Fast Segmentation and Classification of Very High Resolution Remote Sensing Data Using SLIC Superpixels

Abstract

Speed and accuracy are important factors when dealing with time-constraint events for disaster, risk, and crisis-management support. Object-based image analysis can be a time consuming task in extracting information from large images because most of the segmentation algorithms use the pixel-grid for the initial object representation. It would be more natural and efficient to work with perceptually meaningful entities that are derived from pixels using a low-level grouping process (superpixels). Firstly, we tested a new workflow for image segmentation of remote sensing data, starting the multiresolution segmentation (MRS, using ESP2 tool) from the superpixel level and aiming at reducing the amount of time needed to automatically partition relatively large datasets of very high resolution remote sensing data. Secondly, we examined whether a Random Forest classification based on an oversegmentation produced by a Simple Linear Iterative Clustering (SLIC) superpixel algorithm performs similarly with reference to a traditional object-based classification regarding accuracy. Tests were applied on QuickBird and WorldView-2 data with different extents, scene content complexities, and number of bands to assess how the computational time and classification accuracy are affected by these factors. The proposed segmentation approach is compared with the traditional one, starting the MRS from the pixel level, regarding geometric accuracy of the objects and the computational time. The computational time was reduced in all cases, the biggest improvement being from 5 h 35 min to 13 min, for a WorldView-2 scene with eight bands and an extent of 12.2 million pixels, while the geometric accuracy is kept similar or slightly better. SLIC superpixel-based classification had similar or better overall accuracy values when compared to MRS-based classification, but the results were obtained in a fast manner and avoiding the parameterization of the MRS. These two approaches have the potential to enhance the automation of big remote sensing data analysis and processing, especially when time is an important constraint.

A High-Resolution Airborne Color-Infrared Camera Water Mask for the NASA ABoVE Campaign

“…The resulting clusters ranged in size from 20 (small, uniform regions, such as ponds) to 500 pixels (no-data boundaries, featureless water patches or fields) and served as the basis for the classification. Our choice of algorithm and parameters was informed by a previous study [46] and prevents clusters from being larger than the smallest observable water bodies. Next, each processing tile was assigned an optimal global NDWI or NIR threshold as per the connectivity-preserving algorithm of O'Gorman [47].…”

An Open-Source Semi-Automated Processing Chain for Urban Object-Based Classification

“…Segmentation strategies using superpixels could also be investigated for further enhancements, since a new add-on [61] implementing SLIC superpixels method has been developed recently. This approach has provided interesting results in recent research [42].…”

“…Even though this approach could result in oversegmentation in some parts of the scene, some studies [39,41] argue that oversegmentation is preferable to undersegmentation, as the former can be corrected during classification, contrary to the latter. Furthermore, some recent studies [32,42] highlight that oversegmentation, as long as it remains at an admissible level, could be a minor issue in regard to the final classification result. Insofar that the different spatial subsets were well chosen to ensure that they represent the diversity of landscapes in the whole scene, the presence of extreme outliers among the optimized segmentation parameter is an indication that segmentation using a single parameter for the whole scene is not recommended.…”

Toward an operational framework for fine-scale urban land-cover mapping in Wallonia using submeter remote sensing and ancillary vector data

“…Some recent studies argue that oversegmentation is a minor issue that could be corrected during classification, which is not the case of undersegmentation. [47][48][49] Step 3 consists of running the i.segment module of GRASS GIS 50 that implements image segmentation using a region-growing algorithm (an experimental mean-shift algorithm has been recently implemented). The region-growing segmentation uses two parameters: (a) a standardized "threshold" parameter below which segments are merged according to spectral similarity between neighboring objects (tuned in step 2) and (b) a "minsize" parameter entered by the operator that sets the minimum size of segments.…”