The Experts below are selected from a list of 80601 Experts worldwide ranked by ideXlab platform

Cees G M Snoek - One of the best experts on this subject based on the ideXlab platform.

  • visual synonyms for landmark Image retrieval
    Computer Vision and Image Understanding, 2012
    Co-Authors: Efstratios Gavves, Cees G M Snoek, Arnold W M Smeulders
    Abstract:

    In this paper, we address the incoherence problem of the visual words in bag-of-words vocabularies. Different from existing work, which assigns words based on closeness in descriptor space, we focus on identifying pairs of independent, distant words - the visual synonyms - that are likely to host Image patches of similar visual reality. We focus on landmark Images, where the Image Geometry guides the detection of synonym pairs. Image Geometry is used to find those Image features that lie in the nearly identical physical location, yet are assigned to different words of the visual vocabulary. Defined in this way, we evaluate the validity of visual synonyms. We also examine the closeness of synonyms in the L2-normalized feature space. We show that visual synonyms may successfully be used for vocabulary reduction. Furthermore, we show that combining the reduced visual vocabularies with synonym augmentation, we perform on par with the state-of-the-art bag-of-words approach, while having a 98% smaller vocabulary.

  • landmark Image retrieval using visual synonyms
    ACM Multimedia, 2010
    Co-Authors: Efstratios Gavves, Cees G M Snoek
    Abstract:

    In this paper, we consider the incoherence problem of the visual words in bag-of-words vocabularies. Different from existing work, which performs assignment of words based solely on closeness in descriptor space, we focus on identifying pairs of independent, distant words - the visual synonyms - that are still likely to host Image patches with similar appearance. To study this problems we focus on landmark Images, where we can examine whether Image Geometry is an appropriate vehicle for detecting visual synonyms. We propose an algorithm for the extraction of visual synonyms in landmark Images. To show the merit of visual synonyms, we perform two experiments. We examine closeness of synonyms in descriptor space and we show a first application of visual synonyms in a landmark Image retrieval setting. Using visual synonyms, we perform on par with the state-of-the-art, but with six times less visual words.

Efstratios Gavves - One of the best experts on this subject based on the ideXlab platform.

  • visual synonyms for landmark Image retrieval
    Computer Vision and Image Understanding, 2012
    Co-Authors: Efstratios Gavves, Cees G M Snoek, Arnold W M Smeulders
    Abstract:

    In this paper, we address the incoherence problem of the visual words in bag-of-words vocabularies. Different from existing work, which assigns words based on closeness in descriptor space, we focus on identifying pairs of independent, distant words - the visual synonyms - that are likely to host Image patches of similar visual reality. We focus on landmark Images, where the Image Geometry guides the detection of synonym pairs. Image Geometry is used to find those Image features that lie in the nearly identical physical location, yet are assigned to different words of the visual vocabulary. Defined in this way, we evaluate the validity of visual synonyms. We also examine the closeness of synonyms in the L2-normalized feature space. We show that visual synonyms may successfully be used for vocabulary reduction. Furthermore, we show that combining the reduced visual vocabularies with synonym augmentation, we perform on par with the state-of-the-art bag-of-words approach, while having a 98% smaller vocabulary.

  • landmark Image retrieval using visual synonyms
    ACM Multimedia, 2010
    Co-Authors: Efstratios Gavves, Cees G M Snoek
    Abstract:

    In this paper, we consider the incoherence problem of the visual words in bag-of-words vocabularies. Different from existing work, which performs assignment of words based solely on closeness in descriptor space, we focus on identifying pairs of independent, distant words - the visual synonyms - that are still likely to host Image patches with similar appearance. To study this problems we focus on landmark Images, where we can examine whether Image Geometry is an appropriate vehicle for detecting visual synonyms. We propose an algorithm for the extraction of visual synonyms in landmark Images. To show the merit of visual synonyms, we perform two experiments. We examine closeness of synonyms in descriptor space and we show a first application of visual synonyms in a landmark Image retrieval setting. Using visual synonyms, we perform on par with the state-of-the-art, but with six times less visual words.

Stefan Lehner - One of the best experts on this subject based on the ideXlab platform.

  • Ocean wind fields retrieved from the advanced synthetic aperture radar aboard ENVISAT
    Ocean Dynamics, 2004
    Co-Authors: Jochen Horstmann, W Koch, Stefan Lehner
    Abstract:

    In this paper an algorithm is presented which enables high-resolution ocean surface wind fields to be retrieved from the advanced synthetic aperture radar (ASAR) data acquired by the European remote sensing satellite ENVISAT. Wind directions are extracted from wind-induced streaks that are visible in ASAR Images at scales above 200 m and that are approximately in line with the mean surface wind direction. Wind speeds are derived from the normalized radar cross section (NRCS) and Image Geometry of the calibrated ASAR Images, together with the local ASAR-retrieved wind direction. Therefore the empirical C-band model CMOD4, which describes the dependency of the NRCS on wind and Image Geometry, is used. CMOD4 is a semi-empirical model, which was originally developed for the scatterometer of the European remote sensing satellites ERS-1 and 2 operating at C-band with vertical polarization. Consequently, CMOD4 requires modification when applied to ASAR Images that were acquired with horizontal polarization in transmitting and receiving. This is performed by considering the polarization ratio of the NRCS. To demonstrate the applicability of the algorithm, wind fields were computed from several ENVISAT ASAR Images of the North Sea and compared to atmospheric model results of the German weather service.

Jochen Horstmann - One of the best experts on this subject based on the ideXlab platform.

  • Ocean wind fields retrieved from the advanced synthetic aperture radar aboard ENVISAT
    Ocean Dynamics, 2004
    Co-Authors: Jochen Horstmann, W Koch, Stefan Lehner
    Abstract:

    In this paper an algorithm is presented which enables high-resolution ocean surface wind fields to be retrieved from the advanced synthetic aperture radar (ASAR) data acquired by the European remote sensing satellite ENVISAT. Wind directions are extracted from wind-induced streaks that are visible in ASAR Images at scales above 200 m and that are approximately in line with the mean surface wind direction. Wind speeds are derived from the normalized radar cross section (NRCS) and Image Geometry of the calibrated ASAR Images, together with the local ASAR-retrieved wind direction. Therefore the empirical C-band model CMOD4, which describes the dependency of the NRCS on wind and Image Geometry, is used. CMOD4 is a semi-empirical model, which was originally developed for the scatterometer of the European remote sensing satellites ERS-1 and 2 operating at C-band with vertical polarization. Consequently, CMOD4 requires modification when applied to ASAR Images that were acquired with horizontal polarization in transmitting and receiving. This is performed by considering the polarization ratio of the NRCS. To demonstrate the applicability of the algorithm, wind fields were computed from several ENVISAT ASAR Images of the North Sea and compared to atmospheric model results of the German weather service.

  • ocean winds from radarsat 1 scansar
    Canadian Journal of Remote Sensing, 2002
    Co-Authors: Jochen Horstmann, W Koch, Susanne Lehner, Rasmus Tonboe
    Abstract:

    This paper discusses an algorithm designed to retrieve high-resolution wind fields from scanning synthetic aperture radar (ScanSAR) data acquired on board the Canadian satellite RADARSAT-1. The ScanSAR operates at C-band with horizontal polarization. The wind directions are extracted from wind-induced streaks, e.g., from atmospheric boundary layer rolls or wind shadowing, which are approximately in line with the mean wind direction near the ocean surface. The wind speeds are derived from the normalized radar cross section (NRCS) and Image Geometry of the calibrated ScanSAR Images, together with the local wind direction retrieved from the Image. Therefore the semi-empirical C-band model CMOD4, which describes the dependency of the NRCS on wind and Image Geometry, is used. The CMOD4 was originally developed for the scatterometer of the European remote sensing satellites ERS-l and ERS-2 operating at C-band with vertical polarization. Consequently, the CMOD4 required modification for horizontal polarization, ...

W Koch - One of the best experts on this subject based on the ideXlab platform.

  • Ocean wind fields retrieved from the advanced synthetic aperture radar aboard ENVISAT
    Ocean Dynamics, 2004
    Co-Authors: Jochen Horstmann, W Koch, Stefan Lehner
    Abstract:

    In this paper an algorithm is presented which enables high-resolution ocean surface wind fields to be retrieved from the advanced synthetic aperture radar (ASAR) data acquired by the European remote sensing satellite ENVISAT. Wind directions are extracted from wind-induced streaks that are visible in ASAR Images at scales above 200 m and that are approximately in line with the mean surface wind direction. Wind speeds are derived from the normalized radar cross section (NRCS) and Image Geometry of the calibrated ASAR Images, together with the local ASAR-retrieved wind direction. Therefore the empirical C-band model CMOD4, which describes the dependency of the NRCS on wind and Image Geometry, is used. CMOD4 is a semi-empirical model, which was originally developed for the scatterometer of the European remote sensing satellites ERS-1 and 2 operating at C-band with vertical polarization. Consequently, CMOD4 requires modification when applied to ASAR Images that were acquired with horizontal polarization in transmitting and receiving. This is performed by considering the polarization ratio of the NRCS. To demonstrate the applicability of the algorithm, wind fields were computed from several ENVISAT ASAR Images of the North Sea and compared to atmospheric model results of the German weather service.

  • ocean winds from radarsat 1 scansar
    Canadian Journal of Remote Sensing, 2002
    Co-Authors: Jochen Horstmann, W Koch, Susanne Lehner, Rasmus Tonboe
    Abstract:

    This paper discusses an algorithm designed to retrieve high-resolution wind fields from scanning synthetic aperture radar (ScanSAR) data acquired on board the Canadian satellite RADARSAT-1. The ScanSAR operates at C-band with horizontal polarization. The wind directions are extracted from wind-induced streaks, e.g., from atmospheric boundary layer rolls or wind shadowing, which are approximately in line with the mean wind direction near the ocean surface. The wind speeds are derived from the normalized radar cross section (NRCS) and Image Geometry of the calibrated ScanSAR Images, together with the local wind direction retrieved from the Image. Therefore the semi-empirical C-band model CMOD4, which describes the dependency of the NRCS on wind and Image Geometry, is used. The CMOD4 was originally developed for the scatterometer of the European remote sensing satellites ERS-l and ERS-2 operating at C-band with vertical polarization. Consequently, the CMOD4 required modification for horizontal polarization, ...