Scale Optimization Using Evolutionary Reinforcement Learning for Object Detection on Drone Imagery
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (1) · 410-418
DOI: 10.1609/aaai.v38i1.27795 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Jialu Zhang und 8 weiteren Autor:innen. Die Arbeit wurde bisher 19-mal zitiert (Crossref).
Abstract (Originalsprache)
Object detection in aerial imagery presents a significant challenge due to large scale variations among objects. This paper proposes an evolutionary reinforcement learning agent, integrated within a coarse-to-fine object detection framework, to optimize the scale for more effective detection of objects in such images. Specifically, a set of patches potentially containing objects are first generated. A set of rewards measuring the localization accuracy, the accuracy of predicted labels, and the scale consistency among nearby patches are designed in the agent to guide the scale optimization. The proposed scale-consistency reward ensures similar scales for neighboring objects of the same category. Furthermore, a spatial-semantic attention mechanism is designed to exploit the spatial semantic relations between patches. The agent employs the proximal policy optimization strategy in conjunction with the evolutionary strategy, effectively utilizing both the current patch status and historical experience embedded in the agent. The proposed model is compared with state-of-the-art methods on two benchmark datasets for object detection on drone imagery. It significantly outperforms all the compared methods. Code is available at https://github.com/UNNC-CV/EvOD/.
Zitieren
APA
Zhang, J., Yang, X., He, W., Ren, J., Zhang, Q., Zhao, Y., Bai, R., He, X., & Liu, J. (2024). Scale Optimization Using Evolutionary Reinforcement Learning for Object Detection on Drone Imagery. Proceedings of the AAAI Conference on Artificial Intelligence, 38(1), 410-418. https://doi.org/10.1609/aaai.v38i1.27795
Vancouver
Zhang J, Yang X, He W, Ren J, Zhang Q, Zhao Y, et al. Scale Optimization Using Evolutionary Reinforcement Learning for Object Detection on Drone Imagery. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(1):410-418. doi:10.1609/aaai.v38i1.27795
BibTeX
@article{Zhang2024,
author = {Zhang, Jialu and Yang, Xiaoying and He, Wentao and Ren, Jianfeng and Zhang, Qian and Zhao, Yitian and Bai, Ruibin and He, Xiangjian and Liu, Jiang},
title = {Scale Optimization Using Evolutionary Reinforcement Learning for Object Detection on Drone Imagery},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {1},
pages = {410--418},
doi = {10.1609/aaai.v38i1.27795}
}
EUVIMED