ABSTRACT
Landfill monitoring is of paramount importance for environmental sustainability and public health. Remote sensing technology enables the acquisition of high-resolution spatial data over large areas, providing a comprehensive view of landfill sites. The integration of deep learning, particularly convolutional neural networks, enhances landfill segmentation accuracy by automating feature extraction and recognizing complex spatial patterns. However, challenges persist in obtaining labeled training data and identifying specific landfill details. To track these challenges, this paper proposes an advanced method for landfill segmentation. Firstly, we improve the YOLOv7 model by introducing the attention mechanism and pre-training it with the dataset of 313 remote-sensing images of landfills. Then, wavelet transform, and Laplacian pyramid techniques are utilized to augment the original landfill dataset, thereby enhancing the representation of key landfill features at various stages. Finally, we finetune the pre-trained model with the augmented dataset, further improving its capability to discern both detailed and overarching features of landfills. The experimental results demonstrate that the proposed method achieves a mean pixel accuracy (MPA) of 98.111% and a mean intersection over union (mIoU) of 88.57% in landfill segmentation, surpassing other methods in terms of accuracy and proving to be highly effective for landfill monitoring.
- Y Wang, F Lv, X Kang, Y Zhang, and P He, Standards for odor pollution control in municipal solid waste landfills in China: Thoughts and suggestions. Science Bulletin, Science Bulletin, 68, 21, 2756–2761, 2023, https://engine.scichina.com/doi/10.1360/TB-2023-0405Google Scholar
- S Li, X Luo, Y Long, Y Yao, J Liu, and W Wang, Remote Sensing-based Monitoring for Spatial Expansion of Municipal Waste Landfills - A Case Study of Gaoyan Site in Guiyang City, Earth and Environment, 45, 3, 368–373, 2017, http://ir.gyig.ac.cn/handle/42920512-1/8474Google Scholar
- B Aslam, A Maqsoom, MD Tahir, F Ullah, MSU Rehman, and M Albattah, Identifying and Ranking Landfill Sites for Municipal Solid Waste Management: An Integrated Remote Sensing and GIS Approach, Buildings, 12, 5, 605, May 2022, https://doi.org/10.3390/buildings12050605Google ScholarCross Ref
- KK Thanammal, RR Vijayalakshmi, S Arumugaperumal, and JS Jayasudha, Effective Histogram Thresholding Techniques for Natural Images Using Segmentation, Journal of Image and Graphics, 2, 2, 2015, https://doi.org/10.12720/joig.2.2.113-116Google ScholarCross Ref
- N Richard, C Fernandez-Maloigne, C Bonanomi, and A Rizzi, Fuzzy Color Image Segmentation using Watershed Transform, Journal of Image and Graphics, 157–160, 2013, https://doi.org/10.12720/joig.1.3.157-160Google ScholarCross Ref
- R Kaur and ErG Malik, An Image Segmentation Using Improved FCM Watershed Algorithm and DBMF, Journal of Image and Graphics, 2, 2, 2015, https://doi.org/10.12720/joig.2.2.106-112Google ScholarCross Ref
- Z Ma, M Xia, L Weng, and H Lin, Local Feature Search Network for Building and Water Segmentation of Remote Sensing Image, Sustainability, 15, 4, 3034, Feb. 2023, https://doi.org/10.3390/su15043034Google ScholarCross Ref
- C Zhang, L Weng, L Ding, M Xia, and H Lin, CRSNet: Cloud and Cloud Shadow Refinement Segmentation Networks for Remote Sensing Imagery, Remote Sensing, 15, 6, 1664, Mar. 2023, https://doi.org/10.3390/rs15061664Google ScholarCross Ref
- Y Wu, Y Wang, K Xiao, X Wang, and Y Wang, Research and Analysis on Garbage Recognition Using Remote Sensing mages, Urban Geotechnical Investigation & Surveying, 5, 96–99, 2022.Google Scholar
- X Sun , Revealing influencing factors on global waste distribution via deep-learning based dumpsite detection from satellite imagery, Nature Communications, 14, 1, 1444, Mar. 2023, https://doi.org/10.1038/s41467-023-37136-1Google ScholarCross Ref
- X Li, Y Zhou, and F Wang, Advanced Information Mining from Ocean Remote Sensing Imagery with Deep Learning, Journal of Remote Sensing, 2022, 2022/9849645, Jan. 2022, https://doi.org/10.34133/2022/9849645Google ScholarCross Ref
- V Olsson, W Tranheden, J Pinto, and L Svensson, ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning, 2021 IEEE Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA, Jan. 2021, 1368–1377. https://doi.org/10.1109/WACV48630.2021.00141Google ScholarCross Ref
- C-Y Wang, A Bochkovskiy, and H-YM Liao, YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada, Jun. 2023, 7464–7475. https://doi.org/10.1109/CVPR52729.2023.00721Google ScholarCross Ref
- S Woo, J Park, J-Y Lee, and IS Kweon, CBAM: Convolutional Block Attention Module, Computer Vision – ECCV 2018, Cham, 2018, 11211, 3–19. https://doi.org/10.1007/978-3-030-01234-2_1Google ScholarDigital Library
- J Wang, Z Zheng, A Ma, X Lu, and Y Zhong, LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation, May 2022, http://arxiv.org/abs/2110.08733Google Scholar
- S Mohajerani and P Saeedi, Cloud and Cloud Shadow Segmentation for Remote Sensing Imagery Via Filtered Jaccard Loss Function and Parametric Augmentation, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14, 4254–4266, 2021, https://doi.org/10.1109/JSTARS.2021.3070786Google ScholarCross Ref
- L-C Chen, G Papandreou, F Schroff, and H Adam, Rethinking Atrous Convolution for Semantic Image Segmentation, Dec. 2017, http://arxiv.org/abs/1706.05587Google Scholar
- L-C Chen, Y Zhu, G Papandreou, F Schroff, and H Adam, Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation, Computer Vision – ECCV 2018, Cham, 2018, 11211, 833–851. https://doi.org/10.1007/978-3-030-01234-2_49Google ScholarDigital Library
Index Terms
- Investigation on Landfill Segmentation Performance from Remote Sensing Images using Attention Mechanism-Improved YOLOv7 Model
Recommendations
An improved U-Net method for the semantic segmentation of remote sensing images
AbstractForemost deep neural network models trained in natural scenes cannot transfer and apply to remote sensing image semantic segmentation well. Studies have shown that fine-tuning methods containing model fusion can alleviate this dilemma. In this ...
Semantic segmentation of high-resolution remote sensing images based on a class feature attention mechanism fused with Deeplabv3+
AbstractAiming at solving the problems of inaccurate segmentation of edge targets, inconsistent segmentation of different types of targets, and slow prediction efficiency on semantic segmentation of high-resolution remote sensing images by ...
Highlights- The class feature attention mechanism and Deeplabv3+ are combined for high-resolution remote sensing image segmentation.
Towards better exploiting convolutional neural networks for remote sensing scene classification
We present an analysis of three possible strategies for exploiting the power of existing convolutional neural networks (ConvNets or CNNs) in different scenarios from the ones they were trained: full training, fine tuning, and using ConvNets as feature ...
Comments