|
|
基于锯齿空洞空间卷积池化结构的高分辨率遥感影像建筑物提取
|
Abstract:
尽管高分辨率遥感影像地物纹理清晰并且光谱异质性高，但影像中的房屋建筑存在复杂多样性问题，这导致应用卷积神经网络AASPP模型、DenseASPP模型分别进行提取建筑物时，较易产生误提取和遗漏提取。因此，本文提出了一种基于空洞金字塔卷积结构DentateASPP的高分高分辨率遥感影像建筑物提取方法，采用现有建筑物数据集和重庆高分2号影像进行试验，与AASPP和DenseASPP模型建筑物提取的结果相比，实验表明，DentateASPP模型提取建筑物误提取和漏提取最少，效果最优。
Despite the clear texture and high spectral heterogeneity of ground objects in high-resolution remote sensing images, there is a complex and diverse problem with the buildings in the images, which leads to errors and omissions when using convolutional neural network AASPP model and DenseASPP model to extract buildings separately. Therefore, a high-resolution remote sensing image building extraction method based on DentateASPP (Dentate Atrous Spatial pyramid pooling) are proposed. The existing building dataset and high-resolution GF-2 images were used for experiments. Compared with the results of building extraction using AASPP and DenseASPP models, the experiments show that the DentateASPP model has the least number of errors and omissions in extracting buildings, and the best performance.
| [1] | 崔卫红, 熊宝玉, 张丽瑶. 多尺度全卷积神经网络建筑物提取[J]. 测绘学报, 2019, 48(5): 597-608. |
| [2] | Delassus, R. and Giot, R. (2018) CNNs Fusion for Building Detection in Aerial Images for the Building Detection Challenge. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Salt Lake City, 18-22 June 2018, 237-2374. https://doi.org/10.1109/cvprw.2018.00044 |
| [3] | 叶沅鑫, 谭鑫, 孙苗苗, 王蒙蒙. 基于增强DeepLabV3网络的高分辨率遥感影像分类[J]. 测绘通报, 2021(4): 40-44. |
| [4] | Zhao, H., Shi, J., Qi, X., Wang, X. and Jia, J. (2017) Pyramid Scene Parsing Network. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, 21-26 July 2017, 6230-6239. https://doi.org/10.1109/cvpr.2017.660 |
| [5] | Yu, B., Yang, L. and Chen, F. (2018) Semantic Segmentation for High Spatial Resolution Remote Sensing Images Based on Convolution Neural Network and Pyramid Pooling Module. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 11, 3252-3261. https://doi.org/10.1109/jstars.2018.2860989 |
| [6] | Chen, L., Papandreou, G., Kokkinos, I., Murphy, K. and Yuille, A.L. (2018) Deeplab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40, 834-848. https://doi.org/10.1109/tpami.2017.2699184 |
| [7] | Chen, L., Zhu, Y., Papandreou, G., Schroff, F. and Adam, H. (2018) Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C. and Weiss, Y., Eds., Lecture Notes in Computer Science, Springer International Publishing, 833-851. https://doi.org/10.1007/978-3-030-01234-2_49 |
| [8] | Chen, G., Li, C., Wei, W., Jing, W., Woźniak, M., Blažauskas, T., et al. (2019) Fully Convolutional Neural Network with Augmented Atrous Spatial Pyramid Pool and Fully Connected Fusion Path for High Resolution Remote Sensing Image Segmentation. Applied Sciences, 9, Article 1816. https://doi.org/10.3390/app9091816 |
