Zou Changman, Jeon Wang-Su, Rhee Sang-Yong
Department of IT Convergence Engineering, University of Kyungnam, Changwon 51767, Republic of Korea.
College of Computer Science and Technology, Beihua University, Jilin 132013, China.
Sensors (Basel). 2024 May 18;24(10):3211. doi: 10.3390/s24103211.
This study focuses on advancing the field of remote sensing image target detection, addressing challenges such as small target detection, complex background handling, and dense target distribution. We propose solutions based on enhancing the YOLOv7 algorithm. Firstly, we improve the multi-scale feature enhancement (MFE) method of YOLOv7, enhancing its adaptability and precision in detecting small targets and complex backgrounds. Secondly, we design a modified YOLOv7 global information DP-MLP module to effectively capture and integrate global information, thereby improving target detection accuracy and robustness, especially in handling large-scale variations and complex scenes. Lastly, we explore a semi-supervised learning model (SSLM) target detection algorithm incorporating unlabeled data, leveraging information from unlabeled data to enhance the model's generalization ability and performance. Experimental results demonstrate that despite the outstanding performance of YOLOv7, the mean average precision (MAP) can still be improved by 1.9%. Specifically, under testing on the TGRS-HRRSD-Dataset, the MFE and DP-MLP models achieve MAP values of 93.4% and 93.1%, respectively. Across the NWPU VHR-10 dataset, the three models achieve MAP values of 93.1%, 92.1%, and 92.2%, respectively. Significant improvements are observed across various metrics compared to the original model. This study enhances the adaptability, accuracy, and generalization of remote sensing image object detection.
本研究致力于推动遥感图像目标检测领域的发展，解决诸如小目标检测、复杂背景处理和密集目标分布等挑战。我们基于增强YOLOv7算法提出了解决方案。首先，我们改进了YOLOv7的多尺度特征增强（MFE）方法，提高其在检测小目标和复杂背景时的适应性和精度。其次，我们设计了一个改进的YOLOv7全局信息DP-MLP模块，以有效捕获和整合全局信息，从而提高目标检测的准确性和鲁棒性，特别是在处理大规模变化和复杂场景时。最后，我们探索了一种结合未标记数据的半监督学习模型（SSLM）目标检测算法，利用未标记数据中的信息来增强模型的泛化能力和性能。实验结果表明，尽管YOLOv7性能出色，但平均精度均值（MAP）仍可提高1.9%。具体而言，在TGRS-HRRSD数据集上进行测试时，MFE和DP-MLP模型的MAP值分别达到93.4%和93.1%。在NWPU VHR-10数据集上，这三个模型的MAP值分别为93.1%、92.1%和92.2%。与原始模型相比，在各项指标上均有显著提升。本研究提高了遥感图像目标检测的适应性、准确性和泛化能力。
