Search

This paper presents a novel approach for estimating wheat yields based on estimated abundances of endmembers attributed to photosynthetic pigments, using Landsat 8 images acquired during maximum greenness. Endmembers within the wheat pixels are found using an unmixing algorithm then they are further optimized to maximize the predictive power of the abundances for the yields. Similarity of the endmembers to photosynthetic pigment's spectral signatures and their predictive power suggests their relevance to the pigments. Although the initial unmixing of the intimate mixture of photosynthetic pigments is linear, interactions of abundances are used in the optimization to handle the non-linearity using bilinear model. Wheat yields are estimated with abundances, their relevant interactions, agrometeorological parameters and vegetation indices using three machine learning algorithms. Harvester records from 142 fields are used as ground truth for performance assessment. The yields are estimated with 82% accuracy (RMSE = 22.51) when Random Forest algorithm is used with important parameters. [ABSTRACT FROM AUTHOR]

Essential forest ecosystem services can be assessed by better understanding the diversity of vegetation, specifically those of Mediterranean region. A species level classification of maquis would be useful in understanding vegetation structure and dynamics, which would be an indicator of degradation or succession in the region. Although remote sensing was regularly used for classification in the region, maquis are simply represented as one to three categories based on density or height. To fill this gap, we test the capability of Sentinel-2 imagery, together with selected ancillary variables, for an accurate mapping of the dominant maquis formations. We applied Recursive Feature Selection procedure and used a Random Forest classifier. The algorithm is tested using ground truth collected from site and reached 78% and 93% overall accuracy at species level and physiognomic level, respectively. Our results suggest species level characterization of dominant maquis is possible with Sentinel-2 spatial resolution. [ABSTRACT FROM AUTHOR]

Remote sensing scene classification is gaining much more interest in the recent few years for many strategic fields such as security, land cover and land use monitoring. Several methods have been proposed in the literature and they can be divided into three main classes based on the features used: handcrafted features, features obtained by unsupervised learning and those obtained from deep learning. Handcrafted features are generally time consuming and suboptimal. Unsupervised learning based features which have been proposed later gave better results but their performances are still limited because they mainly rely on shallow networks and are not able to extract powerful features. Deep learning based features are recently investigated and gave interesting results. But, they cannot be usually used because of the scarcity of labelled remote sensing images and are also computationally expensive. Most importantly, whatever kind of feature is used, the neighbourhood information of them is ignored. In this paper, we propose a novel remote sensing scene representation and classification approach called Bag of Visual SubGraphs (BoVSG). First, each image is segmented into superpixels in order to summarize the image content while retaining relevant information. Then, the superpixels from all images are clustered according to their colour and texture features and a random label is assigned to each cluster that probably corresponds to some material or land cover type. Thus superpixels belonging to the same cluster have the same label. Afterwards, each image is modelled with a graph where nodes correspond to labelled superpixels and edges model spatial neighbourhoods. Finally, each image is represented by a histogram of the most frequent subgraphs corresponding to land cover adjacency patterns. This way, local spatial relations between the nodes are also taken into account. Resultant feature vectors are classified using standard classification algorithms. The proposed approach is tested on three popular datasets and its performance outperforms state-of-the-art methods, including deep learning methods. Besides its accuracy, the proposed approach is computationally much less expensive than deep learning methods. [ABSTRACT FROM AUTHOR]

Automated detection of buried anti-personnel landmines using remote sensing techniques is very important for clearing minefields without putting lives in danger. Although thermal infrared imaging is promising, it is far from applicable to the real world in its current state-of-the-art. The most serious problem is that experiments are generally held using sandboxes or levelled and cleared soil, but real fields are, at least partially, covered with plants. In this study, we present an algorithm for landmine detection that is robust enough to detect beyond the clutter caused by partial plant cover. The first part is a hypothesis generator based on circular Hough Transform applied to images that are filtered to enhance circular structures. The second part tests the candidate landmine coordinates using rotationally invariant features, including modified Histogram of Oriented Gaussians (HOG), over multiple images taken at different times after Wiener filtering to maximize signal-to-clutter ratio. The performances of various features and classifiers are compared. The overall performance of the algorithm is demonstrated on a dataset of real-world landmine images contaminated by simulated plants. Satisfactory results are obtained up to 40% equivalent plant coverage where more than 65% of the pixels are fully or partially covered by plants. [ABSTRACT FROM AUTHOR]