Next Article in Journal
A Self-Adaptive Mean Shift Tree-Segmentation Method Using UAV LiDAR Data
Previous Article in Journal
Spectral Imagery Tensor Decomposition for Semantic Segmentation of Remote Sensing Data through Fully Convolutional Networks
Open AccessArticle

Geometry Aware Evaluation of Handcrafted Superpixel-Based Features and Convolutional Neural Networks for Land Cover Mapping Using Satellite Imagery

1
CESBIO, CNES, CNRS, IRD, UPS, Université de Toulouse, 31400 Toulouse, France
2
Centre National d’Etudes Spatiales, 18 avenue Edouard Belin, 31400 Toulouse, France
*
Author to whom correspondence should be addressed.
Remote Sens. 2020, 12(3), 513; https://doi.org/10.3390/rs12030513
Received: 13 November 2019 / Revised: 29 January 2020 / Accepted: 31 January 2020 / Published: 5 February 2020
In land cover mapping at a high spatial resolution, pixel values alone are not always sufficient to recognize the more complex classes. Contextual features (computed with a sliding kernel or other kind of spatial support) can be discriminating for certain land cover classes, for example, different levels of urban density, or classes containing heterogeneous pixels, such as orchards and vineyards. However, the reference data used for training the supervised classifier are almost always sparsely labeled, in other words, not every pixel of the training area is labeled. This makes the selection of an appropriate contextual classification method for land cover mapping problematic. Indeed, the current state-of-the art contextual classification model, the Deep Convolutional Neural Network (D-CNN), encounters issues when the geometry of the desired output is absent from the training set. Data-driven methods like D-CNN rely heavily on the availability of extensive training labels to learn both the feature extraction and classification steps. With a sparse training set, sharp corners are rounded, and thin elongated elements may be either thickened, or entirely lost. Alternatively, there are several methods based on the manual selection of contextual features in a chosen neighborhood, guided by the knowledge of the data and past experience from similar problems. Such approaches should not be as sensitive to sparsely labeled data, as they do not rely on any training data for feature extraction. This paper presents a new process for including contextual information in an image classification scheme: the Histogram Of Auto Context Classes in Superpixels (HACCS), which involves classifying an image using the local class histograms as contextual features. These histograms are calculated within superpixels of different sizes in order to provide a multi-scale characterization of the neighborhood, while preserving the geometry of the image objects. This method is evaluated on two data sets presenting different spatial, temporal, and spectral resolutions, and each case is compared with a D-CNN in terms of class accuracy, but also of the quality of the geometry in the produced map. Experiments on the Sentinel-2 time series show that HACCS provides equivalent thematic accuracy compared to the D-CNN, while exhibiting a higher degree of geometric accuracy. On very high spatial resolution imagery (SPOT-7), the D-CNN provides significantly stronger thematic accuracy, but this comes at the cost of a lower level of geometric accuracy. View Full-Text
Keywords: image processing; image segmentation; superpixel segmentation; contextual features; land cover mapping; satellite image time series image processing; image segmentation; superpixel segmentation; contextual features; land cover mapping; satellite image time series
Show Figures

Graphical abstract

MDPI and ACS Style

Derksen, D.; Inglada, J.; Michel, J. Geometry Aware Evaluation of Handcrafted Superpixel-Based Features and Convolutional Neural Networks for Land Cover Mapping Using Satellite Imagery. Remote Sens. 2020, 12, 513. https://doi.org/10.3390/rs12030513

AMA Style

Derksen D, Inglada J, Michel J. Geometry Aware Evaluation of Handcrafted Superpixel-Based Features and Convolutional Neural Networks for Land Cover Mapping Using Satellite Imagery. Remote Sensing. 2020; 12(3):513. https://doi.org/10.3390/rs12030513

Chicago/Turabian Style

Derksen, Dawa; Inglada, Jordi; Michel, Julien. 2020. "Geometry Aware Evaluation of Handcrafted Superpixel-Based Features and Convolutional Neural Networks for Land Cover Mapping Using Satellite Imagery" Remote Sens. 12, no. 3: 513. https://doi.org/10.3390/rs12030513

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop