A Low Coupling and Lightweight Algorithm for Ship Detection in Optical Remote Sensing Images

• Published in: IEEE geoscience and remote sensing letters Vol. 19; pp. 1 - 5
• Main Authors: Deng, Guochao, Wang, Qin, Jiang, Jianfei, Hong, Qirun, Jing, Naifeng, Sheng, Weiguang, Mao, Zhigang
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Artificial neural networks; Complexity; Compression; Compression ratio; Constraint modelling; Convolution; Coupling; Couplings; Deconvolution; Detection; Detection algorithms; Low coupling; Marine vehicles; Methods; model compression; Modelling; Neural networks; Object recognition; optical remote sensing images; Performance enhancement; Quantization (signal); Remote sensing; ship detection; Taylor series; Training; Work platforms
• ISSN: 1545-598X; 1558-0571
• DOI: 10.1109/LGRS.2022.3188850

In recent years, many ship detection algorithms based on convolutional neural networks (CNNs) have been proposed to improve the performance of ship detection. However, with the increase in model complexity and size, it is challenging to deploy these models to resource-constrained edge platforms. In this letter, a low coupling algorithm that belongs to anchor-free methods is proposed for ship detection to reduce the model complexity and still obtain a competitive performance. The proposed low coupling network (LCNet) is easy to deploy and contributes to speeding up the inference and improving memory utilization. In addition, we propose a model compression process consisting of the quantization-aware training (QAT) method and a structural pruning method based on Taylor expansion, which can effectively reduce the model size according to hardware resource constraints. Comparative experimental results demonstrate that LCNet outperforms the state-of-the-art ship detection and natural object detection algorithms, with a 95.27% mAP and 88.91% F1 score on the HRSC2016 dataset. Our proposed model compression method also achieves a compression ratio of at least 80% with a negligible loss of performance.