An Efficient Sky Detection Algorithm From Fisheye Image Based on region classification and segment analysis
DOI:
https://doi.org/10.14738/tmlai.54.3335Keywords:
Region classification, RGB color descriptor, Segment analysis, LSD, Hellinger kernel-based distance.Abstract
In this paper, an efficient approach for automatic and accurate sky region detection from fisheye images is proposed. The proposed approach starts by segmenting the acquired image into regions using Statistical Region Merging method. After that, the segmented regions are characterized using local RGB color descriptor using image quantization. The next step consists of classifying the characterized regions into sky and non-sky regions by using maximal similarity based region classification through Hellinger kernel-based distance. In order to improve the obtained region classification results, a segment analysis based technique using Line Segment Detector is proposed. Experimental results prove the robustness and performance of the proposed procedure.
References
(1) Dhouha Attia. 2014. Segmentation d’images par combinaison adaptative couleur-texture et classification de pixels. : Applications la caractérisation de l’environnement de réception de signaux GNSS. PhD thesis, Université de ´ technologie Belfort-Montbéliard(Jun 2014).
(2) Y El merabet, Y Ruichek, S Ghaffarian, Z Samir, T Boujiha, R Touahni, and R. Messoussi. 2016. Horizon Line Detection from Fisheye Images Using Color Local Image Region Descriptors and Bhattacharyya Coefficient-Based Distance. In International Conference on Advanced Concepts for Intelligent Vision Systems. Springer International Publishing. 58–70.
(3) Juliette Marais et Cyril Meurie. 2013. Quantify et improve GNSS quality of service in land transportation by using image processing. First CNES-ONERA Workshop on Earth-Space Propagation, hal-00912681 (December 2013).
(4) A. El Idrissi, Y. El Merabet, Y. Ruichek, R. Touahni, A. Sbihi, C. Meurie, and A. Moussa. 2015. A Multiple-Objects Recognition Method Based on Region Similarity Measures: Application to Roof Extraction from Orthophotoplans. (IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 6, No. 11 (Novembre 2015).
(5) J. Marais, C. Meurie, S. Ambellouis, and Y. Ruichek. 2013. Projet CAPLOC. Combinaison de l’analyse d’images et la connaissance de la propagation des signaux pour la Localisation. (Agust 2013).
(6) L. Matthies, M. Maimone, A. Johnson, C. Yang, R. Willson, C. Villalpando, S. Goldberg, A. Huertas, A. Stein, and A. Angelova. 2007. Computer vision on mars. Int. J. Comput. Vis. 75, 1 (2007), 67-92.
(7) J. Ning, L. Zhang, D. Zhang, and C. Wu. 2009. Interactive image segmentation by maximal similarity based region merging. (Mars 2009).
(8) R. Nock and F Nielsen. 2004. Statistical region merging.
IEEE Trans. Pattern Anal. Machine Intelligence 26, 11 (2004), 1452–1458.
(9) S. Ramalingam, S. Bouaziz, P. Sturm, and M. Brand. 2010. SKYLINE2GPS: Localization in Urban Canyons Using Omni-Skylines. IEEE International Conference on Intelligent Robots and Systems (2010), 3816–3823.
(10) Z. B Sbeh, L. D Cohen, G Mimoun, and G Coscas. 2001. A New Approach of Geodesic Reconstruction for Drusen Segmentation in Eye Fundus Images. IEEE Transactions on medical imaging 20, 12 (Decembre 2001), 1321–1333.
(11) Y. Shang, G. Li, Z. Luan, X. Zhou, and G Guo. 2016. Sky detection by effective context inference. Neurocomputing 208 (2016), 238–248.
(12) J. A Shufelt. 1999. Performance evaluation and analysis of
monocular building extraction from aerial imagery. IEEE Trans. Pattern Anal. Machine Intell 21 (1999), 311–326.
(13) R. G Von Gioi, J Jakubowicz, J. M Morel, and G Randall. 2012. LSD: a line segment
