a common music representation language and propose the Music Tree Notation format, with the idea to construct a common endpoint for OMR research that allows coordination, reuse of technology and fair evaluation of community efforts. This format represents music as a set of primitives that group together into higher-abstraction nodes, a compromise between the expression of fully graph-based and sequential notation formats. We have also developed a specific set of OMR metrics and a typeset score dataset as a proof of concept of this idea.

show abstract

The 1st Tiny Object Detection Challenge: Methods and Results

Cited by 27 publications

References 15 publications

The State of Aerial Surveillance: A Survey

The State of Aerial Surveillance: A Survey

Probabilistic Ranking-Aware Ensembles for Enhanced Object Detections

A unified representation framework for the evaluation of Optical Music Recognition systems

Contact Info

Product

Resources

About