Quarry recognition based on improved CycleMLP from high-resolution remote sensing imagery

doi:10.13474/j.cnki.11-2246.2023.0045

Abstract

Abstract: The ecological restoration of the quarry area is an important link to improve the function of the regional ecosystem. Identifying the quarry and determining the boundary of the mining area are the prerequisites for completing the restoration task. Currently, the semantic segmentation technology based on deep learning can accurately recognize the objects of interest in high-resolution remote sensing images, providing an effective way for quarry identification. Based on the CycleMLP framework, this paper uses the pyramid structure to input multi-level features into a lightweight MLP decoder, aggregates feature information from different levels, and obtains local and global features at the same time. The convolutional layers are embedded into the feed-forward network, which avoids the accuracy decline caused by position-encoded interpolation. Experiments employ the semantic segmentation dataset of the quarry areas in Nan'an city, Fujian province to train the network and verify the accuracy. The results show that the improved CycleMLP can effectively identify quarry areas from high-resolution remote sensing images. Compared with other methods based on self-attention mechanism, the improved CycleMLP achieves higher accuracy, accurately extracts the boundary of the quarry area, and can provide reliable supporting materials for the restoration of the ecosystem in the quarry area.

Key words: quarry, high-resolution remote sensing images, MLP, decoder, ecological restoration

CLC Number:

P237

ZHAO Yubin, NI Huan, NIU Xiaonan. Quarry recognition based on improved CycleMLP from high-resolution remote sensing imagery[J]. Bulletin of Surveying and Mapping, 2023, 0(2): 84-90.

References

[1] 石丽丽.京西石灰石采石场废弃地植被恢复效果及其评价研究[D].北京: 北京林业大学, 2014.
[2] 宋百敏.北京西山废弃采石场生态恢复研究:自然恢复的过程、特征与机制[D].济南: 山东大学, 2008.
[3] 张玉虎,于长青,宋百敏,等.快速监测评估废弃采石场生态恢复的研究[J].生态与农村环境学报,2007,23(3): 36-40.
[4] 赵浩腾.基于Landsat长时间遥感影像的采石场面积监测与分析[D].北京: 中国科学院大学(中国科学院遥感与数字地球研究所),2018.
[5] 尹红,杨广斌,安裕伦.贵阳市采石场遥感动态监测研究[J].环保科技,2007,13(1): 6-10.
[6] 马得利,孙永康,杨建英,等.基于无人机遥感技术的废弃采石场立地条件类型划分[J].北京林业大学学报,2018,40(9): 90-97.
[7] 王耿明,朱俊凤,陈捷,等.采石场绿色矿山建设无人机动态监测: 以广州市太珍石场为例[J].地矿测绘,2019,35(3): 29-30.
[8] 马林飞,倪欢,周子涵.基于注意力机制的高分遥感图像采石场识别[J].测绘通报,2021(11): 96-100.
[9] SHELHAMER E,LONG J,DARRELL T.Fully convolutional networks for semantic segmentation[C]// Proceedings of 2016 IEEE Transactions on Pattern Analysis and Machine Intelligence.[S.l.]: IEEE,2016: 640-651.
[10] KRIZHEVSKY A,SUTSKEVER I,HINTON G E.ImageNet classification with deep convolutional neural networks[J].Communications of the ACM,2017,60(6): 84-90.
[11] TRAORE B B,KAMSU-FOGUEM B,TANGARA F.Deep convolution neural network for image recognition[J].Ecological Informatics,2018,48: 257-268.
[12] HE Kaiming,ZHANG Xiangyu,REN Shaoqing,et al.Deep residual learning for image recognition[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).[S.l.]: IEEE,2016: 770-778.
[13] CHEN L C,PAPANDREOU G,KOKKINOS I,et al.DeepLab: semantic image segmentation with deep convolutional nets,atrous convolution,and fully connected CRFs[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2018,40(4): 834-848.
[14] ROMERA E,ÁLVAREZ J M,BERGASA L M,et al.ERFNet: efficient residual factorized ConvNet for real-time semantic segmentation[J].IEEE Transactions on Intelligent Transportation Systems,2018,19(1): 263-272.
[15] ZHAO Hengshuang,ZHANG Yi,LIU Shu,et al.PSANet: point-wise spatial attention network for scene parsing[M]//Computer Vision-ECCV 2018.Cham: Springer International Publishing,2018: 270-286.
[16] DOSOVITSKIY A,BEYER L,KOLESNIKOV A,et al.An image is worth 16×16 words: transformers for image recognition at scale[C]//Proceedings of 2021 International Conference on Learning Representations (ICLR).[S.l.]: Oral Paper,2021.
[17] TOUVRON H,CORD M,DOUZE M,et al.Training data-efficient image transformers ＆ distillation through attention[C]//Proceedings of 2021 International Conference on Machine Learning.[S.l.]: PMLR,2021.
[18] LIU Ze,LIN Yutong,CAO Yue,et al.Swin transformer: hierarchical vision transformer using shifted windows[C]//Proceedings of 2022 IEEE/CVF International Conference on Computer Vision (ICCV).Montreal,QC,Canada: IEEE,2022: 9992-10002.
[19] TOLSTIKHIN I,HOULSBY N,KOLESNIKOV A,et al.MLP-mixer: an all-MLP architecture for vision [J].Advances in Neural Information Processing Systems,2021,34: 24261-24272.
[20] DING Xiaohan,CHENG Honghao,ZHANG Xiangyu,et al.Repmlpnet: Hierarchical vision mlp with re-parameterized locality[C]//Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition.[S.l.]: IEEE,2022: 578-587.
[21] DENG Jia,DONG Wei,SOCHER R,et al.ImageNet: a large-scale hierarchical image database[C]//Proceedings of 2009 IEEE Conference on Computer Vision and Pattern Recognition.Miami,FL,USA:IEEE,2009: 248-255.
[22] CHEN Shoufa,XIE Enze,GE Chongjian,et al.CycleMLP: A MLP-like Architecture for Dense Prediction[C]//Proceedings of the International Conference on Learning Representations (ICLR).[S.l.]: Oral Paper,2022.
[23] ISLAM M A,JIA SEN,BRUCE N D B.How much position information do convolutional neural networks encode？ [C]//Proceedings of the International Conference on Learning Representations (ICLR).[S.l.]: Blind Submission Paper,2020.
[24] CHU Xiangxiang,TIAN Zhi,ZHANG Bo,et al.Twins: Revisiting the Design of Spatial Attention in Vision Transformers [J].Advances in Neural Information Processing Systems,2021,34: 9355-9366.
[25] XIE E,WANG Wenhai,YU Zhiding,et al.SegFormer: Simple and efficient design for semantic segmentation with transformers[J].Advances in Neural Information Processing Systems,2021,34: 12077-12090.
[26] DEVLIN J,LEE K,CHANG Mingwei,et al.BERT: Pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of NAACL-HLT.[S.l.]: NAACL-HLT,2019: 4171-4186.
[27] YANG TJ,CHEN YH,SZE V,et al.Designing energy-efficient convolutional neural networks using energy-aware pruning[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition.[S.l.]: IEEE,2017: 5687-5695.
[28] PENG Chengli,ZHANG Kaining,MA Yong,et al.Cross fusion net: a fast semantic segmentation network for small-scale semantic information capturing in aerial scenes[J].IEEE Transactions on Geoscience and Remote Sensing,2022,60: 1-13.
[29] DONG Xiaoyi,BAO Jiamin,CHEN Dongdong,et al.CSWin transformer: a general vision transformer backbone with cross-shaped windows [C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition.[S.l.]: IEEE,2022: 12124-12134.
[30] MEHTA S,RASTEGARI M.MobileViT: light-weight,general-purpose,and mobile-friendly vision transformer [C]//Proceedings of the International Conference on Learning Representations (ICLR).[S.l.]: ICLR,2020.