A Lightweight Object Detection Algorithm for Remote Sensing Images Based on Attention Mechanism and YOLOv5s

• Published in: Remote sensing (Basel, Switzerland) Vol. 15; no. 9; p. 2429
• Main Authors: Liu, Pengfei, Wang, Qing, Zhang, Huan, Mi, Jing, Liu, Youchen
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.05.2023
• Subjects: Accuracy; Algorithms; Analysis; Artificial intelligence; Classification; Computational linguistics; content-aware reassembly of features; Datasets; DD-head; Deep learning; Head; Kitchenware; Language processing; Lightweight; Localization; Modules; Natural language interfaces; Neural networks; object detection; Object recognition; Remote sensing; Semantics; Sensors; SPPCSPG; Target detection; YOLOv5s
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs15092429

The specific characteristics of remote sensing images, such as large directional variations, large target sizes, and dense target distributions, make target detection a challenging task. To improve the detection performance of models while ensuring real-time detection, this paper proposes a lightweight object detection algorithm based on an attention mechanism and YOLOv5s. Firstly, a depthwise-decoupled head (DD-head) module and spatial pyramid pooling cross-stage partial GSConv (SPPCSPG) module were constructed to replace the coupled head and the spatial pyramid pooling-fast (SPPF) module of YOLOv5s. A shuffle attention (SA) mechanism was introduced in the head structure to enhance spatial attention and reconstruct channel attention. A content-aware reassembly of features (CARAFE) module was introduced in the up-sampling operation to reassemble feature points with similar semantic information. In the neck structure, a GSConv module was introduced to maintain detection accuracy while reducing the number of parameters. Experimental results on remote sensing datasets, RSOD and DIOR, showed an improvement of 1.4% and 1.2% in mean average precision accuracy compared with the original YOLOv5s algorithm. Moreover, the algorithm was also tested on conventional object detection datasets, PASCAL VOC and MS COCO, which showed an improvement of 1.4% and 3.1% in mean average precision accuracy. Therefore, the experiments showed that the constructed algorithm not only outperformed the original network on remote sensing images but also performed better than the original network on conventional object detection images.