Search results for " intelligence"
showing 10 items of 6677 documents
Multi-phase classification by a least-squares support vector machine approach in tomography images of geological samples
2016
Abstract. Image processing of X-ray-computed polychromatic cone-beam micro-tomography (μXCT) data of geological samples mainly involves artefact reduction and phase segmentation. For the former, the main beam-hardening (BH) artefact is removed by applying a best-fit quadratic surface algorithm to a given image data set (reconstructed slice), which minimizes the BH offsets of the attenuation data points from that surface. A Matlab code for this approach is provided in the Appendix. The final BH-corrected image is extracted from the residual data or from the difference between the surface elevation values and the original grey-scale values. For the segmentation, we propose a novel least-squar…
Individual Tree Detection and Classification with UAV-Based Photogrammetric Point Clouds and Hyperspectral Imaging
2017
Made available in DSpace on 2018-12-11T17:11:58Z (GMT). No. of bitstreams: 0 Previous issue date: 2017-03-01 Suomen Akatemia Small unmanned aerial vehicle (UAV) based remote sensing is a rapidly evolving technology. Novel sensors and methods are entering the market, offering completely new possibilities to carry out remote sensing tasks. Three-dimensional (3D) hyperspectral remote sensing is a novel and powerful technology that has recently become available to small UAVs. This study investigated the performance of UAV-based photogrammetry and hyperspectral imaging in individual tree detection and tree species classification in boreal forests. Eleven test sites with 4151 reference trees repr…
Convolutional Neural Networks for Cloud Screening: Transfer Learning from Landsat-8 to Proba-V
2018
Cloud detection is a key issue for exploiting the information from Earth observation satellites multispectral sensors. For Proba-V, cloud detection is challenging due to the limited number of spectral bands. Advanced machine learning methods, such as convolutional neural networks (CNN), have shown to work well on this problem provided enough labeled data. However, simultaneous collocated information about the presence of clouds is usually not available or requires a great amount of manual labor. In this work, we propose to learn from the available Landsat −8 cloud masks datasets and transfer this learning to solve the Proba-V cloud detection problem. CNN are trained with Landsat images adap…
Tree Species Classification of Drone Hyperspectral and RGB Imagery with Deep Learning Convolutional Neural Networks
2020
Interest in drone solutions in forestry applications is growing. Using drones, datasets can be captured flexibly and at high spatial and temporal resolutions when needed. In forestry applications, fundamental tasks include the detection of individual trees, tree species classification, biomass estimation, etc. Deep neural networks (DNN) have shown superior results when comparing with conventional machine learning methods such as multi-layer perceptron (MLP) in cases of huge input data. The objective of this research is to investigate 3D convolutional neural networks (3D-CNN) to classify three major tree species in a boreal forest: pine, spruce, and birch. The proposed 3D-CNN models were emp…
Estimating Missing Information by Cluster Analysis and Normalized Convolution
2018
International audience; Smart city deals with the improvement of their citizens' quality of life. Numerous ad-hoc sensors need to be deployed to know humans' activities as well as the conditions in which these actions take place. Even if these sensors are cheaper and cheaper, their installation and maintenance cost increases rapidly with their number. We propose a methodology to limit the number of sensors to deploy by using a standard clustering technique and the normalized convolution to estimate environmental information whereas sensors are actually missing. In spite of its simplicity, our methodology lets us provide accurate assesses.
SVM-based classification of High resolution Urban Satellites Images using Dense SURF and Spectral Information
2018
Remote-sensing focusing on image classification knows a large progress and receives the attention of the remote-sensing community day by day. Combining many kinds of extracted features has been successfully applied to High resolution urban satellite images using support vector machine (SVM). In this paper, we present a methodology that is promoting a performed classification by using pixel-wise SURF description features combined with spectral information in Cielab space for the first time on common scenes of urban imagery. The proposed method gives a promising classification accuracy when compared with the two types of features used separately.
SAR Image Classification Combining Structural and Statistical Methods
2011
The main objective of this paper is to develop a new technique of SAR image classification. This technique combines structural parameters, including the Sill, the slope, the fractal dimension and the range, with statistical methods in a supervised image classification. Thanks to the range parameter, we define the suitable size of the image window used in the proposed approach of supervised image classification. This approach is based on a new way of characterising different classes identified on the image. The first step consists in determining relevant area of interest. The second step consists in characterising each area identified, by a matrix. The last step consists in automating the pr…
Understanding deep learning in land use classification based on Sentinel-2 time series
2020
AbstractThe use of deep learning (DL) approaches for the analysis of remote sensing (RS) data is rapidly increasing. DL techniques have provided excellent results in applications ranging from parameter estimation to image classification and anomaly detection. Although the vast majority of studies report precision indicators, there is a lack of studies dealing with the interpretability of the predictions. This shortcoming hampers a wider adoption of DL approaches by a wider users community, as model’s decisions are not accountable. In applications that involve the management of public budgets or policy compliance, a better interpretability of predictions is strictly required. This work aims …
Transferring deep learning models for cloud detection between Landsat-8 and Proba-V
2020
Abstract Accurate cloud detection algorithms are mandatory to analyze the large streams of data coming from the different optical Earth observation satellites. Deep learning (DL) based cloud detection schemes provide very accurate cloud detection models. However, training these models for a given sensor requires large datasets of manually labeled samples, which are very costly or even impossible to create when the satellite has not been launched yet. In this work, we present an approach that exploits manually labeled datasets from one satellite to train deep learning models for cloud detection that can be applied (or transferred) to other satellites. We take into account the physical proper…
Spectral alignment of multi-temporal cross-sensor images with automated kernel canonical correlation analysis
2015
In this paper we present an approach to perform relative spectral alignment between optical cross-sensor acquisitions. The proposed method aims at projecting the images from two different and possibly disjoint input spaces into a common latent space, in which standard change detection algorithms can be applied. The system relies on the regularized kernel canonical correlation analysis transformation (kCCA), which can accommodate nonlinear dependencies between pixels by means of kernel functions. To learn the projections, the method employs a subset of samples belonging to the unchanged areas or to uninteresting radiometric differences. Since the availability of ground truth information to p…