A Systematic Literature Review and Bibliometric Analysis of Semantic Segmentation Models in Land Cover Map**
Abstract
:1. Introduction
2. Materials and Methods
2.1. Research Questions (RQs)
- RQ1. What are the emerging patterns in land cover map**?
- RQ2. What are the domain studies of semantic segmentation models in land cover map**?
- RQ3. What are the data used in semantic segmentation models for land cover map**?
- RQ4. What are the architecture and performances of semantic segmentation methodologies used in land cover map**?
2.2. Search Strategy
2.3. Study Selection Criteria
2.4. Eligibility and Data Analysis
2.5. Data Synthesis
3. Results and Discussion
3.1. RQ1. What Are the Emerging Patterns in Land Cover Map**?
- Annual distribution of research studies
- Leading Journals
- Geographic distribution of studies
- Leading Themes and Timelines
3.2. RQ2. What Are Domain Studies of Semantic Segmentation Models in Land Cover Map**?
- Land Cover Studies
- Urban
- Precision Agriculture
- Environment
- Forest
- Coastal Areas
3.3. RQ3. What Are the Data Used in Semantic Segmentation Models for Land Cover Map**?
- Study Locations
- Data Sources
- Benchmark datasets
3.4. RQ4. What Are the Architecture and Performances of Semantic Segmentation Methodologies Used in Land Cover Map**?
- Encoder-Decoder based structure
- Transformer-based structure
- Hybrid-based structure
- Performance analysis of semantic segmentation model structures on ISPRS 2-D labelling Potsdam and Vaihingen datasets
- Common experimental training settings
4. Challenges, Future Insights and Directions
4.1. Land Cover Map**
- Extracting boundary information
- Generating Precise Land Cover Maps
4.2. Semantic Segmentation Methodologies
- Enhancing deep learning model performance
- Analysis of RS images
- Unlabeled and Imbalance RS data
5. Conclusions
Author Contributions
Funding
Data Availability Statement
Acknowledgments
Conflicts of Interest
Abbreviations
BANet | Bilateral Awareness Network |
CNN | Convolutional Neural Networks |
DCNN | Deep Convolutional Neural Network |
DEANET | Dual Encoder with Attention Network |
DGFNET | Dual-Gate Fusion Network |
DL | Deep Learning |
DSM | Digital Surface Model |
FCN | Fully Convolutional Networks |
GF-2 | GaoFen-2 |
GF-3 | GaoFen-3 |
GID | GaoFen Image Data |
HFENet | Hierarchical Feature Extraction Network |
HMRT | Hybrid Multi-resolution and Transformer semantic extraction Network |
IEEE | Institute of Electrical and Electronics Engineers |
IoU | Mean Intersection over Union |
ISPRS | International Society for Photogrammetry and Remote Sensing |
LC | Land Cover |
LiDAR | Light Detection and Ranging data |
LoveDA | Land-cOVEr Domain Adaptive |
LULC | Land Use and Land Cover |
MARE | Multi-Attention REsu-Net |
MDPI | Multidisciplinary Digital Publishing Institute |
MIoU | Mean Intersection over Union |
NLP | Natural Language Processing |
OA | Overall Accuracy |
PolSAR | Polarimetric Synthetic Aperture Radar |
RAANET | Residual ASPP with Attention Net |
RQ | Research Question |
RS | Remote Sensing |
RSI | Remote Sensing Imaginary |
SAR | Synthetic Aperture Radar |
SBANet | Semantic Boundary Awareness Network |
SEG-ESRGAN | Segmentation Enhanced Super-Resolution Generative Adversarial Network |
SOCNN | Superpixel-Optimized convolutional neural network |
SOTA | State-Of-The-Art |
UAS | Unmanned Aircraft System |
UAV | Unmanned Aerial Vehicle |
VEDAI | VEhicle Detection in Aerial Imagery |
WHDLD | Wuhan Dense Labeling Dataset |
References
- Vali, A.; Comai, S.; Matteucci, M. Deep Learning for Land Use and Land Cover Classification Based on Hyperspectral and Multispectral Earth Observation Data: A Review. Remote Sens. 2020, 12, 2495. [Google Scholar] [CrossRef]
- Ma, J.; Wu, L.; Tang, X.; Liu, F.; Zhang, X.; Jiao, L. Building Extraction of Aerial Images by a Global and Multi-Scale Encoder-Decoder Network. Remote Sens. 2020, 12, 2350. [Google Scholar] [CrossRef]
- Pourmohammadi, P.; Adjeroh, D.A.; Strager, M.P.; Farid, Y.Z. Predicting Developed Land Expansion Using Deep Convolutional Neural Networks. Environ. Model. Softw. 2020, 134, 104751. [Google Scholar] [CrossRef]
- Di Pilato, A.; Taggio, N.; Pompili, A.; Iacobellis, M.; Di Florio, A.; Passarelli, D.; Samarelli, S. Deep Learning Approaches to Earth Observation Change Detection. Remote Sens. 2021, 13, 4083. [Google Scholar] [CrossRef]
- Wei, P.; Chai, D.; Lin, T.; Tang, C.; Du, M.; Huang, J. Large-Scale Rice Map** under Different Years Based on Time-Series Sentinel-1 Images Using Deep Semantic Segmentation Model. ISPRS J. Photogramm. Remote Sens. 2021, 174, 198–214. [Google Scholar] [CrossRef]
- Dal Molin Jr., R.; Rizzoli, P. Potential of Convolutional Neural Networks for Forest Map** Using Sentinel-1 Interferometric Short Time Series. Remote Sens. 2022, 14, 1381. [Google Scholar] [CrossRef]
- Sun, Y.; Zhang, X.; Huang, J.; Wang, H.; ** with Sentinel-1 Imagery Using Deep Learning Semantic Segmentation Models. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2021, 14, 10357–10374. [Google Scholar] [CrossRef]
- Guo, Y.; Liu, Y.; Oerlemans, A.; Lao, S.; Wu, S.; Lew, M.S. Deep Learning for Visual Understanding: A Review. Neurocomputing 2016, 187, 27–48. [Google Scholar] [CrossRef]
- Huang, J.; Weng, L.; Chen, B.; ** Horizontal and Vertical Urban Densification in Denmark with Landsat Time-Series from 1985 to 2018: A Semantic Segmentation Solution. Remote Sens. Environ. 2020, 251, 112096. [Google Scholar] [CrossRef]
- Wu, F.; Wang, C.; Zhang, H.; Li, J.; Li, L.; Chen, W.; Zhang, B. Built-up Area Map** in China from GF-3 SAR Imagery Based on the Framework of Deep Learning. Remote Sens. Environ. 2021, 262, 112515. [Google Scholar] [CrossRef]
- Xu, S.; Zhang, S.; Zeng, J.; Li, T.; Guo, Q.; **, S. A Framework for Land Use Scenes Classification Based on Landscape Photos. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2020, 13, 6124–6141. [Google Scholar] [CrossRef]
- Xu, L.; Shi, S.; Liu, Y.; Zhang, H.; Wang, D.; Zhang, L.; Liang, W.; Chen, H. A Large-Scale Remote Sensing Scene Dataset Construction for Semantic Segmentation. Int. J. Image Data Fusion 2023, 14, 299–323. [Google Scholar] [CrossRef]
- Sirous, A.; Satari, M.; Shahraki, M.M.; Pashayi, M. A Conditional Generative Adversarial Network for Urban Area Classification Using Multi-Source Data. Earth Sci. Inf. 2023, 16, 2529–2543. [Google Scholar] [CrossRef]
- Vasavi, S.; Sri Somagani, H.; Sai, Y. Classification of Buildings from VHR Satellite Images Using Ensemble of U-Net and ResNet. Egypt. J. Remote Sens. Space Sci. 2023, 26, 937–953. [Google Scholar] [CrossRef]
- Kang, J.; Fernandez-Beltran, R.; Sun, X.; Ni, J.; Plaza, A. Deep Learning-Based Building Footprint Extraction with Missing Annotations. IEEE Geosci. Remote Sens. Lett. 2022, 19, 3002805. [Google Scholar] [CrossRef]
- Yu, J.; Zeng, P.; Yu, Y.; Yu, H.; Huang, L.; Zhou, D. A Combined Convolutional Neural Network for Urban Land-Use Classification with GIS Data. Remote Sens. 2022, 14, 1128. [Google Scholar] [CrossRef]
- Wei, P.; Chai, D.; Huang, R.; Peng, D.; Lin, T.; Sha, J.; Sun, W.; Huang, J. Rice Map** Based on Sentinel-1 Images Using the Coupling of Prior Knowledge and Deep Semantic Segmentation Network: A Case Study in Northeast China from 2019 to 2021. Int. J. Appl. Earth Obs. Geoinf. 2022, 112, 102948. [Google Scholar] [CrossRef]
- Liu, S.; Peng, D.; Zhang, B.; Chen, Z.; Yu, L.; Chen, J.; Pan, Y.; Zheng, S.; Hu, J.; Lou, Z.; et al. The Accuracy of Winter Wheat Identification at Different Growth Stages Using Remote Sensing. Remote Sens. 2022, 14, 893. [Google Scholar] [CrossRef]
- Bem, P.P.D.; de Carvalho Júnior, O.A.; Carvalho, O.L.F.D.; Gomes, R.A.T.; Guimarāes, R.F.; Pimentel, C.M.M. Irrigated Rice Crop Identification in Southern Brazil Using Convolutional Neural Networks and Sentinel-1 Time Series. Remote Sens. Appl. 2021, 24, 100627. [Google Scholar] [CrossRef]
- Niu, B.; Feng, Q.; Su, S.; Yang, Z.; Zhang, S.; Liu, S.; Wang, J.; Yang, J.; Gong, J. Semantic Segmentation for Plastic-Covered Greenhouses and Plastic-Mulched Farmlands from VHR Imagery. Int. J. Digit. Earth 2023, 16, 4553–4572. [Google Scholar] [CrossRef]
- Sykas, D.; Sdraka, M.; Zografakis, D.; Papoutsis, I. A Sentinel-2 Multiyear, Multicountry Benchmark Dataset for Crop Classification and Segmentation With Deep Learning. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2022, 15, 3323–3339. [Google Scholar] [CrossRef]
- Descals, A.; Wich, S.; Meijaard, E.; Gaveau, D.L.A.; Peedell, S.; Szantoi, Z. High-Resolution Global Map of Smallholder and Industrial Closed-Canopy Oil Palm Plantations. Earth Syst. Sci. Data 2021, 13, 1211–1231. [Google Scholar] [CrossRef]
- He, J.; Lyu, D.; He, L.; Zhang, Y.; Xu, X.; Yi, H.; Tian, Q.; Liu, B.; Zhang, X. Combining Object-Oriented and Deep Learning Methods to Estimate Photosynthetic and Non-Photosynthetic Vegetation Cover in the Desert from Unmanned Aerial Vehicle Images with Consideration of Shadows. Remote Sens. 2023, 15, 105. [Google Scholar] [CrossRef]
- Wan, L.; Li, S.; Chen, Y.; He, Z.; Shi, Y. Application of Deep Learning in Land Use Classification for Soil Erosion Using Remote Sensing. Front. Earth Sci. 2022, 10, 849531. [Google Scholar] [CrossRef]
- Cho, A.Y.; Park, S.-E.; Kim, D.-J.; Kim, J.; Li, C.; Song, J. Burned Area Map** Using Unitemporal PlanetScope Imagery With a Deep Learning Based Approach. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2023, 16, 242–253. [Google Scholar] [CrossRef]
- Bergado, J.R.; Persello, C.; Reinke, K.; Stein, A. Predicting Wildfire Burns from Big Geodata Using Deep Learning. Saf. Sci. 2021, 140, 105276. [Google Scholar] [CrossRef]
- Wang, Z.; Yang, P.; Liang, H.; Zheng, C.; Yin, J.; Tian, Y.; Cui, W. Semantic Segmentation and Analysis on Sensitive Parameters of Forest Fire Smoke Using Smoke-Unet and Landsat-8 Imagery. Remote Sens. 2022, 14, 45. [Google Scholar] [CrossRef]
- Liu, C.-C.; Zhang, Y.-C.; Chen, P.-Y.; Lai, C.-C.; Chen, Y.-H.; Cheng, J.-H.; Ko, M.-H. Clouds Classification from Sentinel-2 Imagery with Deep Residual Learning and Semantic Image Segmentation. Remote Sens. 2019, 11, 119. [Google Scholar] [CrossRef]
- Ji, W.; Chen, Y.; Li, K.; Dai, X. Multicascaded Feature Fusion-Based Deep Learning Network for Local Climate Zone Classification Based on the So2Sat LCZ42 Benchmark Dataset. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2023, 16, 449–467. [Google Scholar] [CrossRef]
- Ayhan, B.; Kwan, C. Tree, Shrub, and Grass Classification Using Only RGB Images. Remote Sens. 2020, 12, 1333. [Google Scholar] [CrossRef]
- Maxwell, A.E.; Bester, M.S.; Guillen, L.A.; Ramezan, C.A.; Carpinello, D.J.; Fan, Y.; Hartley, F.M.; Maynard, S.M.; Pyron, J.L. Semantic Segmentation Deep Learning for Extracting Surface Mine Extents from Historic Topographic Maps. Remote Sens. 2020, 12, 4145. [Google Scholar] [CrossRef]
- Zhou, G.; Xu, J.; Chen, W.; Li, X.; Li, J.; Wang, L. Deep Feature Enhancement Method for Land Cover With Irregular and Sparse Spatial Distribution Features: A Case Study on Open-Pit Mining. IEEE Trans. Geosci. Remote Sens. 2023, 61, 4401220. [Google Scholar] [CrossRef]
- Lee, S.-H.; Han, K.-J.; Lee, K.; Lee, K.-J.; Oh, K.-Y.; Lee, M.-J. Classification of Landscape Affected by Deforestation Using High-resolution Remote Sensing Data and Deep-learning Techniques. Remote Sens. 2020, 12, 3372. [Google Scholar] [CrossRef]
- Yu, T.; Wu, W.; Gong, C.; Li, X. Residual Multi-Attention Classification Network for a Forest Dominated Tropical Landscape Using High-Resolution Remote Sensing Imagery. ISPRS Int. J. Geoinf. 2021, 10, 22. [Google Scholar] [CrossRef]
- Pashaei, M.; Kamangir, H.; Starek, M.J.; Tissot, P. Review and Evaluation of Deep Learning Architectures for Efficient Land Cover Map** with UAS Hyper-Spatial Imagery: A Case Study over a Wetland. Remote Sens. 2020, 12, 959. [Google Scholar] [CrossRef]
- Fang, B.; Chen, G.; Chen, J.; Ouyang, G.; Kou, R.; Wang, L. Cct: Conditional Co-Training for Truly Unsupervised Remote Sensing Image Segmentation in Coastal Areas. Remote Sens. 2021, 13, 3521. [Google Scholar] [CrossRef]
- Buchsteiner, C.; Baur, P.A.; Glatzel, S. Spatial Analysis of Intra-Annual Reed Ecosystem Dynamics at Lake Neusiedl Using RGB Drone Imagery and Deep Learning. Remote Sens. 2023, 15, 3961. [Google Scholar] [CrossRef]
- Wang, Z.; Mahmoudian, N. Aerial Fluvial Image Dataset for Deep Semantic Segmentation Neural Networks and Its Benchmarks. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2023, 16, 4755–4766. [Google Scholar] [CrossRef]
- Chen, J.; Chen, G.; Wang, L.; Fang, B.; Zhou, P.; Zhu, M. Coastal Land Cover Classification of High-Resolution Remote Sensing Images Using Attention-Driven Context Encoding Network. Sensors 2020, 20, 7032. [Google Scholar] [CrossRef] [PubMed]
- Li, Y.; Zhou, Y.; Zhang, Y.; Zhong, L.; Wang, J.; Chen, J. DKDFN: Domain Knowledge-Guided Deep Collaborative Fusion Network for Multimodal Unitemporal Remote Sensing Land Cover Classification. ISPRS J. Photogramm. Remote Sens. 2022, 186, 170–189. [Google Scholar] [CrossRef]
- Tzepkenlis, A.; Marthoglou, K.; Grammalidis, N. Efficient Deep Semantic Segmentation for Land Cover Classification Using Sentinel Imagery. Remote Sens. 2023, 15, 2027. [Google Scholar] [CrossRef]
- Billson, J.; Islam, M.D.S.; Sun, X.; Cheng, I. Water Body Extraction from Sentinel-2 Imagery with Deep Convolutional Networks and Pixelwise Category Transplantation. Remote Sens. 2023, 15, 1253. [Google Scholar] [CrossRef]
- Bergamasco, L.; Bovolo, F.; Bruzzone, L. A Dual-Branch Deep Learning Architecture for Multisensor and Multitemporal Remote Sensing Semantic Segmentation. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2023, 16, 2147–2162. [Google Scholar] [CrossRef]
- Yang, X.; Zhang, B.; Chen, Z.; Bai, Y.; Chen, P. A Multi-Temporal Network for Improving Semantic Segmentation of Large-Scale Landsat Imagery. Remote Sens. 2022, 14, 5062. [Google Scholar] [CrossRef]
- Yang, X.; Chen, Z.; Zhang, B.; Li, B.; Bai, Y.; Chen, P. A Block Shuffle Network with Superpixel Optimization for Landsat Image Semantic Segmentation. Remote Sens. 2022, 14, 1432. [Google Scholar] [CrossRef]
- Boonpook, W.; Tan, Y.; Nardkulpat, A.; Torsri, K.; Torteeka, P.; Kamsing, P.; Sawangwit, U.; Pena, J.; Jainaen, M. Deep Learning Semantic Segmentation for Land Use and Land Cover Types Using Landsat 8 Imagery. ISPRS Int. J. Geoinf. 2023, 12, 14. [Google Scholar] [CrossRef]
- Bergado, J.R.; Persello, C.; Stein, A. Recurrent Multiresolution Convolutional Networks for VHR Image Classification. IEEE Trans. Geosci. Remote Sens. 2018, 56, 6361–6374. [Google Scholar] [CrossRef]
- Karila, K.; Matikainen, L.; Karjalainen, M.; Puttonen, E.; Chen, Y.; Hyyppä, J. Automatic Labelling for Semantic Segmentation of VHR Satellite Images: Application of Airborne Laser Scanner Data and Object-Based Image Analysis. ISPRS Open J. Photogramm. Remote Sens. 2023, 9, 100046. [Google Scholar] [CrossRef]
- Zhang, X.; Du, L.; Tan, S.; Wu, F.; Zhu, L.; Zeng, Y.; Wu, B. Land Use and Land Cover Map** Using Rapideye Imagery Based on a Novel Band Attention Deep Learning Method in the Three Gorges Reservoir Area. Remote Sens. 2021, 13, 1225. [Google Scholar] [CrossRef]
- Zhu, Y.; Geis, C.; So, E.; **, Y. Multitemporal Relearning with Convolutional LSTM Models for Land Use Classification. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2021, 14, 3251–3265. [Google Scholar] [CrossRef]
- Fan, Z.; Zhan, T.; Gao, Z.; Li, R.; Liu, Y.; Zhang, L.; **, Z.; Xu, S. Land Cover Classification of Resources Survey Remote Sensing Images Based on Segmentation Model. IEEE Access 2022, 10, 56267–56281. [Google Scholar] [CrossRef]
- Clark, A.; Phinn, S.; Scarth, P. Pre-Processing Training Data Improves Accuracy and Generalisability of Convolutional Neural Network Based Landscape Semantic Segmentation. Land 2023, 12, 1268. [Google Scholar] [CrossRef]
- Mohammadimanesh, F.; Salehi, B.; Mahdianpari, M.; Gill, E.; Molinier, M. A New Fully Convolutional Neural Network for Semantic Segmentation of Polarimetric SAR Imagery in Complex Land Cover Ecosystem. ISPRS J. Photogramm. Remote Sens. 2019, 151, 223–236. [Google Scholar] [CrossRef]
- Wenger, R.; Puissant, A.; Weber, J.; Idoumghar, L.; Forestier, G. Multimodal and Multitemporal Land Use/Land Cover Semantic Segmentation on Sentinel-1 and Sentinel-2 Imagery: An Application on a MultiSenGE Dataset. Remote Sens. 2023, 15, 151. [Google Scholar] [CrossRef]
- ** of Very-High Resolution (VHR) Remote Sensing Image. Int. J. Remote Sens. 2021, 42, 3146–3165. [Google Scholar] [CrossRef]
- Liu, M.; Zhang, P.; Shi, Q.; Liu, M. An Adversarial Domain Adaptation Framework with KL-Constraint for Remote Sensing Land Cover Classification. IEEE Geosci. Remote Sens. Lett. 2022, 19, 3002305. [Google Scholar] [CrossRef]
- Lee, D.G.; Shin, Y.H.; Lee, D.C. Land Cover Classification Using SegNet with Slope, Aspect, and Multidirectional Shaded Relief Images Derived from Digital Surface Model. J. Sens. 2020, 2020, 8825509. [Google Scholar] [CrossRef]
- Wang, Y.; Shi, H.; Zhuang, Y.; Sang, Q.; Chen, L. Bidirectional Grid Fusion Network for Accurate Land Cover Classification of High-Resolution Remote Sensing Images. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2020, 13, 5508–5517. [Google Scholar] [CrossRef]
- Shi, H.; Fan, J.; Wang, Y.; Chen, L. Dual Attention Feature Fusion and Adaptive Context for Accurate Segmentation of Very High-Resolution Remote Sensing Images. Remote Sens. 2021, 13, 3715. [Google Scholar] [CrossRef]
- He, S.; Lu, X.; Gu, J.; Tang, H.; Yu, Q.; Liu, K.; Ding, H.; Chang, C.; Wang, N. RSI-Net: Two-Stream Deep Neural Network for Remote Sensing Images-Based Semantic Segmentation. IEEE Access 2022, 10, 34858–34871. [Google Scholar] [CrossRef]
- Yang, N.; Tang, H. Semantic Segmentation of Satellite Images: A Deep Learning Approach Integrated with Geospatial Hash Codes. Remote Sens. 2021, 13, 2723. [Google Scholar] [CrossRef]
- Boguszewski, A.; Batorski, D.; Ziemba-Jankowska, N.; Dziedzic, T.; Zambrzycka, A. LandCover.Ai: Dataset for Automatic Map** of Buildings, Woodlands, Water and Roads from Aerial Imagery. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, Nashville, TN, USA, 20–25 June 2021. [Google Scholar]
- Gao, J.; Weng, L.; ** of Buildings. ISPRS J. Photogramm. Remote Sens. 2019, 147, 42–55. [Google Scholar] [CrossRef]
- Audebert, N.; Le Saux, B.; Lefèvre, S. Segment-before-Detect: Vehicle Detection and Classification through Semantic Segmentation of Aerial Images. Remote Sens. 2017, 9, 368. [Google Scholar] [CrossRef]
- Abdollahi, A.; Pradhan, B.; Shukla, N.; Chakraborty, S.; Alamri, A. Multi-Object Segmentation in Complex Urban Scenes from High-Resolution Remote Sensing Data. Remote Sens. 2021, 13, 3710. [Google Scholar] [CrossRef]
- Khan, S.D.; Alarabi, L.; Basalamah, S. Deep Hybrid Network for Land Cover Semantic Segmentation in High-Spatial Resolution Satellite Images. Information 2021, 12, 230. [Google Scholar] [CrossRef]
- Liu, R.; Tao, F.; Liu, X.; Na, J.; Leng, H.; Wu, J.; Zhou, T. RAANet: A Residual ASPP with Attention Framework for Semantic Segmentation of High-Resolution Remote Sensing Images. Remote Sens. 2022, 14, 3109. [Google Scholar] [CrossRef]
- Sang, Q.; Zhuang, Y.; Dong, S.; Wang, G.; Chen, H. FRF-Net: Land Cover Classification from Large-Scale VHR Optical Remote Sensing Images. IEEE Geosci. Remote Sens. Lett. 2020, 17, 1057–1061. [Google Scholar] [CrossRef]
- Guo, Y.; Wang, F.; ** through Learning with Noise Correction. IEEE Trans. Geosci. Remote Sens. 2022, 60, 4402013. [Google Scholar] [CrossRef]
- Shen, X.; Weng, L.; ** from Historical Orthophotos Using Domain Adaptation and Spatio-Temporal Transfer Learning. Remote Sens. 2022, 14, 5911. [Google Scholar] [CrossRef]
- Zhang, B.; Chen, T.; Wang, B. Curriculum-Style Local-to-Global Adaptation for Cross-Domain Remote Sensing Image Segmentation. IEEE Trans. Geosci. Remote Sens. 2022, 60, 5611412. [Google Scholar] [CrossRef]
- Li, A.; Jiao, L.; Zhu, H.; Li, L.; Liu, F. Multitask Semantic Boundary Awareness Network for Remote Sensing Image Segmentation. IEEE Trans. Geosci. Remote Sens. 2022, 60, 5400314. [Google Scholar] [CrossRef]
- Shan, L.; Wang, W. DenseNet-Based Land Cover Classification Network with Deep Fusion. IEEE Geosci. Remote Sens. Lett. 2022, 19. [Google Scholar] [CrossRef]
- Safarov, F.; Temurbek, K.; Jamoljon, D.; Temur, O.; Chedjou, J.C.; Abdusalomov, A.B.; Cho, Y.-I. Improved Agricultural Field Segmentation in Satellite Imagery Using TL-ResUNet Architecture. Sensors 2022, 22, 9784. [Google Scholar] [CrossRef] [PubMed]
- Liu, Z.-Q.; Tang, P.; Zhang, W.; Zhang, Z. CNN-Enhanced Heterogeneous Graph Convolutional Network: Inferring Land Use from Land Cover with a Case Study of Park Segmentation. Remote Sens. 2022, 14, 5027. [Google Scholar] [CrossRef]
- Wang, D.; Yang, R.; Liu, H.; He, H.; Tan, J.; Li, S.; Qiao, Y.; Tang, K.; Wang, X. HFENet: Hierarchical Feature Extraction Network for Accurate Landcover Classification. Remote Sens. 2022, 14, 4244. [Google Scholar] [CrossRef]
- Zhang, H.; Liu, M.; Wang, Y.; Shang, J.; Liu, X.; Li, B.; Song, A.; Li, Q. Automated Delineation of Agricultural Field Boundaries from Sentinel-2 Images Using Recurrent Residual U-Net. Int. J. Appl. Earth Obs. Geoinf. 2021, 105, 102557. [Google Scholar] [CrossRef]
- Maggiolo, L.; Marcos, D.; Moser, G.; Serpico, S.B.; Tuia, D. A Semisupervised CRF Model for CNN-Based Semantic Segmentation with Sparse Ground Truth. IEEE Trans. Geosci. Remote Sens. 2022, 60, 5606315. [Google Scholar] [CrossRef]
- Barthakur, M.; Sarma, K.K.; Mastorakis, N. Modified Semi-Supervised Adversarial Deep Network and Classifier Combination for Segmentation of Satellite Images. IEEE Access 2020, 8, 117972–117985. [Google Scholar] [CrossRef]
- Wang, Q.; Luo, X.; Feng, J.; Li, S.; Yin, J. CCENet: Cascade Class-Aware Enhanced Network for High-Resolution Aerial Imagery Semantic Segmentation. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2022, 15, 6943–6956. [Google Scholar] [CrossRef]
- Zhang, C.; Zhang, L.; Zhang, B.Y.J.; Sun, J.; Dong, S.; Wang, X.; Li, Y.; Xu, J.; Chu, W.; Dong, Y.; et al. Land Cover Classification in a Mixed Forest-Grassland Ecosystem Using LResU-Net and UAV Imagery. J. Res. 2022, 33, 923–936. [Google Scholar] [CrossRef]
- Xu, Y.; Wu, L.; ** with Convolutional Neural Network: Case Study in Italy. Land 2022, 11, 1919. [Google Scholar] [CrossRef]
- Abadal, S.; Salgueiro, L.; Marcello, J.; Vilaplana, V. A Dual Network for Super-Resolution and Semantic Segmentation of Sentinel-2 Imagery. Remote Sens. 2021, 13, 4547. [Google Scholar] [CrossRef]
- Henry, C.J.; Storie, C.D.; Palaniappan, M.; Alhassan, V.; Swamy, M.; Aleshinloye, D.; Curtis, A.; Kim, D. Automated LULC Map Production Using Deep Neural Networks. Int. J. Remote Sens. 2019, 40, 4416–4440. [Google Scholar] [CrossRef]
- Shojaei, H.; Nadi, S.; Shafizadeh-Moghadam, H.; Tayyebi, A.; Van Genderen, J. An Efficient Built-up Land Expansion Model Using a Modified U-Net. Int. J. Digit. Earth 2022, 15, 148–163. [Google Scholar] [CrossRef]
- Dong, X.; Zhang, C.; Fang, L.; Yan, Y. A Deep Learning Based Framework for Remote Sensing Image Ground Object Segmentation. Appl. Soft Comput. 2022, 130, 109695. [Google Scholar] [CrossRef]
- Guo, X.; Chen, Z.; Wang, C. Fully Convolutional Densenet with Adversarial Training for Semantic Segmentation of High-Resolution Remote Sensing Images. J. Appl. Remote Sens. 2021, 15, 016520. [Google Scholar] [CrossRef]
- Zhang, B.; Wan, Y.; Zhang, Y.; Li, Y. JSH-Net: Joint Semantic Segmentation and Height Estimation Using Deep Convolutional Networks from Single High-Resolution Remote Sensing Imagery. Int. J. Remote Sens. 2022, 43, 6307–6332. [Google Scholar] [CrossRef]
- Li, W.; Chen, K.; Shi, Z. Geographical Supervision Correction for Remote Sensing Representation Learning. IEEE Trans. Geosci. Remote Sens. 2022, 60, 5411520. [Google Scholar] [CrossRef]
- Shi, W.; Qin, W.; Chen, A. Towards Robust Semantic Segmentation of Land Covers in Foggy Conditions. Remote Sens. 2022, 14, 4551. [Google Scholar] [CrossRef]
- Zhang, W.; Tang, P.; Zhao, L. Fast and Accurate Land Cover Classification on Medium Resolution Remote Sensing Images Using Segmentation Models. Int. J. Remote Sens. 2021, 42, 3277–3301. [Google Scholar] [CrossRef]
- Dechesne, C.; Mallet, C.; Le Bris, A.; Gouet-Brunet, V. Semantic Segmentation of Forest Stands of Pure Species Combining Airborne Lidar Data and Very High Resolution Multispectral Imagery. ISPRS J. Photogramm. Remote Sens. 2017, 126, 129–145. [Google Scholar] [CrossRef]
- Zhang, Z.; Lu, W.; Cao, J.; ** Based on Self-Training with Weighted Pseudo-Labels. Int. J. Appl. Earth Obs. Geoinf. 2022, 112, 102931. [Google Scholar] [CrossRef]
- Liu, Q.; Kampffmeyer, M.; Jenssen, R.; Salberg, A.-B. Dense Dilated Convolutions Merging Network for Land Cover Classification. IEEE Trans. Geosci. Remote Sens. 2020, 58, 6309–6320. [Google Scholar] [CrossRef]
- Li, Z.; Zhang, H.; Lu, F.; Xue, R.; Yang, G.; Zhang, L. Breaking the Resolution Barrier: A Low-to-High Network for Large-Scale High-Resolution Land-Cover Map** Using Low-Resolution Labels. ISPRS J. Photogramm. Remote Sens. 2022, 192, 244–267. [Google Scholar] [CrossRef]
- Yuan, Q.; Mohd Shafri, H.Z. Multi-Modal Feature Fusion Network with Adaptive Center Point Detector for Building Instance Extraction. Remote Sens. 2022, 14, 4920. [Google Scholar] [CrossRef]
- Mboga, N.; D’aronco, S.; Grippa, T.; Pelletier, C.; Georganos, S.; Vanhuysse, S.; Wolff, E.; Smets, B.; Dewitte, O.; Lennert, M.; et al. Domain Adaptation for Semantic Segmentation of Historical Panchromatic Orthomosaics in Central Africa. ISPRS Int. J. Geoinf. 2021, 10, 523. [Google Scholar] [CrossRef]
- Zhang, Z.; Doi, K.; Iwasaki, A.; Xu, G. Unsupervised Domain Adaptation of High-Resolution Aerial Images via Correlation Alignment and Self Training. IEEE Geosci. Remote Sens. Lett. 2021, 18, 746–750. [Google Scholar] [CrossRef]
- Simms, D.M. Fully Convolutional Neural Nets In-the-Wild. Remote Sens. Lett. 2020, 11, 1080–1089. [Google Scholar] [CrossRef]
- Liu, C.; Du, S.; Lu, H.; Li, D.; Cao, Z. Multispectral Semantic Land Cover Segmentation from Aerial Imagery with Deep Encoder-Decoder Network. IEEE Geosci. Remote Sens. Lett. 2022, 19, 5000105. [Google Scholar] [CrossRef]
- Sun, P.; Lu, Y.; Zhai, J. Map** Land Cover Using a Developed U-Net Model with Weighted Cross Entropy. Geocarto Int. 2022, 37, 9355–9368. [Google Scholar] [CrossRef]
- Chen, J.; Sun, B.; Wang, L.; Fang, B.; Chang, Y.; Li, Y.; Zhang, J.; Lyu, X.; Chen, G. Semi-Supervised Semantic Segmentation Framework with Pseudo Supervisions for Land-Use/Land-Cover Map** in Coastal Areas. Int. J. Appl. Earth Obs. Geoinf. 2022, 112, 102881. [Google Scholar] [CrossRef]
Data Sources | Number of Articles | References |
---|---|---|
RS Satellites | ||
Sentinel-2 | 7 | [45,64,65,66,67] |
Landsat | 5 | [33,68,69,70] |
Worldview-03 | 2 | [71,72] |
Rapid eye | 1 | [73] |
Worldview-02 | 1 | [74] |
Quickbird | 1 | [74] |
ZY-3 | 1 | [48] |
PlanetScope | 1 | [49] |
GF-2 | 2 | [48,75] |
Aerial images | ||
Phantom m multi-rotor AUS | 1 | [59] |
Quadcopter drone | 1 | [61] |
Vexcel Ultracam Eagle Camera | 1 | [76] |
DJI-Phantom 4 pro UAV | 1 | [47] |
SAR SAT | ||
RADARSAT-2 | 1 | [77] |
Sentinel-1 | 6 | [10,41,43,64,65,78] |
GF-3 | 1 | [79] |
ALOS-2 | 1 | [80] |
Others | ||
Earth digitalglobe | 2 | [44,60] |
Mobile phone | 1 | [35] |
Lidar Sources | 1 | [37] |
Models | Datasets | Performance Metrics | Limitation/Future Work |
---|---|---|---|
RAANet [108] | LoveDA, ISPRS Vaihingen | MIoU = 77.28, MIoU = 73.47 | Accuracy can be improved with optimization. |
PSE-UNet Model [113] | Salinas Dataset | MIoU = 88.50 | Inaccurate segmentation of land cover features with low frequencies, superfluous parameter redundancy, and unvalidated generalization capabilities. |
SEG-ESRGAN [114] | Sentinel-2 and WorldView-2 image pairs. | MIoU = 62.78 | The assessment of utilizing medium-resolution images has not been tested |
Class-wise FCN [26] | Vaihingen, Potsdam | MIoU = 72.35, MIoU = 76.88 | Enhancements in performance can be achieved through class-wise considerations for multiple classes, along with improved and more efficient implementations. |
MARE [115] | Vaihingen | MIoU = 81.76 | Improve performance through parameter optimization and extend approach incorporating other self-supervised algorithms. |
Feature fusion with dual attention and flexible contextual adaptation [94] | Vaihingen, GaoFen-2 | MIoU = 70.51, MIoU = 56.98 | Computational complexity issue. |
Deanet [100] | LandCover.ai, DSTL dataset, DeepGlobe | MIoU = 90.28, MIoU = 52.70, MIoU = 71.80 | Suboptimal performance. Future efforts involve incorporating the spatial attention module into a single unified backbone network. |
An encoder-decoder framework featuring attention-guided multi-scale context integration [116] | GF-2 images | MIoU = 62.3% | Reduced accuracy on imbalance data. |
Models | Data | Performance | Limitation |
---|---|---|---|
Swin-S-GF [117], | GID | OA = 89.15 MIoU = 80.14 | Computational complexity issue and slow convergence speed. |
CG-Swin [119] | Vaihingen, Potsdam | OA = 91.68 MIoU = 83.39, OA = 91.93 MIoU = 87.61 | Extending CG-Swin to accommodate multi-modal data sources for more comprehensive and robust classification. |
BANet [30] | Vaihingen, Potsdam, UAVid dataset | MIoU = 81.35, MIoU = 86.25, MIoU = 64.6 | Combine convolution and Transformer as a hybrid structure to improve performance. |
Spectral spatial transformer [118] | Indian dataset | OA = 0.94 | Computational complexity issue |
Sgformer [18] | Landcover dataset | MIOU = 0.85 | Computational complexity issue and slow convergence speed. |
Parallel Swin Transformer [120] | Postdam, GID WHDLD | OA = 89.44, OA = 84.67, OA = 84.86 | Performance can be improved. |
Models | Datasets | Performance Metrics | Limitation |
---|---|---|---|
RSI-Net [95] | Vaihingen, Potsdam, GID | OA = 91.83, OA = 93.31, OA = 93.67 | Limitation in segmentation of pixel-wise semantics. Enhanced feature map fusion decoders can lead to performance improvements. |
HMRT [32] | Potsdam | OA = 85.99 MIoU = 74.14 | Parameter complexity issue, decrease in segmentation accuracy due to a lot of noise. Optimization is required. |
UNetFormer [19] | UAVid, Vaihingen, Potsdam, LoveDA | MIoU = 67.8, OA = 91.0 MIoU = 82.7, OA = 91.3 MIoU = 86.8, MIoU = 52.4 | Investigate the Transformer’s potential and practicality in addressing geospatial vision tasks is open for research. |
(TL-ResUNet) model [130] | DeepGlobe | IoU = 0.81 | Improve classification performance is open for research, and develo** real time and automated solution for land use land cover. |
CNN-enhanced heterogeneous GCN [131] | Bei**g dataset, Shenzhen dataset. | MIoU = 70.48, MIoU = 62.45 | Future endeavor is to optimize the utilization of pretrained deep CNN features and GCN features across various segmentation scales. |
HFENet [132] | MZData, LandCover Dataset, WHU Building Dataset | MIoU = 87.19, MIoU = 89.69, MIoU = 92.12 | Time and space complexity issues. Future work can be to automatically fine-tune the parameters to attain the optimal performance of the model. |
Model’s Structures | Batch Size | Epochs | Learning Rate | Data Augmentation | Backbone | Popular Optimizer | Parameters | Evaluation Metrics |
---|---|---|---|---|---|---|---|---|
Encoder/decoder-based | 4, 8, 16, 64 | 100–500 | 0.01 | Yes | ResNet | SGD | Low–High | MIoU, OA, F1 |
Transformer-based | 6, 8 | 100–200 | 0.0006 | Yes | ResNet/Swintiny | Adam | High | MIoU, OA, F1 |
Hybrid models | 8, 16 | 40–100 | 0.0006 | Yes | ResNet | Adam | Low–High | MIoU, OA, F1 |
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
Ajibola, S.; Cabral, P. A Systematic Literature Review and Bibliometric Analysis of Semantic Segmentation Models in Land Cover Map**. Remote Sens. 2024, 16, 2222. https://doi.org/10.3390/rs16122222
Ajibola S, Cabral P. A Systematic Literature Review and Bibliometric Analysis of Semantic Segmentation Models in Land Cover Map**. Remote Sensing. 2024; 16(12):2222. https://doi.org/10.3390/rs16122222
Chicago/Turabian StyleAjibola, Segun, and Pedro Cabral. 2024. "A Systematic Literature Review and Bibliometric Analysis of Semantic Segmentation Models in Land Cover Map**" Remote Sensing 16, no. 12: 2222. https://doi.org/10.3390/rs16122222