| 张堃,白浚哲,欧阳鹏,徐浚哲,张培建,费敏锐,华亮.基于MFFISNet的低空地物识别方法研究[J].电子测量与仪器学报,2026,40(3):58-70 |
| 基于MFFISNet的低空地物识别方法研究 |
| Research on low-altitude object recognition method based on MFFISNet |
| |
| DOI： |
| 中文关键词: 实例分割 多模态特征融合 卷积神经网络 无人机图像 地理空间物体 |
| 英文关键词:instance segmentation multimodal feature fusion CNNs UAV imagery geospatial object recognition |
| 基金项目:国家自然科学基金（62473216）项目资助 |
|
|
| Author | Institution |
| Zhang Kun | 1.School of Electrical and Automation Engineering, Nantong University, Nantong 226019, China; 2.Nantong Key Laboratory of
Intelligent Control and Intelligent Computing,Nantong 226019, China |
| Bai Junzhe | School of Electrical and Automation Engineering, Nantong University, Nantong 226019, China |
| Ouyang Peng | School of Electrical and Automation Engineering, Nantong University, Nantong 226019, China |
| Xu Junzhe | Nantong Electric Power Design Institute Co., Ltd.,
Nantong 226019, China |
| Zhang Peijian | School of Electrical and Automation Engineering, Nantong University, Nantong 226019, China |
| Fei Minrui | School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 210053, China |
| Hua Liang | School of Electrical and Automation Engineering, Nantong University, Nantong 226019, China |
|
| 摘要点击次数: 329 |
| 全文下载次数: 292 |
| 中文摘要: |
| 随着无人机航拍技术的快速发展，低空场景中对基础设施等目标的精确识别需求日益增强。然而，传统目标检测与语义分割方法在边界刻画及同类实例区分方面仍存在不足。针对此问题，提出一种改进的多模态特征融合实例分割网络，以提升无人机遥感影像中目标分割的精细化程度与鲁棒性。所得方法的创新点：构建双路径输入结构，同时利用RGB影像与DSM信息，丰富多模态特征表达；面向DSM分支引入HWF-LM与DMSCA，显著增强模型对高程与结构信息的表征能力；提出FGCA机制，实现跨模态特征的高效融合，从而提升复杂场景下的实例分割精度。在Drone-OrthoSeg数据集上，所提方法的边界框mAP和掩模mAP分别达到42.63%和42.69%；在NWPU VHR-10数据集上分别为77.86%和72.59%；在雾天海上场景的FoggyShipInsseg数据集上亦取得63.86%与59.69%的良好表现。实验结果表明，该方法在准确性与鲁棒性方面均优于现有先进方法，可为低空场景下的基础设施自动化检测和测量提供高效可靠的技术支持。 |
| 英文摘要: |
| With the rapid development of drone aerial photography technology, the demand for precise recognition of targets such as infrastructure in low-altitude scenarios has been increasingly growing. However, traditional object detection and semantic segmentation methods still have shortcomings in boundary delineation and distinguishing between similar instances. To address these issues, this paper proposes an improved multimodal feature fusion instance segmentation network, MFFISNet, to enhance the fineness and robustness of target segmentation in drone remote sensing images. The method in this paper includes three main innovations: a dual-path input structure is constructed, utilizing both RGB images and DSM information to enrich multimodal feature representation; for the DSM branch, HWF-LM and DMSCA are introduced, significantly enhancing the model’s ability to represent elevation and structural information; FGCA mechanism is proposed to achieve efficient fusion of cross-modal features, thereby improving instance segmentation accuracy in complex scenarios. On the Drone-OrthoSeg dataset, MFFISNet achieved a bounding box mAP of 42.63% and mask mAP of 42.69%; on the NWPU VHR-10 dataset, the results were 77.86% and 72.59%, respectively; and on the foggy maritime scenarios of the FoggyShipInsseg dataset, it also achieved good performance of 63.86% and 59.69%. Experimental results indicate that the proposed method outperforms existing advanced methods in both accuracy and robustness, providing efficient and reliable technical support for automated detection and measurement of infrastructure in low-altitude scenarios. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
