期刊
SENSORS
卷 21, 期 16, 页码 -出版社
MDPI
DOI: 10.3390/s21165460
关键词
remote sensing image; object detection; anchor configurations; differential evolution; YOLO; attention module
资金
- National Key Research and Development Program of China [2019YFB2204200]
- Beijing Natural Science Foundation [4202063]
- Fundamental Research Funds for the Central Universities [2020JBM020]
- BJTUKwai Industry-University-Research Cooperation Project
The study introduces a lightweight object detection method for remote sensing images, achieving high-speed and high-accuracy detection through efficient channel attention layers and differential evolution algorithm. Experimental results show that the network outperforms existing lightweight models in accuracy and performs well on embedded boards.
Deep learning-based object detection in remote sensing images is an important yet challenging task due to a series of difficulties, such as complex geometry scene, dense target quantity, and large variant in object distributions and scales. Moreover, algorithm designers also have to make a trade-off between model's complexity and accuracy to meet the real-world deployment requirements. To deal with these challenges, we proposed a lightweight YOLO-like object detector with the ability to detect objects in remote sensing images with high speed and high accuracy. The detector is constructed with efficient channel attention layers to improve the channel information sensitivity. Differential evolution was also developed to automatically find the optimal anchor configurations to address issue of large variant in object scales. Comprehensive experiment results show that the proposed network outperforms state-of-the-art lightweight models by 5.13% and 3.58% in accuracy on the RSOD and DIOR dataset, respectively. The deployed model on an NVIDIA Jetson Xavier NX embedded board can achieve a detection speed of 58 FPS with less than 10W power consumption, which makes the proposed detector very suitable for low-cost low-power remote sensing application scenarios.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据