融合多尺度MLP和边缘细化的遥感影像建筑物提取

doi:10.3778/j.issn.1002-8331.2308-0032

摘要/Abstract

摘要： 针对高分辨率遥感影像中建筑物尺度变化大、干扰因素多和被遮挡等问题导致的错误分割，提出一种融合多尺度MLP和边缘细化的遥感影像建筑物提取方法。结合局部多层感知器与全局多层感知器提高模型对于影像中不同区域的理解能力和感知能力，弱化背景无关元素的干扰；通过获取不同层次特征图的边缘增强图，实现建筑物轮廓的精细化；设计一个对输出预测图进行特征级深度监督模块来兼顾定位精度和边缘精度，进一步提高分割效果。实验结果表明，所提算法在WHU和Inria Aerial Image Labeling数据集上的precision、recall、F1-score和IoU分别达到了96.18%、95.74%、95.96%、91.82%与91.37%、89.66%、90.51%、82.79%，对比其他相关算法，精度在不同程度提升的同时也保持了较低的参数量和计算量，为准确、快速地提取光学高分辨率遥感影像中的建筑物信息提供了有力支持。

关键词: 多层感知器, 建筑物分割, 多尺度MLP, 边缘细化

Abstract: Aiming at the wrong segmentation caused by the large scale change of buildings, multiple confounding and occlusion in high-resolution remote sensing images, a building extraction method based on multi-scale MLP and edge thinning is proposed. Firstly, the local multilayer perceptron and the global multilayer perceptron are combined to improve the model’s ability to understand and perceive different areas in the image, and weaken the interference of background independent elements. Then, by obtaining edge enhancement images of different level feature maps, the refinement of building contours is achieved. Finally, a feature level deep supervision module is designed to balance the positioning accuracy and edge accuracy of the output prediction map, further improving the segmentation effect. The experimental results show that the proposed algorithm achieves 96.18%, 95.74%, 95.96%, 91.82% and 91.37%, 89.66%, 90.51%, and 82.79% precicion, recall, F1 score, and IoU, respectively, on the WHU and Inria Aerial Image Labeling datasets. Compared to other related algorithms, it not only improves accuracy to varying degrees but also maintains a lower parameter volume and computational load, providing robust support for the accurate and rapid extraction of building information from optical high-resolution remote sensing images.

Key words: multilayer perceptron, building segmentation, multi-scale MLP, edge thinning

王杰, 蒋伏松. 融合多尺度MLP和边缘细化的遥感影像建筑物提取[J]. 计算机工程与应用, 2024, 60(23): 198-208.

WANG Jie, JIANG Fusong. Building Extraction from Remote Sensing Images by Fusing Multi-Scale MLP and Edge Refinement[J]. Computer Engineering and Applications, 2024, 60(23): 198-208.

参考文献

[1] 袁意映. 基于深度学习的遥感图像建筑物分割方法[D]. 银川: 宁夏大学, 2022.
YUAN Y Y. Building segmentation method for remote sensing images based on deep learning[D]. Yinchuan: Ningxia University, 2022.
[2] 吴炜, 骆剑承, 沈占锋, 等. 光谱和形状特征相结合的高分辨率遥感图像的建筑物提取方法[J]. 武汉大学学报 (信息科学版), 2012, 37(7): 800-805.
WU W, LUO C J, SHEN Z F, et al. A method for extracting buildings from high resolution remote sensing images by combining spectral and shape features[J]. Geomatics and Information Science of Wuhan University, 2012, 37(7): 800-805.
[3] 胡荣明, 黄小兵, 黄远程. 增强形态学建筑物指数应用于高分辨率遥感影像中建筑物提取[J]. 测绘学报, 2014, 43(5): 514-520.
HU R M, HUANG X B, HUANG Y C. An enhanced morphological building index for building extraction from high-resoulution images[J]. Acta Geodaetica et Cartographica Sinica, 2014, 43(5): 514-520.
[4] CHEN X L, ZHAO J, CHEN S Y. Lightweight semantic segmentation network based on attention coding[J]. Laser & Optoelectronics Progress, 2021, 58(14): 225-233.
[5] LIU P H, LIU X P, LIU M X, et al. Building footprint extraction from high-resolution images via spatial residual inception convolutional neural network[J]. Remote Sensing, 2019, 11(7): 830.
[6] CHEN S, ZUO Q, WANG Z. Semantic segmentation of high resolution remote sensing images based on improved ResU-Net[C]//Proceedings of the IEEE International Geoscience and Remote Sensing Symposium, 2022: 3492-3495.
[7] ZHANG S, WANG C, LI J, et al. MF-Dfnet: a deep learning method for pixel-wise classification of very high-resolution remote sensing images[J]. International Journal of Remote Sensing, 2022, 43: 18-27.
[8] LI D L, CHEN Z Y, FAN W T, et al. Self-attention in reconstruction bias U-net for semantic segmentation of building rooftops in optical remote sensing images[J]. Remote Sensing, 2021, 13(13): 2524.
[9] 王燕, 南佩奇. MFFNet：多级特征融合图像语义分割网络[J]. 计算机科学与探索, 2024, 18(3): 707-717.
WANG Y, NAN P Q. MFFNet：Image segmentation network of multi-level feature fusion[J]. Journal of Frontiers of Computer Science & Technology, 2024, 18(3): 707-717.
[10] 周华平, 邓彬. 融合多层次特征的deeplabV3+轻量级图像分割算法[J]. 计算机工程与应用, 2024, 60(16): 269-275.
ZHOU H P, DENG B. DeeplabV3+lightweight image segmentation algorithm based on multilevel feature fusion[J]. Computer Engineering and Applications, 2024, 60(16): 269-275.
[11] DIAKOGIANNIS F I, WALDNER F, CACCETTA P, et al. ResUNet-A: a deep learning framework for semantic segmentation of remotely sensed data[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 162: 94-114.
[12] WANG W H, XIE E, LI X, et al. PVT v2: improved baselines with pyramid vision transformer[J]. Computational Visual Media, 2022, 8(3): 415-424.
[13] WANG W, XIE E, LI X, et al. Pyramid vision transformer: A versatile backbone for dense prediction without convolutions[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021: 568-578.
[14] TOLSTIKHIN I O, HOULSBY N, KOLESNIKOV A, et al. MLP-mixer: an all-MLP architecture for vision[C]//Advances in Neural Information Processing Systems, 2021: 24261-24272.
[15] SUDRE C H, LI W, VERCAUTEREN T, et al. Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations[J]. arXiv:1707.03237, 2017.
[16] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]//Proceedings of the IEEE International Conference on Computer Vision, 2017: 2980-2988.
[17] JI S P, WEI S Q, LU M. Fully convolutional networks for multisource building extraction from an open aerial and satellite imagery data set[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(1): 574-586.
[18] MAGGIORI E, TARABALKA Y, CHARPIAT G, et al. Can semantic labeling methods generalize to any city? the inria aerial image labeling benchmark[C]//Proceedings of the 2017 IEEE International Geoscience and Remote Sensing Symposium, 2017: 3226-3229.
[19] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016: 770-778.
[20] ZHAO H S, SHI J P, QI X J, et al. Pyramid scene parsing network[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017: 6230-6239.
[21] CHEN J, LU Y, YU Q, et al. TransUNet: transformers make strong encoders for medical image segmentation[J]. arXiv:2102.04306, 2021.
[22] GUO H N, SU X, TANG S K, et al. Scale-robust deep-supervision network for mapping building footprints from high-resolution remote sensing images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021, 14: 10091-10100.
[23] GUO H, DU B, ZHANG L, et al. A coarse-to-fine boundary refinement network for building footprint extraction from remote sensing imagery[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2022, 183: 240-252.