MangroveSeg: Deep-Supervision-Guided Feature Aggregation Network for Mangrove Detection and Segmentation in Satellite Images
Abstract
:1. Introduction
- A novel deep-supervision-guided feature aggregation network called MangroveSeg is proposed for mangrove detection and segmentation. This innovative network constructs an encoder module inspired by the hybrid ResNet structure.
- The deep supervision model is introduced to further enhance the representation of features, which mitigates the complexities associated with camouflage target detection by integrating an attention mechanism and a multi-scale feature fusion framework to effectively obtain both local and global features for enhancing feature representation.
- The novel learning-based mangrove detection model can be used to update the baselines over multi-year, (2015–2019) to 2023, periods for change detecting. The proposed model can automatically and accurately detect the distribution and area of mangroves from satellite images, which provides a way of achieving a mangrove monitoring gateway for application at the global scale.
2. Materials
2.1. Study Area
2.2. Dataset Acquisition and Ground Truth Annotation
2.3. Data Pre-Processing
- The initial step was to integrate the satellite image layer into the QGIS program. Subsequently, the truth label was imported as a new layer, and the locations of both layers were fine-tuned.
- The next step comprised aligning the map layer with Dongzhaigang Nature Reserve. The map scale of 5300:1 was utilized to divide the designated area. To generate the required XYZ tiles, the Raster Tools module in the QGIS software was employed. The tile size was set to 256 × 256 pixels, and the map layer’s zoom level was adjusted to level 17. Following this, the satellite images and ground truth label image were then exported based on the map layer.
- Finally, the produced image files were organized into a dataset, sorted based on their file names. The dataset of the mangroves was divided into two parts, consisting of 4000 images, with 3002 for training and 998 for testing. Since the trained model can be used to monitor the distribution of mangrove forests in any area, we also evaluated the statistical square measure of some mangrove areas from Hainan Xinying Mangrove National Wetland Park as testing data.
3. Methods
3.1. The Proposed MangroveSeg Network
3.1.1. Attention Block Module
3.1.2. Feature Fusion and Conduction Module
3.1.3. Deep Supervision Module
3.2. Experimental Setting
3.3. Evaluation Criteria
3.4. Result Analysis
3.5. Ablation Study
4. Discussion
4.1. Advances for Alleviating Challenging Issues
- This method improves the feature representation and contrast between mangroves and the surroundings; therefore, the deep supervision model enables more accurate segmentation. Figure 12 shows the testing results via MangroveSeg, in which it can be observed that the unannotated mangroves in the annotated ground truth were detected in the test result. The area marked in red demonstrates that the proposed MangroveSeg network can effectively detect camouflaged mangrove areas from the complex surrounding environment.
- The proposed MangroveSeg network can be directly used for change detection in mangrove forests of certain areas during a specific period of time when the way of obtaining regional data is the same as that for the training data. It can be retrained as needed to adapt to data with different characteristics, which make change detection unrestricted by using existing software.
4.2. Limitations
- The mangrove detection performance is greatly affected by data heterogeneity caused by the phenology of this type of forest. When collecting data from detection areas, the performance of the model cannot be guaranteed where there are significant differences in weather, season, and other phenological conditions. How to improve the generalization ability of methods is a direction that needs to be continuously developed.
- When the terrain structure of the surface is complex and there are significant differences in surface information, false detections may occur as shown in Figure 13 and marked in red. Due to factors such as shadows and terrain, the texture information in satellite images is complex, resulting in inaccurate mangrove detection.
- The MangroveSeg network runs on the Python development platform, which is inconvenient for users, and it can be developed on a web platform for users to approach conveniently.
- The MangroveSeg network only uses RGB images of visible light and does not fully utilize multi-band data. In the future, we can explore the fusion of multi-band and multi-scale data to further improve network performance.
5. Conclusions
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- Jia, M.; Wang, Z.; Li, L.; Song, K.; Ren, C.; Liu, B.; Mao, D. Mapping China’s mangroves based on an object-oriented classification of Landsat imagery. Wetlands 2014, 34, 277–283. [Google Scholar] [CrossRef]
- Su, J.; Gasparatos, A. Perceptions about mangrove restoration and ecosystem services to inform ecosystem-based restoration in Large Xiamen Bay, China. Landsc. Urban Plan. 2023, 235, 104763. [Google Scholar] [CrossRef]
- Künzer, C.; Bluemel, A.; Gebhardt, S.; Quoc, T.V.; Dech, S. Remote Sensing of Mangrove Ecosystems: A Review. Remote Sens. 2011, 3, 878–928. [Google Scholar] [CrossRef]
- Pham, T.D.; Yokoya, N.; Bui, D.T.; Yoshino, K.; Friess, D.A. Remote Sensing Approaches for Monitoring Mangrove Species, Structure, and Biomass: Opportunities and Challenges. Remote Sens. 2019, 11, 230. [Google Scholar] [CrossRef]
- Zhang, Z.; Ahmed, M.R.; Zhang, Q.; Li, Y.; Li, Y.F. Monitoring of 35-Year Mangrove Wetland Change Dynamics and Agents in the Sundarbans Using Temporal Consistency Checking. Remote Sens. 2023, 15, 18. [Google Scholar] [CrossRef]
- Qiu, F.; Pu, W.; Zou, Y.; Zhong, F. Finer Resolution Estimation and Mapping of Mangrove Biomass Using UAV LiDAR and WorldView-2 Data. Forests 2019, 10, 871. [Google Scholar] [CrossRef]
- Aljahdali, M.O.; Munawar, S.; Khan, W.R. Monitoring Mangrove Forest Degradation and Regeneration: Landsat Time Series Analysis of Moisture and Vegetation Indices at Rabigh Lagoon, Red Sea. Forests 2021, 12, 52. [Google Scholar] [CrossRef]
- Hagger, V.; Worthington, T.A.; Lovelock, C.E.; Adame, M.F.; Amano, T.; Brown, B.M.; Friess, D.A.; Landis, E.; Mumby, P.J.; Morrison, T.H.; et al. Drivers of global mangrove loss and gain in social-ecological systems. Nat. Commun. 2022, 13, 6373. [Google Scholar] [CrossRef]
- Basáez-Muoz, A.d.J.; Jordán-Garza, A.G.; Serrano, A. Forest Structure and Projections of Avicennia germinans (L.) L. at Three Levels of Perturbation in a Southwestern Gulf of Mexico Mangrove. Forests 2021, 12, 989. [Google Scholar] [CrossRef]
- Longépée, E.; Abdallah, A.A.; Jeanson, M.; Golléty, C. Local Ecological Knowledge on Mangroves in Mayotte Island (Indian Ocean) and Influencing Factors. Forests 2021, 12, 53. [Google Scholar] [CrossRef]
- Anh, D.T.N.; Tran, H.D.; Ashley, M.; Nguyen, A.T. Monitoring landscape fragmentation and aboveground biomass estimation in Can Gio Mangrove Biosphere Reserve over the past 20 years. Ecol. Inform. 2022, 70, 101743. [Google Scholar] [CrossRef]
- Pettorelli, N.; Nagendra, H.; Rocchini, D.; Rowcliffe, M.; Williams, R.; Ahumada, J.; Angelo, C.D.D.; Atzberger, C.; Boyd, D.; Buchanan, G. Remote Sensing in Ecology and Conservation: Three years on. Remote Sens. Ecol. Conserv. 2017, 3, 53–56. [Google Scholar] [CrossRef]
- Valderrama-Landeros, L.; Flores-De-Santiago, F.; Kovacs, J.M.; Flores-Verdugo, F. An assessment of commonly employed satellite-based remote sensors for mapping mangrove species in Mexico using an NDVI-based classification scheme. Environ. Monit. Assess. 2018, 190, 23. [Google Scholar] [CrossRef]
- Baloloy, A.B.; Blanco, A.C.; Ana, R.R.C.S.; Nadaoka, K. Development and application of a new mangrove vegetation index (MVI) for rapid and accurate mangrove mapping. ISPRS J. Photogramm. Remote Sens. 2020, 166, 95–117. [Google Scholar] [CrossRef]
- Liu, M.; Zhang, H.; Lin, G.; Lin, H.; Tang, D. Zonation and Directional Dynamics of Mangrove Forests Derived from Time-Series Satellite Imagery in Mai Po, Hong Kong. Sustainability 2018, 10, 1913. [Google Scholar] [CrossRef]
- Wang, D.; Wan, B.; Qiu, P.; Zuo, Z.; Wu, X. Mapping Height and Aboveground Biomass of Mangrove Forests on Hainan Island Using UAV-LiDAR Sampling. Remote Sens. 2019, 11, 2156. [Google Scholar] [CrossRef]
- Maurya, K.; Mahajan, S.; Chaube, N.R. Remote sensing techniques: Mapping and monitoring of mangrove ecosystem—A review. Complex Intell. Syst. 2021, 7, 2797–2818. [Google Scholar] [CrossRef]
- Taureau, F.; Robin, M.; Proisy, C.; Fromard, F.; Imbert, D.; Debaine, F. Mapping the Mangrove Forest Canopy Using Spectral Unmixing of Very High Spatial Resolution Satellite Images. Remote Sens. 2019, 11, 17. [Google Scholar] [CrossRef]
- Nagarajan, P.; Rajendran, L.; Pillai, N.D.; Lakshmanan, G. Comparison of machine learning algorithms for mangrove species identification in Malad creek, Mumbai using WorldView-2 and Google Earth images. J. Coast. Conserv. 2022, 26, 1–13. [Google Scholar] [CrossRef]
- Pourshamsi, M.; Xia, J.; Yokoya, N.; Garcia, M.; Lavalle, M.; Pottier, E.; Balzter, H. Tropical forest canopy height estimation from combined polarimetric SAR and LiDAR using machine-learning. ISPRS J. Photogramm. Remote Sens. 2021, 172, 79–94. [Google Scholar] [CrossRef]
- Wang, J.; Chen, X.; Cao, L.; An, F.; Chen, B.; Xue, L.; Yun, T. Individual Rubber Tree Segmentation Based on Ground-Based LiDAR Data and Faster R-CNN of Deep Learning. Forests 2019, 10, 793. [Google Scholar] [CrossRef]
- Lassalle, G.; Ferreira, M.P.; La Rosa, L.E.C.; de Souza Filho, C.R. Deep learning-based individual tree crown delineation in mangrove forests using very-high-resolution satellite imagery. ISPRS J. Photogramm. Remote Sens. 2022, 189, 220–235. [Google Scholar] [CrossRef]
- Ronneberger, O.; Fischer, P.; Brox, T. U-net: Convolutional networks for biomedical image segmentation. In Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany, 5–9 October 2015; pp. 234–241. [Google Scholar]
- Simonyan, K.; Zisserman, A. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv 2014, arXiv:1409.1556. [Google Scholar] [CrossRef]
- He, K.; Zhang, X.; Ren, S.; Sun, J. Deep Residual Learning for Image Recognition. In Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 27–30 June 2016; pp. 770–778. [Google Scholar]
- Li, H.; Hu, B.; Li, Q.; Jing, L. CNN-Based Individual Tree Species Classification Using High-Resolution Satellite Imagery and Airborne LiDAR Data. Forests 2021, 12, 1697. [Google Scholar] [CrossRef]
- Soni, A.; Koner, R.; Villuri, V.G.K. M-UNet: Modified U-Net Segmentation Framework with Satellite Imagery. In Proceedings of the Global AI Congress 2019, Singapore, 3 April 2020; pp. 47–59. [Google Scholar]
- Xu, C.; Wang, J.; Sang, Y.; Li, K.; Liu, J.; Yang, G. An Effective Deep Learning Model for Monitoring Mangroves: A Case Study of the Indus Delta. Remote Sens. 2023, 15, 2220. [Google Scholar] [CrossRef]
- Guo, M.; Yu, Z.; Xu, Y.; Huang, Y.; Li, C. ME-Net: A Deep Convolutional Neural Network for Extracting Mangrove Using Sentinel-2A Data. Remote Sens. 2021, 13, 1292. [Google Scholar] [CrossRef]
- Lomeo, D.; Singh, M. Cloud-Based Monitoring and Evaluation of the Spatial-Temporal Distribution of Southeast Asia’s Mangroves Using Deep Learning. Remote Sens. 2022, 14, 2291. [Google Scholar] [CrossRef]
- Irem Ulku, E.A.; Ghamisi, P. Deep Semantic Segmentation of Trees Using Multispectral Images. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2022, 15, 7589–7604. [Google Scholar] [CrossRef]
- Sinha, A.; Dolz, J. Multi-Scale Self-Guided Attention for Medical Image Segmentation. IEEE J. Biomed. Health Inform. 2021, 25, 121–130. [Google Scholar] [CrossRef]
- Li, H.; Li, H.; Peng, X.; Peng, X.; Zeng, J.; Zeng, J.; Xiao, J.; Xiao, J.; Nie, D.; Nie, D. Explainable attention guided adversarial deep network for 3D radiotherapy dose distribution prediction. Knowl.-Based Syst. 2022, 241, 108324. [Google Scholar] [CrossRef]
- Vardanjani, S.M.; Fathi, A.; Moradkhani, K. Grsnet: Gated residual supervision network for pixel-wise building segmentation in remote sensing imagery. Int. J. Remote Sens. 2022, 43, 4872–4887. [Google Scholar] [CrossRef]
- Zhou, T.; Zhou, Y.; Gong, C.; Yang, J.; Zhang, Y. Feature Aggregation and Propagation Network for Camouflaged Object Detection. IEEE Trans. Image Process. 2022, 31, 7036–7047. [Google Scholar] [CrossRef] [PubMed]
- Bunting, P.; Rosenqvist, A.; Hilarides, L.; Lucas, R.M.; Thomas, N.; Tadono, T.; Worthington, T.A.; Spalding, M.; Murray, N.J.; Rebelo, L.-M. Global Mangrove Extent Change 1996-2020: Global Mangrove Watch Version 3.0. Remote Sens. 2022, 14, 3657. [Google Scholar] [CrossRef]
- China National Platform for Common Geospatial Information Service. Available online: https://www.tianditu.gov.cn/ (accessed on 8 February 2023).
- Liao, J.; Zhu, B.; Chang, Y.; Zhang, L. A dataset of mangrove forests changes in Hainan Island based on GF-2 data during 2015–2019. Sci. Data Bank 2022, 7, 1–11. [Google Scholar] [CrossRef]
- Oktay, O.; Schlemper, J.; Folgoc, L.L.; Lee, M.; Heinrich, M.; Misawa, K.; Mori, K.; Mcdonagh, S.; Hammerla, N.Y.; Kainz, B. Attention U-Net: Learning Where to Look for the Pancreas. arXiv 2018, arXiv:1804.03999. [Google Scholar] [CrossRef]
- Zhou, Z.; Siddiquee, M.M.R.; Tajbakhsh, N.; Liang, J. UNet++: A Nested U-Net Architecture for Medical Image Segmentation. IEEE Trans. Med. Imaging 2018, 39, 1856–1867. [Google Scholar] [CrossRef]
- Qin, X.; Zhang, Z.; Huang, C.; Dehghan, M.; Jagersand, M. U2-Net: Going deeper with nested U-structure for salient object detection. Pattern Recognit. 2020, 106, 107404. [Google Scholar] [CrossRef]
- Shen, M.; Bu, Y.; Wornell, G.W. On Balancing Bias and Variance in Unsupervised Multi-Source-Free Domain Adaptation. In Proceedings of the 40th International Conference on Machine Learning, Honolulu, HI, USA, 23–29 July 2023; pp. 30976–30991. [Google Scholar]
- Zhang, X.; Xu, R.; Yu, H.; Zou, H.; Cui, P. Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization. arXiv 2023, arXiv:2303.03108. [Google Scholar] [CrossRef]
Method | mIoU% | mPA% | ACC% | Parameters | Time/Epoch |
---|---|---|---|---|---|
FAPNET [25] | 65.85 | 81.1 | 81.26 | 27.1M | 46S |
UNet [28] | 59.64 | 73.88 | 77.76 | 34.5M | 35S |
ATT-UNet [29] | 59.27 | 73.71 | 75.6 | 41.4M | 31S |
UNet++ [30] | 57.61 | 72.35 | 75.44 | 36.6M | 32S |
U2Net [31] | 57.77 | 72.38 | 75.29 | 44.0M | 36S |
MangroveSeg (ours) | 80.7 | 89.02 | 89.58 | 57.5M | 48S |
Attention Block | Feature Fusion Block | mIoU% | mPA% | ACC% | Recall% |
---|---|---|---|---|---|
65.85 | 81.1 | 81.26 | 81.1 | ||
√ | 73.59 | 84.11 | 86.15 | 84.11 | |
√ | 70.14 | 81.46 | 85.68 | 81.46 | |
√ | √ | 80.7 | 89.02 | 89.68 | 89.02 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Dong, H.; Gao, Y.; Chen, R.; Wei, L. MangroveSeg: Deep-Supervision-Guided Feature Aggregation Network for Mangrove Detection and Segmentation in Satellite Images. Forests 2024, 15, 127. https://doi.org/10.3390/f15010127
Dong H, Gao Y, Chen R, Wei L. MangroveSeg: Deep-Supervision-Guided Feature Aggregation Network for Mangrove Detection and Segmentation in Satellite Images. Forests. 2024; 15(1):127. https://doi.org/10.3390/f15010127
Chicago/Turabian StyleDong, Heng, Yifan Gao, Riqing Chen, and Lifang Wei. 2024. "MangroveSeg: Deep-Supervision-Guided Feature Aggregation Network for Mangrove Detection and Segmentation in Satellite Images" Forests 15, no. 1: 127. https://doi.org/10.3390/f15010127
APA StyleDong, H., Gao, Y., Chen, R., & Wei, L. (2024). MangroveSeg: Deep-Supervision-Guided Feature Aggregation Network for Mangrove Detection and Segmentation in Satellite Images. Forests, 15(1), 127. https://doi.org/10.3390/f15010127