Vegetation Detection Using Deep Learning and Conventional Methods
"> Figure 1
<p>Block diagram showing the used dataset and applied methods. mIoU is the mean-intersection-of-union metric.</p> "> Figure 2
<p>Sample images from Vasiliko dataset and their annotations (silver color corresponds to barren land, green color corresponds to tree/shrub/grass, red color corresponds to urban land, and blue color corresponds to water in land cover map annotations). (<b>a</b>) Color image for mari_20_3_8; (<b>b</b>) ground truth land cover map for mari_20_3_8; (<b>c</b>) color image for mari_20_42_4; (<b>d</b>) ground truth land cover map for mari_20_42_4.</p> "> Figure 3
<p>The color Kimisala images for the 10 and 20 cm resolutions and their ground truth land cover annotations (yellow: Vegetation (tree/shrub), blue: Non-vegetation (barren land and archaeological sites)). (<b>a</b>) Color image (Kimisala-10); (<b>b</b>) color image (Kimisala-20); (<b>c</b>) land cover map (Kimisala-10); (<b>d</b>) land cover map (Kimisala-20).</p> "> Figure 4
<p>Block diagram of DeepLabV3+ [<a href="#B42-remotesensing-12-02502" class="html-bibr">42</a>].</p> "> Figure 5
<p>Our customized convolutional neural network (CNN) model structure.</p> "> Figure 6
<p>Block diagram for the NDVI-ML method.</p> "> Figure 7
<p>DeepLabV3+ vegetation detection results for the two Kimisala test images using the model trained with the Vasiliko dataset. (<b>a</b>) DeepLabV3+ results for Kimisala-10 (green: Tree/shrub/grass, silver: Barren land, red: urban land); (<b>b</b>) DeepLabV3+ results for Kimisala-20 (green: Tree/shrub/grass, silver: Barren land, red: urban land); (<b>c</b>) DeepLabV3+ estimated vegetation map for Kimisala-10 (yellow: Vegetation, blue: Non-vegetation); (<b>d</b>) DeepLabV3+ estimated vegetation map Kimisala-20 (yellow: Vegetation, blue: Non-vegetation); (<b>e</b>) detected vegetation with DeepLabV3+ for Kimisala-10; (<b>f</b>) detected vegetation with DeepLabV3+ for Kimisala-20.</p> "> Figure 8
<p>The total loss plot for DeepLabV3+ model training from scratch for NDVI-GB bands.</p> "> Figure 9
<p>The total loss plot for DeepLabV3+ model training with the NDVI band replaced with the R band and with the pre-trained RGB model as the initial model.</p> "> Figure 10
<p>CNN vegetation detection results for the Kimisala-20 test image using the CNN model trained with the Vasiliko dataset. (<b>a</b>) Estimated vegetation binary map Kimisala-20 using CNN (yellow: Vegetation, blue: Non-vegetation); (<b>b</b>) detected vegetation using CNN for Kimisala-20.</p> "> Figure 11
<p>NDVI only (threshold = 0) vegetation detection results for the two Kimisala test images. (<b>a</b>) NDVI-only estimated vegetation map (Kimisala-10) (yellow: Vegetation, blue: Non-vegetation); (<b>b</b>) NDVI-only estimated vegetation map (Kimisala-20) (yellow: Vegetation, blue: Non-vegetation); (<b>c</b>) Detected vegetation with NDVI only (Kimisala-10); (<b>d</b>) Detected vegetation with NDVI only (Kimisala-20).</p> "> Figure 12
<p>NDVI + ML vegetation detection results for the two Kimisala test images. (<b>a</b>) NDVI + ML estimated vegetation map (Kimisala-10) (yellow: Vegetation, blue: Non-vegetation); (<b>b</b>) NDVI + ML estimated vegetation map (Kimisala-20) (yellow: Vegetation, blue: Non-vegetation); (<b>c</b>) detected vegetation with NDVI + ML (Kimisala-10); (<b>d</b>) detected vegetation with NDVI + ML (Kimisala-20).</p> "> Figure 13
<p>Zoomed in section of Vasiliko (training) and Kimisala (test) images.</p> ">
Abstract
:1. Introduction
- We introduced a novel object-based vegetation detection method, NDVI-ML, which utilized NDVI, computer vision, and machine learning techniques with no need for training. The method is simple and outperformed the two investigated deep learning methods in detection performance.
- We demonstrated the potential use of the NDVI band image as a replacement to the red (R) band in the color image for DeepLabV3+ model training to take advantage of the NIR band while fulfilling the three-input channels restriction in DeepLabV3+ and transfer learning from a pre-trained RGB model.
- We compared the detection performances of DeepLabV3+ (RGB and NDVI-GB bands), our CNN-based deep learning method (RGB and RGB-NIR bands), and NDVI-ML (RGB-NIR). This demonstrated that DeepLabV3+ detection results using RGB color bands only were better than those obtained by conventional methods using the NDVI index only and were also quite close to NDVI-ML’s results which used NIR band and several sophisticated machine learning and computer vision techniques.
- We discussed the underlying reasons why NDVI-ML could be performing better than the deep learning methods and potential strategies to further boost the deep learning methods’ performances.
2. Materials and Methods
2.1. Dataset Used for Training and Testing
2.1.1. Vasiliko Site Data Used for Training
2.1.2. Kimisala Site Data Used for Testing
2.2. DeepLabV3+
2.3. CNN Model
2.4. NDVI-ML
2.5. Performance Comparison Metrics
3. Results
3.1. DeepLabV3+
Results Using DeepLabV3+ Model Trained with Vasiliko Dataset
3.2. CNN Results
3.3. NDVI-ML Results
3.4. Performance Comparisons
4. Discussion
5. Conclusions
Author Contributions
Funding
Conflicts of Interest
References
- Kwan, C.; Gribben, D.; Ayhan, B.; Bernabe, S.; Plaza, A.; Selva, M. Improving Land Cover Classification Using Extended Multi-Attribute Profiles (EMAP) Enhanced Color, Near Infrared, and LiDAR Data. Remote Sens. 2020, 12, 1392. [Google Scholar] [CrossRef]
- Tan, K.; Zhang, Y.; Wang, X.; Chen, Y. Object-Based Change Detection Using Multiple Classifiers and Multi-Scale Uncertainty Analysis. Remote Sens. 2019, 11, 359. [Google Scholar] [CrossRef] [Green Version]
- Skarlatos, D.; Vlachos, M. Vegetation removal from UAV derived DSMS, using combination of RGB and NIR imagery. ISPRS Ann. Photogramm. Remote Sens. Spat. Inf. Sci. 2018, IV-2, 255–262. [Google Scholar]
- Hellesen, T.; Matikainen, L. An Object-Based Approach for Mapping Shrub and Tree Cover on Grassland Habitats by Use of LiDAR and CIR Orthoimages. Remote Sens. 2013, 5, 558–583. [Google Scholar] [CrossRef] [Green Version]
- Ayhan, B.; Kwan, C.; Kwan, L.; Skarlatos, D.; Vlachos, M. Deep learning models for accurate vegetation classification using RGB image only. In Proceedings of the Geospatial Informatics X (Conference SI113), Anaheim, CA, USA, 21 April 2020. [Google Scholar]
- Ayhan, B.; Kwan, C. A Comparative Study of Two Approaches for UAV Emergency Landing Site Surface Type Estimation. In Proceedings of the 44th Annual Conference of the IEEE Industrial Electronics Society, Washington, DC, USA, 21–23 October 2018. [Google Scholar]
- Ayhan, B.; Kwan, C.; Budavari, B.; Larkin, J.; Gribben, D. Semi-automated emergency landing site selection approach for UAVs. IEEE Trans. Aerosp. Electron. Syst. 2019, 55, 1892–1906. [Google Scholar] [CrossRef]
- Guirado, E.; Tabik, S.; Alcaraz-Segura, D.; Cabello, J.; Herrera, F. Deep-learning versus OBIA for scattered shrub detection with Google earth imagery: Ziziphus Lotus as case study. Remote Sens. 2017, 9, 1220. [Google Scholar] [CrossRef] [Green Version]
- Lindgren, D. Land Use Planning and Remote Sensing; Taylor & Francis: Milton, UK, 1984; Volume 2. [Google Scholar]
- Yang, L.; Wu, X.; Praun, E.; Ma, X. Tree detection from aerial imagery. In Proceedings of the 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, Seattle, WA, USA, 4–6 November 2009; pp. 131–137. [Google Scholar]
- Bradley, D.M.; Unnikrishnan, R.; Bagnell, J. Vegetation detection for driving in complex environments. In Proceedings of the 2007 IEEE International Conference on Robotics and Automation, Roma, Italy, 10–14 April 2007; pp. 503–508. [Google Scholar]
- Zare, A.; Bolton, J.; Gader, P.; Schatten, M. Vegetation mapping for landmine detection using long-wave hyperspectral imagery. IEEE Trans. Geosci. Remote Sens. 2007, 46, 172–178. [Google Scholar] [CrossRef]
- Miura, T.; Huete, A.R.; Van Leeuwen, W.J.D.; Didan, K. Vegetation detection through smoke-filled AVIRIS images: An assessment using MODIS band passes. J. Geophys. Res. Atmos. 1998, 103, 32001–32011. [Google Scholar] [CrossRef]
- Gandhi, G.M.; Parthiban, S.; Thummalu, N.; Christy, A. Ndvi: Vegetation change detection using remote sensing and gis–A case study of Vellore District. Procedia Comput. Sci. 2015, 57, 1199–1210. [Google Scholar] [CrossRef] [Green Version]
- Bhandari, A.K.; Kumar, A.; Singh, G.K. Feature extraction using Normalized Difference Vegetation Index (NDVI): A case study of Jabalpur city. Procedia Technol. 2012, 6, 612–621. [Google Scholar] [CrossRef] [Green Version]
- Zhou, H.; Van Rompaey, A. Detecting the impact of the “Grain for Green” program on the mean annual vegetation cover in the Shaanxi province, China using SPOT-VGT NDVI data. Land Use Policy 2009, 26, 954–960. [Google Scholar] [CrossRef]
- Gates, D.M. Biophysical Ecology; Springer: New York, NY, USA, 1980; p. 611. [Google Scholar]
- Salamati, N.; Larlus, D.; Csurka, G.; Süsstrunk, S. Incorporating near-infrared information into semantic image segmentation. arXiv 2014, arXiv:1406.6147. [Google Scholar]
- Senecal, J.J.; Sheppard, J.W.; Shaw, J.A. Efficient Convolutional Neural Networks for Multi-Spectral Image Classification. In Proceedings of the 2019 International Joint Conference on Neural Networks (IJCNN), Budapest, Hungary, 14–19 July 2019; pp. 1–8. [Google Scholar]
- Zhang, X.; Han, L.; Han, L.; Zhu, L. How Well Do Deep Learning-Based Methods for Land Cover Classification and Object Detection Perform on High Resolution Remote Sensing Imagery? Remote Sens. 2020, 12, 417. [Google Scholar] [CrossRef] [Green Version]
- Audebert, N.; Saux, B.L.; Lefevre, S. Semantic Segmentation of Earth Observation Data Using Multimodal and Multi-scale Deep Networks. arXiv 2016, arXiv:1609.06846. [Google Scholar]
- Huang, B.; Zhao, B.; Song, Y. Urban land-use mapping using a deep convolutional neural network with high spatial resolution multispectral remote sensing imagery. Remote Sens. Environ. 2018, 214, 73–86. [Google Scholar] [CrossRef]
- Kemker, R.; Salvaggio, C.; Kanan, C. Algorithms for Semantic Segmentation of Multispectral Remote Sensing Imagery using Deep Learning. ISPRS J. Photogramm. Remote Sens. 2018, 145, 60–77. [Google Scholar] [CrossRef] [Green Version]
- Zheng, C.; Wang, L. Semantic Segmentation of Remote Sensing Imagery Using Object-Based Markov Random Field Model With Regional Penalties. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2015, 8, 1924–1935. [Google Scholar] [CrossRef]
- Chen, L.-C.; Papandreou, G.; Kokkinos, K.; Murphy, K.; Yuille, A.L. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans. Pattern Anal. Mach. Intell. 2017, 40, 834–848. [Google Scholar] [CrossRef]
- Available online: http://host.robots.ox.ac.uk:8080/leaderboard/displaylb.php?cls=mean&challengeid=11&compid=6&submid=15347#KEY_DeepLabv3+_JFT (accessed on 10 April 2020).
- Zhao, H.; Shi, J.; Qi, X.; Wang, X.; Jia, J. Pyramid scene parsing network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017. [Google Scholar]
- Vijay, B.; Kendall, A.; Cipolla, R. Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 2017, 39, 2481–2495. [Google Scholar]
- Zhou, B.; Zhao, H.; Puig, X.; Fidler, S.; Barriuso, A.; Torralba, A. Scene parsing through ade20k dataset. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017; pp. 633–641. [Google Scholar]
- Du, Z.; Yang, J.; Ou, C.; Zhang, T. Smallholder Crop Area Mapped with a Semantic Segmentation Deep Learning Method. Remote Sens. 2019, 11, 888. [Google Scholar] [CrossRef] [Green Version]
- Wang, J.; Shen, L.; Qiao, W.; Dai, Y.; Li, Z. Deep feature fusion with integration of residual connection and attention model for classification of VHR remote sensing images. Remote Sens. 2019, 11, 1617. [Google Scholar] [CrossRef] [Green Version]
- Shang, R.; Zhang, J.; Jiao, L.; Li, Y.; Marturi, N.; Stolkin, R. Multi-scale Adaptive Feature Fusion Network for Semantic Segmentation in Remote Sensing Images. Remote Sens. 2020, 12, 872. [Google Scholar] [CrossRef] [Green Version]
- Ding, L.; Tang, H.; Bruzzone, L. Improving Semantic Segmentation of Aerial Images Using Patch-based Attention. arXiv 2019, arXiv:1911.08877. [Google Scholar]
- Torres, D.L.; Feitosa, R.Q.; Happ, P.N.; Rosa, L.E.C.L.; Junior, J.M.; Martins, J.; Bressan, P.O.; Gonçalves, W.N.; Liesenberg, V. Applying Fully Convolutional Architectures for Semantic Segmentation of a Single Tree Species in Urban Environment on High Resolution UAV Optical Imagery. Sensors 2020, 20, 563. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Huang, S.; Nex, F.; Lin, Y.; Yang, M.Y. Semantic segmentation of building in airborne images. Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. 2019, 42, 35–42. [Google Scholar] [CrossRef] [Green Version]
- Example Dataset of EOPatches for Slovenia. 2017. Available online: http://eo-learn.sentinel-hub.com/ (accessed on 10 April 2020).
- Demir, I.; Koperski, K.; Lindenbaum, D.; Pang, G.; Huang, J.; Basu, S.; Raskar, R.D. A challenge to parse the earth through satellite images. arXiv 2018, arXiv:1805.06561. [Google Scholar]
- Perez, D.; Banerjee, D.; Kwan, C.; Dao, M.; Shen, Y.; Koperski, K.; Marchisio, G.; Li, J. Deep Learning for Effective Detection of Excavated Soil Related to Illegal Tunnel Activities. In Proceedings of the IEEE Ubiquitous Computing Electronics and Mobile Communication Conference, New York, NY, USA, 19–21 October 2017; pp. 626–632. [Google Scholar]
- Lu, Y.; Koperski, K.; Kwan, C.; Li, J. Deep Learning for Effective Refugee Tent Extraction Near Syria-Jordan Border. IEEE Geosci. Remote Sens. Lett. Early Access 2020. [Google Scholar] [CrossRef]
- Kwan, C.; Ayhan, B.; Budavari, B.; Lu, Y.; Perez, D.; Li, J.; Bernabe, S.; Plaza, A. Deep Learning for Land Cover Classification Using Only a Few Bands. Remote Sens. 2020, 12, 2000. [Google Scholar] [CrossRef]
- Transfer Learning from RGB to Multi-Band Imagery. Available online: https://www.azavea.com/blog/2019/08/30/transfer-learning-from-rgb-to-multi-band-imagery/ (accessed on 10 April 2020).
- Chen, L.C.; Zhu, Y.; Papandreou, G.; Schroff, F.; Adam, H. Encoder-decoder with atrous separable convolution for semantic image segmentation. In Proceedings of the European Conference on Computer vision (ECCV), Munich, Germany, 8–14 September 2018; pp. 801–818. [Google Scholar]
- Srivastava, N.; Hinton, G.; Krizhevsky, A.; Sutskever, I.; Salakhutdinov, R. Dropout: A simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 2014, 15, 1929–1958. [Google Scholar]
- Rouse, J.W.; Haas, R.H.; Schell, J.A.; Deering, D.W. Monitoring vegetation systems in the Great Plains with ERTS. NASA Spec. Publ. 1974, 1, 309–317. [Google Scholar]
- Pothen, A.; Fan, C.J. Computing the block triangular form of a sparse matrix. ACM Trans. Math. Softw. (TOMS) 1990, 16, 303–324. [Google Scholar] [CrossRef]
- MathWorks Image Processing Toolbox. Available online: https://www.mathworks.com/help/images/ref/bwconncomp.html (accessed on 10 April 2020).
- Reynolds, D.A.; Quatieri, T.F.; Dunn, R.B. Speaker verification using adapted Gaussian mixture models. Digit. Signal. Process. 2000, 10, 19–41. [Google Scholar] [CrossRef] [Green Version]
- Mathworks Computer Vision Toolbox, Evaluate Semantic Segmentation Data Set against Ground Truth. Available online: https://www.mathworks.com/help/vision/ref/evaluatesemanticsegmentation.html (accessed on 10 April 2020).
- Tensorflow Models, DeepLabV3+ Training Details. Available online: https://github.com/tensorflow/models/issues/4345 (accessed on 10 April 2020).
- Ayhan, B.; Kwan, C. Tree, Shrub, and Grass Classification Using Only RGB Images. Remote Sens. 2020, 12, 1333. [Google Scholar] [CrossRef] [Green Version]
Training Parameter | Value |
---|---|
Learning policy | Poly |
Base learning rate | 0.0001 |
Learning rate decay factor | 0.1 |
Learning rate decay step | 2000 |
Learning power | 0.9 |
Training number of steps | ≥100,000 |
Momentum | 0.9 |
Train batch size | 2 |
Weight decay | 0.00004 |
Train crop size | ‘513,513’ |
Last layer gradient multiplier | 1 |
Upsample logits | True |
Drop path keep prob | 1 |
tf_initial_checkpoint | deeplabv3_pascal_train_aug |
initialize_last_layer | False |
last_layers_contain_logits_only | True |
slow_start_step | 0 |
slow_start_learning_rate | 1 × 10−4 |
fine_tune_batch_norm | False |
min_scale_factor | 0.5 |
max_scale_factor | 2 |
scale_factor_step_size | 0.25 |
atrous_rates | [6,12,18] |
output_stride | 16 |
1: for Each connected component vegetation object, ccvo, |
2: if number of pixels in ccvo < minVegObj, |
3: Assign ccvo pixels as “Non-vegetation” in its sub-vegetation map |
4: end |
5: if minVegObj < number of pixels in ccvo < medVegObj, |
6: Find the pixels in ccvo with red content (R) > green content (G), or blue content (B) > green content (G) |
7: Remove these identified pixels from ccvo |
8: Assign all the remaining pixels in ccvo as “Vegetation” in its sub-vegetation map |
9: end |
10: if number of pixels in ccvo > medVegObj, |
11: Identify the pixels in ccvo with red content (R)>green content(G), or blue content(B)>green content (G) |
12: Label the identified pixels as “Non-vegetation” in its sub-vegetation map |
13: Exclude the identified pixels from ccvo |
14: if the number of pixels in ccvo > minGMM |
15: Fit a two-class GMM to split ccvo pixels into “Vegetation” and “Non-vegetation” classes |
16: Assign the class with lower green content (G) as “Non-vegetation”, higher (G) content as “Vegetation” |
17: if (averaged green content difference in Vegetation and Non-vegetation class) > thrGMMGreen |
18: Extract spatial information of the identified Non-vegetation pixels to decide whether they are shadow-related Non-vegetation pixels or dark-toned Vegetation pixels which are located inside the vegetation object. |
19: - Apply a 5x5 average filter to the Non-vegetation class pixels to form spatial statistical features |
20: - Apply a two-class GMM to the spatial features to split them into two classes, Dark-toned vegetation and Shadow. |
21: - Among the two GMM classes, assign the one with the lower green content as Non-vegetation. |
22: Exclude the identified Non-vegetation pixels from ccvo |
23: Apply a closing morphology operation to ccvo |
24: Assign the remaining pixels in ccvo after closing operation as “Vegetation” in its sub-veg. map |
25: else |
26: Apply a closing morphology operation to ccvo |
27: Assign the remaining pixels in ccvo after closing operation as “Vegetation” in its sub-veg. map |
28: end |
29: else |
30: Apply a closing morphology operation to ccvo pixels |
31: Assign the remaining pixels in ccvo after closing operation as “Vegetation” in its sub-veg. map |
32: end |
33: end |
34: Generate final vegetation map using all sub-veg. maps |
1: Find the connected component vegetation objects in the final vegetation map |
2: for Each connected component, |
3: if the number of pixels in the connected component < minVegObj, |
4: Label all pixels of the connected component to Non-vegetation |
5: else |
6: Compute the mean RGB values for the pixels of the connected component |
7: if (R) or (B) content in the mean RGB values of the connected component is higher than (G) content, |
8: Label the pixels of the connected component as “Non-vegetation” |
9: else |
10: Label the pixels of the connected component as “Vegetation” |
11: end |
12: end |
13: end |
Method | Accuracy | mIoU (Vegetation & Non-Vegetation) |
---|---|---|
DeepLabV3+ (model trained with Slovenia) [5] | 0.6171 | 0.4454 |
DeepLabV3+ (model trained with DeepGlobe [5] | Very poor | Very poor |
DeepLabV3+ (model trained with Vasiliko) | 0.8578 | 0.7435 |
Method | Accuracy | mIoU (Vegetation & Non-Vegetation) |
---|---|---|
DeepLabV3+ (model trained with Slovenia) [5] | 0.6304 | 0.4355 |
DeepLabV3+ (model trained with DeepGlobe) [5] | Very poor | Very poor |
DeepLabV3+ (model trained with Vasiliko) | 0.8015 | 0.6541 |
Test Dataset | Method | Accuracy | mIoU |
---|---|---|---|
Kimisala-10 | DeepLabV3+ (model trained with Vasiliko, RGB) | 0.8578 | 0.7435 |
DeepLabV3+ (model trained with Vasiliko, NDVI-G-B | 0.8601 | 0.7495 | |
Kimisala-20 | DeepLabV3+ (model trained with Vasiliko, RGB) | 0.8015 | 0.6541 |
DeepLabV3+ (model trained with Vasiliko, NDVI-G-B | 0.8089 | 0.6677 |
Bands | Patch Size | Training Data Per Class | Overall Accuracy |
---|---|---|---|
RGB and NIR (4 bands) | 7 × 7 | 30,000 | 0.8091 |
RGB (3 bands) | 7 × 7 | 30,000 | 0.7620 |
Quadrant | Accuracy | mIoU |
---|---|---|
Q1 | 0.8126 | 0.6979 |
Q2 | 0.8342 | 0.6775 |
Q3 | 0.8470 | 0.7041 |
Q4 | 0.8253 | 0.6861 |
Avg | 0.8298 | 0.6914 |
Method | Accuracy | mIoU (Vegetation & Non-Vegetation) |
---|---|---|
NDVI only (NDVI threshold = 0.0) | 0.7565 | 0.6047 |
NDVI only (NDVI threshold = 0.09) | 0.7234 | 0.5662 |
NDVI - ML | 0.8730 | 0.7737 |
Method | Accuracy | mIoU (Vegetation & Non-Vegetation) |
---|---|---|
NDVI only (NDVI threshold = 0.0) | 0.7563 | 0.6045 |
NDVI only (NDVI threshold = 0.09) | 0.7232 | 0.5659 |
NDVI - ML | 0.8578 | 0.7487 |
Method | Accuracy | mIoU (Vegetation & Non-Vegetation) |
---|---|---|
NDVI only (NDVI threshold = 0.0) | 0.7565 | 0.6047 |
NDVI only (NDVI threshold = 0.09) | 0.7234 | 0.5662 |
NDVI - ML (4 bands, RGB+NIR) | 0.8730 | 0.7737 |
DeepLabV3+ (model trained with Slovenia, RGB) [5] | 0.6171 | 0.4454 |
DeepLabV3+ (model trained with DeepGlobe, RGB [5]) | Very poor | Very poor |
DeepLabV3+ (model trained with Vasiliko, RGB) [5] | 0.8578 | 0.7435 |
DeepLabV3+ (model trained with Vasiliko, NDVI-G-B) | 0.8601 | 0.7495 |
Method | Accuracy | mIoU (Vegetation & Non-Vegetation) |
---|---|---|
NDVI only (NDVI threshold = 0.0) | 0.7563 | 0.6045 |
NDVI only (NDVI threshold = 0.09) | 0.7232 | 0.5659 |
NDVI - ML (4 bands, RGB+NIR) | 0.8578 | 0.7487 |
DeepLabV3+ (model trained with Slovenia, RGB) [5] | 0.6304 | 0.4355 |
DeepLabV3+ (model trained with DeepGlobe, RGB) [5] | Very poor | Very poor |
DeepLabV3+ (model trained with Vasiliko, RGB) [5] | 0.8015 | 0.6541 |
DeepLabV3+ (model trained with Vasiliko, NDVI-G-B) | 0.8089 | 0.6677 |
Our customized CNN (4 bands, RGB+NIR) | 0.8298 | 0.6914 |
© 2020 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 (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Ayhan, B.; Kwan, C.; Budavari, B.; Kwan, L.; Lu, Y.; Perez, D.; Li, J.; Skarlatos, D.; Vlachos, M. Vegetation Detection Using Deep Learning and Conventional Methods. Remote Sens. 2020, 12, 2502. https://doi.org/10.3390/rs12152502
Ayhan B, Kwan C, Budavari B, Kwan L, Lu Y, Perez D, Li J, Skarlatos D, Vlachos M. Vegetation Detection Using Deep Learning and Conventional Methods. Remote Sensing. 2020; 12(15):2502. https://doi.org/10.3390/rs12152502
Chicago/Turabian StyleAyhan, Bulent, Chiman Kwan, Bence Budavari, Liyun Kwan, Yan Lu, Daniel Perez, Jiang Li, Dimitrios Skarlatos, and Marinos Vlachos. 2020. "Vegetation Detection Using Deep Learning and Conventional Methods" Remote Sensing 12, no. 15: 2502. https://doi.org/10.3390/rs12152502