首页 >  , Vol. , Issue () : -

摘要

全文摘要次数: 111 全文下载次数: 286
引用本文:

DOI:

10.11834/jrs.20210001

收稿日期:

2020-01-01

修改日期:

2020-07-24

PDF Free   EndNote   BibTeX
基于场景子区域多标签学习的露天煤矿区场景识别
摘要:

(目的)露天煤矿区作为环境治理的主要对象需要对其进行监管,随着遥感技术的发展,基于高分辨率遥感影像对露天煤矿区场景进行识别成为可能。对露天煤矿区场景的子区域进行特征学习和识别,针对单标签学习算法在场景子区域识别中识别率较低的问题,本文将多标签学习策略和地理学第一定律相结合,提出一种基于场景子区域多标签学习的场景识别算法。(方法)为了使露天煤矿区场景与其周边场景进行区分,设置了6类矿区标签和7类非矿区标签,将露天煤矿区场景和非露天煤矿区场景的子区域都标注13类标签构成多标签数据集。用基于多标签学习的Inception_v3模型训练多标签数据集,对输入的遥感影像划分为相同大小的子区域并进行多标签分类。为了对子区域包含的多标签预测结果进行分析从而识别出属于露天煤矿区场景的子区域,设计了一种场景子区域判定算法,对包含矿区标签的子区域利用矿区标签的标签相关性和标签完整性进行判定,识别出的子区域构成露天煤矿区场景。(结果)实验结果表明:在露天煤矿区场景子区域识别中,本文算法的F1分数为0.857,与单标签学习算法相比,F1分数最高提高了8个百分点;在研究区遥感影像上对露天煤矿区场景进行识别,本文算法的识别结果接近真值。(结论)综上,本文算法能够自动学习并提取子区域内多类标签的有效特征,在露天煤矿区场景中可以取得良好的识别效果。

Scene recognition of opencast coal mine areas based on scene sub-region multi-label learning
Abstract:

Objective: With the development of remote sensing technology, high-resolution remote sensing images become available to scene recog-nition of opencast coal mine areas, which is conducive to the supervision of opencast coal mine areas for environmental governance. The scene is divided into multiple sub-regions for feature learning and recognition. Aiming at the poor performance of sub-region recognition based on single-label learning, this paper combines a multi-label learning strategy with the first law of geography to propose a scene recognition algorithm based on scene sub-region multi-label learning. Method: In order to distinguish the scene of opencast coal mine areas from its surrounding scene, 6 types of mining tags and 7 non-mining tags are set. The sub-regions, cropped from the scene of opencast coal mine areas and its surrounding scene, are labeled with 13 types of tags to form a multi-label dataset. Train the dataset with the Inception_v3 based on multi-label learning. The input remote sensing images are divided into sub-regions of the same size, and multi-label classification is performed on the sub-regions with the trained model. In order to recognize the sub-regions belonging to the scene of the opencast coal mine areas according to the multi-label classification results, a scene sub-region determination algorithm is introduced. Using the label correlation and the label integrity of the mining tags to determine whether the sub-region, containing the mining tags, belongs to the scene of the opencast coal mine areas. And the recognized sub-regions constitute the scene of the opencast coal mine areas. Result: The results show that, in scene sub-region recognition of opencast coal mine areas, compared with single-label learning al-gorithms, the F1-score of the proposed method, 0.857, is increased by up to 8 percentage points. On the remote sensing image of the study area, the recognition results of proposed method in scene recognition of opencast coal mine areas are close to true values. Conclusion: For a large number of multi-class features included in the scene of opencast coal mine areas on high-resolution remote sensing images, this paper proposes a scene recognition algorithm based on scene sub-region multi-label learning, which can automatically learn and extract the effective features of multi-class tags in sub-regions, and performs well in scene recognition tasks of opencast coal mine areas, proving the effectiveness of the proposed method.

本文暂时没有被引用!

欢迎关注学报微信

遥感学报交流群 分享按钮