Semantic Segmentation of High-Resolution Airborne Images with Dual-Stream DeepLabV3
Bibliographic Data
| ID | 22031332 |
|---|---|
| Authors | Ozgun Akcay (0000-0003-0474-7518, Çanakkale Onsekiz Mart Üniversitesi, corresponding author), Ahmet Cumhur Kinaci (0000-0002-8832-5453, Çanakkale Onsekiz Mart Üniversitesi), Emin Ozgur Avsar (0000-0002-3804-1209, Çanakkale Onsekiz Mart Üniversitesi), Umut Aydar (0000-0002-3987-6435, Çanakkale Onsekiz Mart Üniversitesi) |
| Year | 2021 |
| Volume | 11 |
| Issue | 1 |
| Pages | 23 |
| Publication date | 2021-12-30 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | ISPRS International Journal of Geo-Information (JOURNAL) |
| Journal identifiers | ISSN: 2220-9964 • E-ISSN: 2220-9964 |
| Publisher | MDPI AG (PUBLISHER • IT) |
| DOI | 10.3390/ijgi11010023 |
| OpenAlex | W4206356281 |
| Language | EN |
| Citations received | 1 |
| References cited | 38 |
In geospatial applications such as urban planning and land use management, automatic detection and classification of earth objects are essential and primary subjects. When the significant semantic segmentation algorithms are considered, DeepLabV3+ stands out as a state-of-the-art CNN. Although the DeepLabV3+ model is capable of extracting multi-scale contextual information, there is still a need for multi-stream architectural approaches and different training approaches of the model that can leverage multi-modal geographic datasets. In this study, a new end-to-end dual-stream architecture that considers geospatial imagery was developed based on the DeepLabV3+ architecture. As a result, the spectral datasets other than RGB provided increments in semantic segmentation accuracies when they were used as additional channels to height information. Furthermore, both the given data augmentation and Tversky loss function which is sensitive to imbalanced data accomplished better overall accuracies. Also, it has been shown that the new dual-stream architecture using Potsdam and Vaihingen datasets produced 88.87% and 87.39% overall semantic segmentation accuracies, respectively. Eventually, it was seen that enhancement of the traditional significant semantic segmentation networks has a great potential to provide higher model performances, whereas the contribution of geospatial data as the second stream to RGB to segmentation was explicitly shown
Computer vision · Geography · Geospatial analysis · Image segmentation · Remote sensing · RGB color model · Scale-space segmentation · Segmentation · Advanced Image Fusion Techniques · Advanced Neural Network Applications · Computer Science · Remote-Sensing Image Classification · Artificial Intelligence
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
The Cityscapes Dataset for Semantic Urban Scene Understanding
Support-Vector Networks
Mask R-CNN
A survey on Image Data Augmentation for Deep Learning
DeepLab
Random Forests
Machine Learning of Spatial Data
Semantic Segmentation of Remote-Sensing Imagery Using Heterogeneous Big Data
| Citations per year | 0.33 |
|---|---|
| Citation span | 2023 - 2023 (1) |
| Highly cited | No |