Matthieu Molinier

Matthieu Molinier
VTT Technical Research Centre of Finland | vtt · Remote Sensing and Environment Information Systems

M. Sc.

About

73
Publications
19,802
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
1,084
Citations
Citations since 2017
26 Research Items
885 Citations
2017201820192020202120222023050100150200250
2017201820192020202120222023050100150200250
2017201820192020202120222023050100150200250
2017201820192020202120222023050100150200250
Introduction
Over 15 years of professional experience in change detection in optical medium and very high resolution satellite images, machine learning in remote sensing, for various applications including forestry, forest monitoring. Specialties: * Method development and prototyping for remote sensing and satellite images * Machine learning, deep learning * Image processing for change detection and time series analysis * Motion detection and tracking in video sequences
Additional affiliations
October 2004 - present
VTT Technical Research Centre of Finland
Position
  • Researcher

Publications

Publications (73)
Article
Full-text available
Designing discriminative powerful texture features robust to realistic imaging conditions is a challenging computer vision problem with many applications, including material recognition and analysis of satellite or aerial imagery. In the past, most texture description approaches were based on dense orderless statistical distribution of local featur...
Article
Full-text available
We compared the performance of Sentinel-2 and Landsat 8 data for forest variable prediction in the boreal forest of Southern Finland. We defined twelve modelling setups to train multivariable prediction models with either multilayer perceptron (MLP) or regression tree models with the brute force forward selection method. The reference data consiste...
Article
Full-text available
Cloud contamination is an inevitable problem in optical remote sensing images. Unlike thick clouds, thin clouds do not completely block out background which makes it possible to restore background information. In this paper, we propose a semi-supervised method based on generative adversarial networks (GANs) and a physical model of cloud distortion...
Article
Full-text available
The spectral and spatial resolutions of modern optical Earth observation data are continuously increasing. To fully utilize the data, integrate them with other information sources and create applications relevant to real-world problems, extensive training data are required. We present TAIGA, an open dataset including continuous and categorical fore...
Article
Full-text available
Cloud detection is a crucial step in the optical satellite image processing pipeline for Earth observation. Clouds in optical remote sensing images seriously affect the visibility of the background and greatly reduce the usability of images for land applications. Traditional methods based on thresholding, multi-temporal or multi-spectral informatio...
Article
Full-text available
Lytic polysaccharide monooxygenases (EC1.14.99.53-56, LPMOs) are oxidative enzymes with the capability to enhance lignocellulose saccharification as well as nanofibrillation of cellulosic fibres. The parameters affecting the efficiency of oxidative modification of cotton linters and softwood kraft fibres by LPMO from Trichoderma reesei ( Tr AA9A) w...
Article
Full-text available
Multi-spectral remote sensing images are widely used for monitoring the globe. Although thin clouds can affect all optical bands, the influences of thin clouds differ with band wavelength. When processing multi-spectral bands at different resolutions, many methods only remove thin clouds in visible/near infrared bands or rescale multi resolution ba...
Chapter
This chapter presents an overview of the main time series analysis methods for environment monitoring with earth observation, from classical methods to the deep learning (DL) methods. It summarizes main differences between bi-temporal change detection, annual time series and dense time series analyses, and also presents the three main types of annu...
Article
Full-text available
Estimation of forest structural variables is essential to provide relevant insights for public and private stakeholders in forestry and environmental sectors. Airborne light detection and ranging (LiDAR) enables accurate forest inventory, but it is expensive for large area analyses. Continuously increasing volume of open Earth Observation (EO) imag...
Preprint
Clouds are a very important factor in the availability of optical remote sensing images. Recently, deep learning-based cloud detection methods have surpassed classical methods based on rules and physical models of clouds. However, most of these deep models are very large which limits their applicability and explainability, while other models do not...
Article
Full-text available
Clouds are a very important factor in the availability of optical remote sensing images. Recently, deep learning (DL)-based cloud detection methods have surpassed classical methods based on rules and physical models of clouds. However, most of these deep models are very large, which limits their applicability and explainability, while other models...
Article
Full-text available
Thin clouds seriously affect the availability of optical remote sensing images, especially in visible bands. Short-wave infrared (SWIR) bands are less influenced by thin clouds, but usually have lower spatial resolution than visible (Vis) bands in high spatial resolution remote sensing images (e.g., in Sentinel-2A/B, CBERS04, ZY-1 02D and HJ-1B sat...
Article
Full-text available
Clouds in optical remote sensing images seriously affect the visibility of background pixels and greatly reduce the availability of images. It is necessary to detect clouds before processing images. In this paper, a novel cloud detection method based on attentive generative adversarial network (Auto-GAN) is proposed for cloud detection. Our main id...
Article
Full-text available
Cloud detection is an important step in the processing of remote sensing images. Most methods based on convolutional neural networks (CNNs) for cloud detection require pixel-level labels, which are time-consuming and expensive to annotate. To overcome this challenge, this letter proposes a novel semisupervised algorithm for cloud detection by train...
Article
Full-text available
Introduction: Recent research focused on the interaction between land cover and the development of allergic and respiratory disease has provided conflicting results and the underlying mechanisms are not fully understood. In particular, green space, which confers an overall positive impact on general health, may be significantly contributing to adv...
Conference Paper
Citizen Science or participatory sensing can help filling in the gaps of in-situ reference forestry data needed to analyze satellite images. In this study, we show that the Relasphone, a biomass measuring application previously developed and tested in boreal forests of Finland and temperate-cold pine forests in Durango, Mexico, can be adapted to pi...
Article
Full-text available
Enzymatic modification of bleached softwood kraft fibres for improved fibre reactivity was studied at high (20% w/w) and low (1% w/w) dry matter content. The role of enzyme family and structure in fibre modification was assessed using endoglucanases from three structurally different glycoside hydrolase (GH) families (5, 7 and 45) with and without a...
Article
Full-text available
Despite the application of state-of-the-art fully Convolutional Neural Networks (CNNs) for semantic segmentation of very high-resolution optical imagery, their capacity has not yet been thoroughly examined for the classification of Synthetic Aperture Radar (SAR) images. The presence of speckle noise, the absence of efficient feature expression, and...
Article
Full-text available
In land monitoring applications, clouds and shadows are considered noise that should be removed as automatically and quickly as possible, before further analysis. This paper presents a method to detect clouds and shadows in Suomi NPP satellite's VIIRS (Visible Infrared Imaging Radiometer Suite) satellite images. The proposed cloud and shadow detect...
Preprint
Full-text available
The article has been published in ISPRS Journal of Photogrammetry and Remote Sensing : https://www.sciencedirect.com/science/article/pii/S0924271618300285 This is the Preprint of the first version submitted in June 2017, without additional experiments on ResNet.
Article
Full-text available
Due to the high cost of traditional forest plot measurements, the availability of up-to-date in situ forest inventory data has been a bottleneck for remote sensing image analysis in support of the important global forest biomass mapping. Capitalizing on the proliferation of smartphones, citizen science is a promising approach to increase spatial an...
Conference Paper
Full-text available
Citizen observations, environmental data gathered by volunteers without professional observation capabilities, have been extensively used for Finnish water quality monitoring tasks. Recently, mobile smartphones and their digital cameras have enabled more direct measurements of transparency related water quality variables with inexpensive technology...
Conference Paper
Full-text available
This is a selection of results of the North State project, that demonstrate how innovative methods applied to the new Sentinel data streams can be combined with models to monitor carbon and water fluxes for pan-boreal Europe.
Conference Paper
Full-text available
Citizen Science, propelled by the growing popularity of smartphones, can provide valuable reference information for remote sensing image analysis. We demonstrate that the Relasphone, a biomass measuring application previously developed and tested in boreal forests of Finland, can be adapted to temperate-cold pine forests in Durango State, Mexico. R...
Conference Paper
Full-text available
The objective of project North State, funded by Framework Program 7 of the European Union, is to develop innovative data fusion methods that exploit the new generation of multi-source data from Sentinels and other satellites in an intelligent, self-learning framework. The remote sensing outputs are interfaced with state-of-the-art carbon and water...
Conference Paper
Full-text available
Citizen science is a promising way to increase temporal and spatial coverages of in-situ data, and to aid in data processing and analysis. In this paper, we present how citizen science can be used together with Earth observation, and demonstrate its value through three pilot projects focusing on forest biomass analysis, data management in emergenci...
Conference Paper
Full-text available
The availability of ground reference forest data can be a bottleneck in remote sensing studies. Data may be available in only limited areas because of the cost and lengthy process of traditional forest inventory data collection by professionals. In certain cases, forest inventory data may not be easy to obtain, if not impossible. We propose a new...
Conference Paper
Full-text available
Storms and heavy winds can induce degradations on wide areas of forest, which have a severe impact on the ecological habitat and on economical value. During ten days in July and August 2010, the thunderstorms named Asta, Veera, Lahja and Sylvi raged in southern and middle Finland. About 8.1 million m^3 of forest was damaged, and the storms caused s...
Article
Full-text available
Water transparency is one indicator of water quality. High water transparency is an indication of clean water. A common method for measuring water transparency is Secchi depth. In this paper, we present an approach to water quality (Secchi depth and turbidity) monitoring using mobile phones and a small device designed for water quality measurements...
Conference Paper
Full-text available
Other distances based on CDFs From the observation of pair-wise CDFs (Fig. 3), we propose two other measures for change detection : • Maximum shift between CDFs ("horizontal distance" HD) : this is the same principle as the K-S distance, but along the axis of histogram bins. • Area between curves (ABC) : absolute normalized area of the region betwe...
Conference Paper
Full-text available
The overall objective of the Social Forest Planning project is to develop and demonstrate a novel system for forest management planning and updating of present plans. The system combines images from cellular phones with remote sensing data to predict forest variables. The variables are input to a Planner Engine that outputs forest resources informa...
Conference Paper
A system that combines forest variable information from cellular phone images with remote sensing data was developed. The system utilizes the central projection geometry of the cell phone images by applying the so called relascope principle to derive information on stem basal area, that is closely related to forest biomass. Information on tree spec...
Conference Paper
Full-text available
The overall objective of the Social Forest Planning project is to develop and demonstrate a novel system for forest management planning and updating of present plans. The system to be developed combines images from cellular phones with remote sensing data to predict forest variables. The variables are input to a Planner Engine that outputs forest r...
Conference Paper
Full-text available
The aim of this study was to develop an automatic procedure to detect tree stems in cell phone images. If the stems can be detected, the central projection geometry of the images makes it possible to apply the so called relascope principle to predict the basal area of stems per hectare. The basal area is closely correlated with tree biomass. Images...
Conference Paper
Full-text available
The aim of this study was to provide an effective feature selection for tree species classifiers in mixed-species boreal forest, from a very high resolution optical satellite image. The 35 input features were the 5 input spectral bands (multispectral and panchromatic channels), 9 contextual features derived from the panchromatic channel and 21 segm...
Article
Full-text available
This paper compares ALOS PALSAR fully polarimetric and dual-polarized data in the application area of land cover mapping. To assure versatile comparison of the data, different classification methods and different features of data are used. Two of the classification methods used are based on supervised classification and two on unsupervised classifi...
Conference Paper
Full-text available
The overall objective of the Social Forest Planning project is to develop and demonstrate a novel system for forest management planning and updating of present plans. The system to be developed combines images from cellular phones with remote sensing data to predict forest variables. The variables are input to a Planner Engine that outputs forest r...
Conference Paper
Full-text available
Identification of clear-cuts and thinning cuts that occurred between the acquisition of satellite and aerial images was done using object-based change detection. The study, aiming at a new method to update forest cover maps, was part of the NewForest project on the development of a forest planning system. The results show clear matching between the...
Conference Paper
Full-text available
The work related to this paper is part of an on-going study called NewForest - Renewal of Forest Resource Mapping. In this study the methodologies developed for individual tree crown (ITC) recognition and crown width estimation will be combined with forest variable estimates that are produced using features calculated from segmented VHR satellite i...
Conference Paper
Full-text available
This study is part of the on-going NewForest project, whose objective is to develop remote sensing data analysis methods for producing species-wise forest variable estimates with accuracy that is adequate for operational forest inventory. Species-wise forest estimates relies on individual treetop locations detection from the remote sensing imagery....
Conference Paper
Full-text available
The objective was to produce a mosaic of several polarimetric ALOS/Palsar scenes in such a form that polarimetric processing methods - like polarization synthesis and various decomposition techniques - can be applied to the mosaic product. A study site was selected in Finnish Lapland (centre 68.5 degrees north, 27.5 degrees east) in an area where...
Conference Paper
Full-text available
The objective of ForSe - Season Monitoring study was to develop an automatic method to analyze web-camera images of nature. As the outcome the image analysis produces indices that indicate the seasonal development stage of the forest (e.g. degree of autumn colour of deciduous trees). IP web-cameras of a pilot camera network were programmed to take...
Conference Paper
Full-text available
Six polarimetric change detection indices were tested on L band ALOS PALSAR data over Kuortane, Finland. Tests included quantitative evaluation of change indices compared to reference change maps, and qualitative evaluation by visual inspection. Results suggest an additional accuracy using fully polarimetric data in change detection. Contrast Ratio...
Conference Paper
Full-text available
Self-Organising Maps (SOMs) have been successfully applied to content-based image retrieval (CBIR). In this study, we investigate the potential of PicSOM, an image database browsing system, applied to quad-polarised ALOS PALSAR images. Databases of small images were artificially created, either from a single satellite image for object detection, or...
Conference Paper
Full-text available
The potential of TerraSAR-X imagery for forest cutting monitoring was experimentally investigated in images over Kuortane, Finland. In this study, 10 dual-polarised change detection indices were tested versus a ground truth of clearcuts done between the acquisition dates. Preliminary results suggest the decrease of entropy and the increase of coher...
Conference Paper
Full-text available
Polarimetric Palsar data were ortho-rectified for analysis of polarimetric signatures of forested stands. A strong posi-tive correlation of 0.93 was found between Palsar HV am-plitude and forest stem volume in stands with a stem vol-ume of 150 m 3 /ha or below. For HH data, the correlation coefficient was 0.82.
Conference Paper
Full-text available
This article compares four land cover classification methods using ALOS Palsar fully polarimetric data. Two methods are based on supervised classification and two on unsupervised classification. Both full polarimetric and intensity data were used. Fully polarimetric data gave better results (85.5%–80.8%) than intensity data only (84%–76.1%) but the...
Conference Paper
Full-text available
Methods for terrain correction of polarimetric SAR data were studied and developed. Ortho-rectification resampling and amplitude correction utilized Stokes matrix data. The Stokes matrix of thermal noise was subtracted before amplitude normalization. Application of an azimuth-slope correction algorithm resulted in slightly narrower distribution of...
Conference Paper
Full-text available
This article aims at providing a comparison of polarimetric change detection indices from a practical point of view. Six polarimetric change detection indices were tested on L band EMISAR data over Norway. Tests included quantitative evaluation of change maps compared to a ground truth of changes, and qualitative evaluation by visual inspection. Co...
Article
Full-text available
The increasing amount and resolution of satellite sensors demand new techniques for browsing remote sensing image archives. Content-based querying allows an efficient retrieval of images based on the information they contain, rather than their acquisition date or geographical extent. Self-organizing maps (SOMs) have been successfully applied in the...
Technical Report
Full-text available
Long-term monitoring based on satellite imagery involves systems capable of ingesting huge amount of data. We investigated the potential of PicSOM, an image database browsing system based on Content-Based Image Retrieval (CBIR), for satellite image analysis. By visually querying a satellite image database, man-made structures or changes between two...
Conference Paper
Full-text available
Methods for terrain correction of polarimetric SAR data were studied and developed. Ortho-rectification resampling and amplitude correction utilized Stokes matrix data. The Stokes matrix of thermal noise was subtracted before amplitude normalization. Application of an azimuth-slope correction algorithm resulted in slightly narrower distribution of...
Conference Paper
Full-text available
In this study, we extended the potential of a Content- Based Image Retrieval (CBIR) system based on Self-Organizing Maps (SOMs), for the analysis of remote sensing data. A database was artificially created by splitting each image to be analyzed into small images (or imagelets ). Content-based image retrieval was applied to fully polarimetric airbor...