The Experts below are selected from a list of 177 Experts worldwide ranked by ideXlab platform
Ioannis Kompatsiaris - One of the best experts on this subject based on the ideXlab platform.
-
lbp flow and hybrid encoding for real time water and Fire Classification
International Conference on Computer Vision, 2017Co-Authors: Konstantinos Avgerinakis, Panagiotis Giannakeris, Alexia Briassouli, Anastasios Karakostas, Stefanos Vrochidis, Ioannis KompatsiarisAbstract:The analysis of dynamic scenes in video is a very useful task especially for the detection and monitoring of natural hazards such as floods and Fires. In this work, we focus on the challenging problem of real-world dynamic scene understanding, where videos contain dynamic textures that have been recorded in the "wild". These videos feature large illumination variations, complex motion, occlusions, camera motion, as well as significant intra-class differences, as the motion patterns of dynamic textures of the same category may be subject to large variations in real world recordings. We address these issues by introducing a novel dynamic texture descriptor, the "Local Binary Pattern-flow" (LBP-flow), which is shown to be able to accurately classify dynamic scenes whose complex motion patterns are difficult to separate using existing local descriptors, or which cannot be modelled by statistical techniques. LBP-flow builds upon existing Local Binary Pattern (LBP) descriptors by providing a low-cost representation of both appearance and optical flow textures, to increase its representation capabilities. The descriptor statistics are encoded with the Fisher vector, an informative mid-level descriptor, while a neural network follows to reduce the dimensionality and increase the discriminability of the encoded descriptor. The proposed algorithm leads to a highly accurate spatio-temporal descriptor which achieves a very low computational cost, enabling the deployment of our descriptor in real world surveillance and security applications. Experiments on challenging benchmark datasets demonstrate that it achieves recognition accuracy results that surpass State-of-the-Art dynamic texture descriptors.
-
ICCV Workshops - LBP-Flow and Hybrid Encoding for Real-Time Water and Fire Classification
2017 IEEE International Conference on Computer Vision Workshops (ICCVW), 2017Co-Authors: Konstantinos Avgerinakis, Panagiotis Giannakeris, Alexia Briassouli, Anastasios Karakostas, Stefanos Vrochidis, Ioannis KompatsiarisAbstract:The analysis of dynamic scenes in video is a very useful task especially for the detection and monitoring of natural hazards such as floods and Fires. In this work, we focus on the challenging problem of real-world dynamic scene understanding, where videos contain dynamic textures that have been recorded in the "wild". These videos feature large illumination variations, complex motion, occlusions, camera motion, as well as significant intra-class differences, as the motion patterns of dynamic textures of the same category may be subject to large variations in real world recordings. We address these issues by introducing a novel dynamic texture descriptor, the "Local Binary Pattern-flow" (LBP-flow), which is shown to be able to accurately classify dynamic scenes whose complex motion patterns are difficult to separate using existing local descriptors, or which cannot be modelled by statistical techniques. LBP-flow builds upon existing Local Binary Pattern (LBP) descriptors by providing a low-cost representation of both appearance and optical flow textures, to increase its representation capabilities. The descriptor statistics are encoded with the Fisher vector, an informative mid-level descriptor, while a neural network follows to reduce the dimensionality and increase the discriminability of the encoded descriptor. The proposed algorithm leads to a highly accurate spatio-temporal descriptor which achieves a very low computational cost, enabling the deployment of our descriptor in real world surveillance and security applications. Experiments on challenging benchmark datasets demonstrate that it achieves recognition accuracy results that surpass State-of-the-Art dynamic texture descriptors.
Sabyasachi Gaan - One of the best experts on this subject based on the ideXlab platform.
-
Improving Flame Retardancy of in-situ Silica-Epoxy Nanocomposites cured with Aliphatic Hardener: Combined effect of DOPO-based flame-retardant and Melamine
Composites Part C: Open Access, 2020Co-Authors: Aurelio Bifulco, Dambarudhar Parida, Khalifah A. Salmeia, Sandro Lehner, Rolf Stämpfli, Hilber Markus, Giulio Malucelli, Francesco Branda, Sabyasachi GaanAbstract:ABSTRACT Silica-epoxy nanocomposites were prepared via an “in-situ” sol-gel synthesis process and a phosphorus (P) flame-retardant i.e. 6H-dibenz[c,e][1,2]oxaphosphorin,6-[(1-oxido-2,6,7-trioxa-1-phosphabicyclo[2.2.2]oct-4-yl)methoxy]-, 6-oxide (DP) and melamine (Mel) were further added to the matrix to improve its Fire performance. The main components of epoxy resin were bisphenol A diglycidyl ether (DGEBA) and isophorone diamine (IPDA) hardener. The addition of DP as well as silica alone into the epoxy system stopped the melt dripping phenomena in the vertical Fire test (UL 94), however, the addition of melamine was crucial for achieving the highest Fire Classification (UL 94-V0 rating). The presence of DP and Mel in the silica-epoxy nanocomposite promoted a large reduction (ranging from 53% up to 80%) in the heat release rate (HRR) and a delay (up to 31%) in the ignition time in the cone calorimetry experiments. Improved Fire performance of the epoxy system was attributed to; i) a condensed phase activity of silica, DP and melamine to form a protective thermal barrier during combustion and ii) a minor gas phase flame inhibition activity of DOPO component of DP. The mechanical characterization of the epoxy nanocomposites through tensile tests showed that the addition of DP increases the stiffness of the epoxy resin, resulting in a strong increase of Young modulus (up to 32%) and in a slight decrease of fracture strength, elongation at break and toughness. An increased glass transition temperature (up to 8%) of the epoxy system possibly due to hydrogen bonds and polar interactions of DP with the matrix was also observed.
-
Some key Factors Influencing the Flame Retardancy of EDA-DOPO Containing Flexible Polyurethane Foams
2018Co-Authors: Agnieszka Przystaś, Khalifah A. Salmeia, Milijana Jovic, Daniel Rentsch, Laurent Ferry, Henri Mispreuve, Heribert Perler, Sabyasachi GaanAbstract:In this work we have investigated the role of various additives (emulsifier, anti-dripping agent) and formulation procedure (pre- dispersion of solid additives in polyol via milling) which influence the flame retardancy of 6,6′-[ethan-1,2-diylbis(azandiyl)]bis(6H-dibenzo[c,e][1,2]oxaphosphin-6-oxid) (EDA-DOPO) containing flexible polyurethane foams. For comparison, the flame retardancy of two additional structurally analogues bridged 9, 10-dihydro-9-oxa-10-phosphaphenanthrene-10-oxide (DOPO) based compounds i.e. ethanolamine-DOPO (ETA-DOPO) and ethylene glycol-DOPO (EG-DOPO) were also evaluated together with EDA-DOPO in flexible PU foams of various formulations. The flame retardancy of three bridged-DOPO compounds depends on the type of PU formulation. For certain PU formulation containing EDA-DOPO, lower Fire performance was observed. Addition of emulsifier and polytetrafluoroethylene (PTFE) to these PU formulations influenced positively the flame retardancy of EDA-DOPO/PU foams. In addition, dispersion of EDA-DOPO and PTFE via milling in polyol improved the flame retardancy of the PU foams. Mechanistic studies performed using pyrolysis combustion flow calorimetry (PCFC) and its coupling to FTIR showed no difference in the combustion efficiency of the bridged-DOPO compounds in PU foams. From these PCFC experiments we can conclude that these bridged-DOPO compounds and their decomposition products may work primarily in the gas phase as flame inhibitors. Physiochemical behavior of additives in PU formulation responsible for the improvement in the flame retardancy of PU foams was further investigated by studying the dripping behavior of the PU foams in UL 94 HB test. A high-speed camera was used to study the dripping behavior in the UL 94 HB test and results indicate a considerable reduction of a total number of melt drips and flaming drips for the flame retardant formulations. This reduction in melt drips and flaming drips during the UL 94 HB tests help PU foams achieve higher Fire Classification.
-
Some Key Factors Influencing the Flame Retardancy of EDA-DOPO Containing Flexible Polyurethane Foams
Polymers, 2018Co-Authors: Agnieszka Przystas, Khalifah A. Salmeia, Milijana Jovic, Daniel Rentsch, Laurent Ferry, Henri Mispreuve, Heribert Perler, Sabyasachi GaanAbstract:The role of various additives (emulsifier, anti-dripping agent) and formulation procedures (pre-dispersion of solid additives in polyol via milling) which influence the flame retardancy of 6,6'-[ethan-1,2-diylbis(azandiyl)]bis(6H-dibenzo[c,e][1,2]oxaphosphin-6-oxid) (EDA-DOPO) containing flexible polyurethane foams has been investigated in this work. For comparison, the flame retardancy of two additional structurally-analogous bridged 9,10-dihydro-9-oxa-10-phosphaphenanthrene-10-oxide (DOPO)-based compounds, i.e., ethanolamine-DOPO (ETA-DOPO) and ethylene glycol-DOPO (EG-DOPO) were also evaluated together with EDA-DOPO in flexible PU foams of various formulations. The flame retardancy of these three bridged-DOPO compounds depends on the type of PU formulation. For certain PU formulations containing EDA-DOPO, lower Fire performance was observed. Addition of emulsifier and polytetrafluoroethylene (PTFE) to these PU formulations influenced positively the flame retardancy of EDA-DOPO/PU foams. In addition, dispersion of EDA-DOPO and PTFE via milling in polyol improved the flame retardancy of the PU foams. Mechanistic studies performed using a microscale combustion calorimeter (MCC) and its coupling to FTIR showed no difference in the combustion efficiency of the bridged-DOPO compounds in PU foams. From MCC experiments it can be concluded that these bridged-DOPO compounds and their decomposition products may work primarily in the gas phase as flame inhibitors. The physiochemical behavior of additives in PU formulation responsible for the improvement in the flame retardancy of PU foams was further investigated by studying the dripping behavior of the PU foams in the UL 94 HB test. A high-speed camera was used to study the dripping behavior in the UL 94 HB test and results indicate a considerable reduction of the total number of melt drips and flaming drips for the flame retardant formulations. This reduction in melt drips and flaming drips during the UL 94 HB tests help PU foams achieve higher Fire Classification.
Esko Mikkola - One of the best experts on this subject based on the ideXlab platform.
-
European classes for the reaction to Fire performance of wood-based panels
Fire and Materials, 2010Co-Authors: Birgit Östman, Esko MikkolaAbstract:The Classification system for the reaction to Fire performance of building products in Europe has been applied to wood-based panels as being ‘products with known and stable Fire performance’. The European Classification system includes two sub-systems, one main system for all construction products except floorings and the other for flooring products. Panel properties such as density, thickness, joints and types of end-use application including different substrates have been studied thoroughly and are included in the Classification. Most wood-based panels fall in classes D-s2, d0 or Dfl-s1 (for floorings). Testing has been performed according to EN 13823 SBI-Single Burning Item test, EN ISO 9239-1 Radiant panel test, and EN ISO 11925-2 Small flame test. Clear relationships between the main Euroclass Fire performance parameters and product parameters (such as density and thickness) have been demonstrated. Tables with reaction to Fire Classification of different wood-based panels and end-use applications have been developed in two steps, approved by the European Commission and published in their Official Journal. The table is also included in the harmonized product standard and may be used for CE-marking. Copyright © 2010 John Wiley & Sons, Ltd.
-
European classes for the reaction to Fire performance of wood products
Holz als Roh- und Werkstoff, 2006Co-Authors: Birgit A.-l. Östman, Esko MikkolaAbstract:The new Classification system for the reaction to Fire performance of building products in Europe has been applied to five different product families of wood: Wood-based panels, Structural timber, Glued laminated timber, Solid wood panelling and cladding and Wood flooring as being ‘products with known and stable Fire performance’. The European Classification system includes two sub-systems, one main system for all construction products except floorings and the other for flooring products. Wood properties such as density, thickness, joints and types of end use application including different substrates have been studied thoroughly and are included in the Classification. Most wood products fall in classes D-s2, d0 or D_fl-s1 (for floorings). Testing has been performed according to EN 13823 (2002) SBI- Single Burning Item test, EN ISO 9239-1 (2002) Radiant panel test, and EN ISO 11925-2 (2002) Small flame test. In all, more than one hundred wood products in different end use applications have been studied. Clear relationships between the main Euroclass Fire performance parameters and product parameters (such as density and thickness) have been demonstrated. Tables with reaction to Fire Classification of different wood products and end use applications have been developed, approved by the European Commission and published in their Official Journal. This procedure is ongoing with further official decisions to be published. Das neue europäische Klassifizierungssystem zum Brandverhalten von Bauprodukten gilt für die fünf Produktgruppen Holzwerkstoffe, Bauholz, Brettschichtholz, Wand- und Deckenbekleidungen aus Massivholz sowie Holzfußböden, die als “Produkte mit bekanntem und abschätzbarem Brandverhalten” gelten. Das europäische Klassifizierungssystem wird in zwei Kategorien unterteilt: eine Hauptkategorie für alle Bauprodukte mit Ausnahme von Bodenbelägen und eine Kategorie für Bodenbeläge. Holzeigenschaften, wie zum Beispiel Rohdichte, Dicke, Verbindungen und Anwendungsarten einschließlich verschiedener Trägerplatten wurden eingehend untersucht und in die Klassifizierung einbezogen. Die meisten Holzprodukte werden den Klassen D-s2, d0 oder D_fl-s1 (Fußböden) zugeordnet. Prüfungen erfolgten nach den Normen EN 13823 (2002) thermische Beanspruchung durch einen einzelnen brennenden Gegenstand, EN ISO 9239-1 (2002) Brandverhalten bei Beanspruchung mit einem Wärmestrahler und EN ISO 11925-2 (2002) Entzündbarkeit von Bauprodukten bei direkter Flammeneinwirkung. Insgesamt wurden über einhundert Holzprodukte in unterschiedlichen praktischen Anwendungsarten untersucht. Eindeutige Zusammenhänge zwischen den Hauptparametern zum Brandverhalten nach der Euroklasse und den Produktparametern (wie zum Beispiel Rohdichte und Dicke) wurden dargestellt. Tabellen mit der Klassifizierung des Brandverhaltens verschiedener Holzprodukte und Endanwendungen wurden erstellt, von der Europäischen Kommission genehmigt und in deren Amtsblatt veröffentlicht. Dieses Verfahren dauert noch an. Die Veröffentlichung weiterer amtlicher Entscheidungen steht noch aus.
-
European classes for the reaction to Fire performance of wood products
European Journal of Wood and Wood Products, 2006Co-Authors: Birgit Östman, Esko MikkolaAbstract:The new Classification system for the reaction to Fire performance of building products in Europe has been applied to five different product families of wood: Wood-based panels, Structural timber, Glued laminated timber, Solid wood panelling and cladding and Wood flooring as being ‘products with known and stable Fire performance’. The European Classification system includes two sub-systems, one main system for all construction products except floorings and the other for flooring products. Wood properties such as density, thickness, joints and types of end use application including different substrates have been studied thoroughly and are included in the Classification. Most wood products fall in classes D-s2, d0 or Dfl-s1 (for floorings). Testing has been performed according to EN 13823 (2002) SBI- Single Burning Item test, EN ISO 9239-1 (2002) Radiant panel test, and EN ISO 11925-2 (2002) Small flame test. In all, more than one hundred wood products in different end use applications have been studied. Clear relationships between the main Euroclass Fire performance parameters and product parameters (such as density and thickness) have been demonstrated. Tables with reaction to Fire Classification of different wood products and end use applications have been developed, approved by the European Commission and published in their Official Journal. This procedure is ongoing with further official decisions to be published.
Konstantinos Avgerinakis - One of the best experts on this subject based on the ideXlab platform.
-
lbp flow and hybrid encoding for real time water and Fire Classification
International Conference on Computer Vision, 2017Co-Authors: Konstantinos Avgerinakis, Panagiotis Giannakeris, Alexia Briassouli, Anastasios Karakostas, Stefanos Vrochidis, Ioannis KompatsiarisAbstract:The analysis of dynamic scenes in video is a very useful task especially for the detection and monitoring of natural hazards such as floods and Fires. In this work, we focus on the challenging problem of real-world dynamic scene understanding, where videos contain dynamic textures that have been recorded in the "wild". These videos feature large illumination variations, complex motion, occlusions, camera motion, as well as significant intra-class differences, as the motion patterns of dynamic textures of the same category may be subject to large variations in real world recordings. We address these issues by introducing a novel dynamic texture descriptor, the "Local Binary Pattern-flow" (LBP-flow), which is shown to be able to accurately classify dynamic scenes whose complex motion patterns are difficult to separate using existing local descriptors, or which cannot be modelled by statistical techniques. LBP-flow builds upon existing Local Binary Pattern (LBP) descriptors by providing a low-cost representation of both appearance and optical flow textures, to increase its representation capabilities. The descriptor statistics are encoded with the Fisher vector, an informative mid-level descriptor, while a neural network follows to reduce the dimensionality and increase the discriminability of the encoded descriptor. The proposed algorithm leads to a highly accurate spatio-temporal descriptor which achieves a very low computational cost, enabling the deployment of our descriptor in real world surveillance and security applications. Experiments on challenging benchmark datasets demonstrate that it achieves recognition accuracy results that surpass State-of-the-Art dynamic texture descriptors.
-
ICCV Workshops - LBP-Flow and Hybrid Encoding for Real-Time Water and Fire Classification
2017 IEEE International Conference on Computer Vision Workshops (ICCVW), 2017Co-Authors: Konstantinos Avgerinakis, Panagiotis Giannakeris, Alexia Briassouli, Anastasios Karakostas, Stefanos Vrochidis, Ioannis KompatsiarisAbstract:The analysis of dynamic scenes in video is a very useful task especially for the detection and monitoring of natural hazards such as floods and Fires. In this work, we focus on the challenging problem of real-world dynamic scene understanding, where videos contain dynamic textures that have been recorded in the "wild". These videos feature large illumination variations, complex motion, occlusions, camera motion, as well as significant intra-class differences, as the motion patterns of dynamic textures of the same category may be subject to large variations in real world recordings. We address these issues by introducing a novel dynamic texture descriptor, the "Local Binary Pattern-flow" (LBP-flow), which is shown to be able to accurately classify dynamic scenes whose complex motion patterns are difficult to separate using existing local descriptors, or which cannot be modelled by statistical techniques. LBP-flow builds upon existing Local Binary Pattern (LBP) descriptors by providing a low-cost representation of both appearance and optical flow textures, to increase its representation capabilities. The descriptor statistics are encoded with the Fisher vector, an informative mid-level descriptor, while a neural network follows to reduce the dimensionality and increase the discriminability of the encoded descriptor. The proposed algorithm leads to a highly accurate spatio-temporal descriptor which achieves a very low computational cost, enabling the deployment of our descriptor in real world surveillance and security applications. Experiments on challenging benchmark datasets demonstrate that it achieves recognition accuracy results that surpass State-of-the-Art dynamic texture descriptors.
Agnieszka Przystas - One of the best experts on this subject based on the ideXlab platform.
-
Some Key Factors Influencing the Flame Retardancy of EDA-DOPO Containing Flexible Polyurethane Foams
Polymers, 2018Co-Authors: Agnieszka Przystas, Khalifah A. Salmeia, Milijana Jovic, Daniel Rentsch, Laurent Ferry, Henri Mispreuve, Heribert Perler, Sabyasachi GaanAbstract:The role of various additives (emulsifier, anti-dripping agent) and formulation procedures (pre-dispersion of solid additives in polyol via milling) which influence the flame retardancy of 6,6'-[ethan-1,2-diylbis(azandiyl)]bis(6H-dibenzo[c,e][1,2]oxaphosphin-6-oxid) (EDA-DOPO) containing flexible polyurethane foams has been investigated in this work. For comparison, the flame retardancy of two additional structurally-analogous bridged 9,10-dihydro-9-oxa-10-phosphaphenanthrene-10-oxide (DOPO)-based compounds, i.e., ethanolamine-DOPO (ETA-DOPO) and ethylene glycol-DOPO (EG-DOPO) were also evaluated together with EDA-DOPO in flexible PU foams of various formulations. The flame retardancy of these three bridged-DOPO compounds depends on the type of PU formulation. For certain PU formulations containing EDA-DOPO, lower Fire performance was observed. Addition of emulsifier and polytetrafluoroethylene (PTFE) to these PU formulations influenced positively the flame retardancy of EDA-DOPO/PU foams. In addition, dispersion of EDA-DOPO and PTFE via milling in polyol improved the flame retardancy of the PU foams. Mechanistic studies performed using a microscale combustion calorimeter (MCC) and its coupling to FTIR showed no difference in the combustion efficiency of the bridged-DOPO compounds in PU foams. From MCC experiments it can be concluded that these bridged-DOPO compounds and their decomposition products may work primarily in the gas phase as flame inhibitors. The physiochemical behavior of additives in PU formulation responsible for the improvement in the flame retardancy of PU foams was further investigated by studying the dripping behavior of the PU foams in the UL 94 HB test. A high-speed camera was used to study the dripping behavior in the UL 94 HB test and results indicate a considerable reduction of the total number of melt drips and flaming drips for the flame retardant formulations. This reduction in melt drips and flaming drips during the UL 94 HB tests help PU foams achieve higher Fire Classification.