EN FR
EN FR
New Software and Platforms
Bilateral Contracts and Grants with Industry
Bibliography
New Software and Platforms
Bilateral Contracts and Grants with Industry
Bibliography


Section: New Results

Semantic Segmentation for Remote Sensing Data

Participants: Maria Papadomanolaki, Maria Vakalopoulou (in collaboration with Christina Karakizi, Georgia Antoniou, Konstantinos Karantzalos, Nikos Paragios; National Technical University of Athens, Therapanacea)

Detailed, accurate and frequent land cover mapping is a prerequisite for several important geospatial applications and the fulfilment of current sustainable development goals. This work [9] introduces a methodology for the classification of annual high-resolution satellite data into several detailed land cover classes. In particular, a nomenclature with 27 different classes was introduced based on CORINE Land Cover (CLC) Level-3 categories and further analysing various crop types. Without employing cloud masks and/or interpolation procedures, we formed experimental datasets of Landsat-8 (L8) images with gradually increased cloud cover in order to assess the influence of cloud presence on the reference data and the resulting classification accuracy. The performance of shallow kernel-based and deep patch-based machine learning classification frameworks was evaluated. Quantitatively, the resulting overall accuracy rates differed within a range of less than 3%; however, maps produced based on Support Vector Machines (SVM) were more accurate across class boundaries and the respective framework was less computationally expensive compared to the applied patch-based deep Convolutional Neural Network (CNN). Further experimental results and analysis indicated that employing all multitemporal images with up to 30% cloud cover delivered relatively higher overall accuracy rates as well as the highest per-class accuracy rates. Moreover, by selecting 70% of the top-ranked features after applying a feature selection strategy, slightly higher accuracy rates were achieved. A detailed discussion of the quantitative and qualitative evaluation outcomes further elaborates on the performance of all considered classes and highlights different aspects of their spectral behaviour and separability.

Moreover, semantic segmentation is a mainstream method in several remote sensing applications based on very-high-resolution data, achieving recently remarkable performance by the use of deep learning and more specifically, pixel-wise dense classification models. In this work [36], we exploit the use of a relatively deep architecture based on repetitive downscale upscale processes that had been previously employed for human pose estimation. By integrating such a model, we are aiming to capture low-level details, such as small objects, object boundaries and edges. Experimental results and quantitative evaluation has been performed on the publicly available ISPRS (WGIII/4) benchmark dataset indicating the potential of the proposed approach.