Geometric Filtering of Matches Between Points in Bands of Hyperspectral Cubes

Autor(es)

Berveglieri, Adilson ^[1] ; Tommaselli, Antonio Maria Garcia ^[2]

Afiliação do(s) autor(es)

^[1] Sao Paulo State Univ, Dept Stat, BR-19060900 Presidente Prudente - Brazil

^[2] Sao Paulo State Univ, Dept Cartog, BR-19060900 Presidente Prudente - Brazil

• Tipo de documento: Artigo Científico
• Fonte: IEEE Geoscience and Remote Sensing Letters; v. 16, n. 3, p. 492-496, MAR 2019.
• Citações Web of Science: 0

Resumo

Hyperspectral images can present low contrast, noisy pixels, and illumination variation among bands, which complicates the extraction of interest points and reduces the number of reliable image matches affecting subsequent tasks as band registration and bundle adjustment. Once matched points have been determined, a technique to select correct matches in sets with outliers is required, as well as to fix mismatches. In this letter, we apply a filtering technique that uses a majority voting algorithm combined with a 2-D Helmert geometric transformation to identify consistent matches. The correct matches also allow the estimation of parameters of a geometric transformation, which enables point transfer between images. Thus, mismatches can be fixed to their correct positions. Experiments were performed with the proposed technique using hyperspectral images that were collected with a lightweight camera using the time-sequential principle, while onboard an unmanned aerial vehicle. Scale-invariant feature transform was used for both keypoint extraction and image matching. Reliable matches were extracted from the sets with outliers, and incorrect matches were fixed. The results of the technique were compared with an algorithm based on random sample consensus. In the comparison, the proposed technique was efficient in extracting a larger number of correct matches. In addition, 85% of the incorrect matches were recovered, which significantly increased the density of matched pairs. (AU)

• Processo FAPESP: 13/50426-4 - Unmanned airborne vehicle-based 4D remote sensing for mapping Rain Forest biodiversity and its change in Brazil (UAV_4D_Bio)
• Beneficiário: Antonio Maria Garcia Tommaselli
• Modalidade de apoio: Auxílio à Pesquisa - Regular
• Processo FAPESP: 14/05033-7 - Orientação Integrada de Imagens Hiperespectrais Coletadas por VANT
• Beneficiário: Adilson Berveglieri
• Modalidade de apoio: Bolsas no Brasil - Pós-Doutorado