Mapping Atlantic rainforest degradation and regeneration history with indicator species using convolutional network.

The Atlantic rainforest of Brazil is one of the global terrestrial hotspots of biodiversity. Despite having undergone large scale deforestation, forest cover has shown signs of increases in the last decades. Here, to understand the degradation and regeneration history of Atlantic rainforest remnants near São Paulo, we combine a unique dataset of very high resolution images from Worldview-2 and Worldview-3 (0.5 and 0.3m spatial resolution, respectively), georeferenced aerial photographs from 1962 and use a deep learning method called U-net to map (i) the forest cover and changes and (ii) two pioneer tree species, Cecropia hololeuca and Tibouchina pulchra. For Tibouchina pulchra, all the individuals were mapped in February, when the trees undergo mass-flowering with purple and pink blossoms. Additionally, elevation data at 30m spatial resolution from NASA Shuttle Radar Topography Mission (SRTM) and annual mean climate variables (Terraclimate datasets at ∼ 4km of spatial resolution) were used to analyse the forest and species distributions. We found that natural forests are currently more frequently found on south-facing slopes, likely because of geomorphology and past land use, and that Tibouchina is restricted to the wetter part of the region (southern part), which annually receives at least 1600 mm of precipitation. Tibouchina pulchra was found to clearly indicate forest regeneration as almost all individuals were found within or adjacent to forests regrown after 1962. By contrast, Cecropia hololeuca was found to indicate older disturbed forests, with all individuals almost exclusively found in forest fragments already present in 1962. At the regional scale, using the dominance maps of both species, we show that at least 4.3% of the current region's natural forests have regrown after 1962 (Tibouchina dominated, ∼ 4757 ha) and that ∼ 9% of the old natural forests have experienced significant disturbance (Cecropia dominated).

Spatio-temporal video segmentation with shape growth or shrinkage constraint.

We propose a new method for joint segmentation of monotonously growing or shrinking shapes in a time sequence of noisy images. The task of segmenting the image time series is expressed as an optimization problem using the spatio-temporal graph of pixels, in which we are able to impose the constraint of shape growth or of shrinkage by introducing monodirectional infinite links connecting pixels at the same spatial locations in successive image frames. The globally optimal solution is computed with a graph cut. The performance of the proposed method is validated on three applications: segmentation of melting sea ice floes and of growing burned areas from time series of 2D satellite images, and segmentation of a growing brain tumor from sequences of 3D medical scans. In the latter application, we impose an additional intersequences inclusion constraint by adding directed infinite links between pixels of dependent image structures.

Spectral-spatial classification of hyperspectral data based on a stochastic minimum spanning forest approach.

In this paper, a new method for supervised hyperspectral data classification is proposed. In particular, the notion of stochastic minimum spanning forest (MSF) is introduced. For a given hyperspectral image, a pixelwise classification is first performed. From this classification map, M marker maps are generated by randomly selecting pixels and labeling them as markers for the construction of MSFs. The next step consists in building an MSF from each of the M marker maps. Finally, all the M realizations are aggregated with a maximum vote decision rule in order to build the final classification map. The proposed method is tested on three different data sets of hyperspectral airborne images with different resolutions and contexts. The influences of the number of markers and of the number of realizations M on the results are investigated in experiments. The performance of the proposed method is compared to several classification techniques (both pixelwise and spectral-spatial) using standard quantitative criteria and visual qualitative evaluation.

Segmentation and classification of hyperspectral images using minimum spanning forest grown from automatically selected markers.

A new method for segmentation and classification of hyperspectral images is proposed. The method is based on the construction of a minimum spanning forest (MSF) from region markers. Markers are defined automatically from classification results. For this purpose, pixelwise classification is performed, and the most reliable classified pixels are chosen as markers. Each classification-derived marker is associated with a class label. Each tree in the MSF grown from a marker forms a region in the segmentation map. By assigning a class of each marker to all the pixels within the region grown from this marker, a spectral-spatial classification map is obtained. Furthermore, the classification map is refined using the results of a pixelwise classification and a majority voting within the spatially connected regions. Experimental results are presented for three hyperspectral airborne images. The use of different dissimilarity measures for the construction of the MSF is investigated. The proposed scheme improves classification accuracies, when compared to previously proposed classification techniques, and provides accurate segmentation and classification maps.