Exportar Publicação
A publicação pode ser exportada nos seguintes formatos: referência da APA (American Psychological Association), referência do IEEE (Institute of Electrical and Electronics Engineers), BibTeX e RIS.
Hamad, M., Conti, C., Nunes, P. & Soares, L. D. (2023). Hyperpixels: Flexible 4D over-segmentation for dense and sparse light fields. IEEE Transactions on Image Processing. 32, 3790-3805
M. F. Hamad et al., "Hyperpixels: Flexible 4D over-segmentation for dense and sparse light fields", in IEEE Transactions on Image Processing, vol. 32, pp. 3790-3805, 2023
@article{hamad2023_1724525668924, author = "Hamad, M. and Conti, C. and Nunes, P. and Soares, L. D.", title = "Hyperpixels: Flexible 4D over-segmentation for dense and sparse light fields", journal = "IEEE Transactions on Image Processing", year = "2023", volume = "32", number = "", doi = "10.1109/TIP.2023.3290523", pages = "3790-3805", url = "https://ieeexplore.ieee.org/document/10173755" }
TY - JOUR TI - Hyperpixels: Flexible 4D over-segmentation for dense and sparse light fields T2 - IEEE Transactions on Image Processing VL - 32 AU - Hamad, M. AU - Conti, C. AU - Nunes, P. AU - Soares, L. D. PY - 2023 SP - 3790-3805 SN - 1057-7149 DO - 10.1109/TIP.2023.3290523 UR - https://ieeexplore.ieee.org/document/10173755 AB - 4D Light Field (LF) imaging, since it conveys both spatial and angular scene information, can facilitate computer vision tasks and generate immersive experiences for end-users. A key challenge in 4D LF imaging is to flexibly and adaptively represent the included spatio-angular information to facilitate subsequent computer vision applications. Recently, image over-segmentation into homogenous regions with perceptually meaningful information has been exploited to represent 4D LFs. However, existing methods assume densely sampled LFs and do not adequately deal with sparse LFs with large occlusions. Furthermore, the spatio-angular LF cues are not fully exploited in the existing methods. In this paper, the concept of hyperpixels is defined and a flexible, automatic, and adaptive representation for both dense and sparse 4D LFs is proposed. Initially, disparity maps are estimated for all views to enhance over-segmentation accuracy and consistency. Afterwards, a modified weighted K-means clustering using robust spatio-angular features is performed in 4D Euclidean space. Experimental results on several dense and sparse 4D LF datasets show competitive and outperforming performance in terms of over-segmentation accuracy, shape regularity and view consistency against state-of-the-art methods. ER -