EVALUACIÓN DE LA PERSISTENCIA DE PUNTOS DE INTERÉS DADOS POR SIFT, SURF, ORB Y GFTT BAJO MOVIMIENTO EN SUPERFICIES PLANARES (ASSESSMENT OF THE PERSISTENCE OF POINTS OF INTEREST GIVEN BY SIFT, SURF, ORB AND GFTT UNDER MOVEMENTS ON PLANAR SURFACES)
Resumen
En el área de la visión computacional y procesamiento de imágenes uno de los temas de mayor interés en la comunidad es la interpretación de escenas a partir de la extracción de puntos de interés. Existen muchos métodos y variantes para la extracción de estos puntos. Aquí los métodos SIFT (por sus siglas en inglés, Scale-Invariant Feature Transform, Transformación de características invariables a escala), el método SURF (Speeded-Up Robust Features, Características robustas aceleradas), el método ORB (Oriented FAST and Rotated BRIEF, BREVE Orientación rápida y brevemente rotada) y GFTT (Good Features To Track, Buenas características para rastrear) de extracción de puntos de interés serán estudiados. Dadas las diferencias entre los descriptores propios de cada método, se creó un descriptor compatible para los cuatro métodos. Permitiendo así, el realizar una comparativa del rastreo de los puntos de interés bajo las mismas condiciones. Además de conocer el desempeño de la persistencia por cada método. Esto, con el objetivo de identificar cuáles son los métodos que conservan la mayor cantidad de puntos de interés ante el video de los movimientos de un dispositivo móvil autónomo bajo movimientos en el plano cartesiano.
Palabras Clave: Descriptores locales, Persistencia, Puntos de interés.
Abstract
In the area of computational vision and image processing one of the topics of the greatest interest in the community is the interpretation of motion scenes base on the extraction of points of interest. There are many methods and variants to extract these points. Here are the SIFT methods (Scale-Invariant Feature Transform), the SURF method (Speeded-Up Robust Features), the ORB method (Oriented FAST and Rotated BRIEF), BRIEF ORIENTED FAST and ROTATED) and GFTT (Good Features To Track) the extraction methods of Points of Interest (POI) will be studied. Given the differences between the descriptors of each method, a compatible descriptor was created for all four methods. So, the tracking comparison of POIs under the same conditions. Aiming know the persistence performance by each method. This, in order to identify the methods that retain the most points by using the video of movements of a mobile self employed device in the cartesian plane.
Keywords: Local descriptors, Persistence, Tracking, Points of interest.
Texto completo:
452-466 PDFReferencias
González, R. C., & Woods, R. E. (2002). Digital Image Processing. 2nd edn Prentice Hall. New Jersey, 793.
Yun, Q. (2018). IMAGE AND VIDEO COMPRESSION FOR MULTIMEDIA ENGINEERING: Fundamentals, Algorithms, and... Standards. crc Press.
Adel, E., Elmogy, M., & Elbakry, H. (2014, December). Real time image mosaicing system based on feature extraction techniques. In 2014 9th International Conference on Computer Engineering & Systems (ICCES) (pp. 339-345). IEEE.
Li, Y., Wang, S., Tian, Q., & Ding, X. (2015). A survey of recent advances in visual feature detection. Neurocomputing, 149, 736-751.
Tareen, S. A. K., & Saleem, Z. (2018, March). A comparative analysis of sift, surf, kaze, akaze, orb, and brisk. In 2018 International conference on computing, mathematics and engineering technologies (iCoMET) (pp. 1-10). IEEE.
Rivera, F. J. V., Vargas, D. M., & Ruíz, M. Á. (2019). Comparative Analysis of Interest Point Detectors Algorithms on Robotic Operative System. Research in Computing Science, 148, 55-64.
Bojanić, D., Bartol, K., Pribanić, T., Petković, T., Donoso, Y. D., & Mas, J. S. (2019, September). On the Comparison of Classic and Deep Keypoint Detector and Descriptor Methods. In 2019 11th International Symposium on Image and Signal Processing and Analysis (ISPA) (pp. 64-69). IEEE.
Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints. International journal of computer vision, 60(2), 91-110.
Ansari, S. (2019, February). A Review on SIFT and SURF for Underwater Image Feature Detection and Matching. In 2019 IEEE International Conference on Electrical, Computer and Communication Technologies (ICECCT) (pp. 1-4). IEEE.
Awad, A. I., & Hassaballah, M. (2016). Image feature detectors and descriptors. Studies in Computational Intelligence. Springer International Publishing, Cham.
Karami, E., Prasad, S., & Shehata, M. (2017). Image matching using SIFT, SURF, BRIEF and ORB: performance comparison for distorted images. arXiv preprint arXiv:1710.02726.
Bay, H., Ess, A., Tuytelaars, T., & Van Gool, L. (2008). Speeded-up robust features (SURF). Computer vision and image understanding, 110(3), 346-359.
Rublee, E., Rabaud, V., Konolige, K., & Bradski, G. (2011, November). ORB: An efficient alternative to SIFT or SURF. In 2011 International conference on computer vision (pp. 2564-2571). Ieee.
Shi, J. (1994, June). Good features to track. In 1994 Proceedings of IEEE conference on computer vision and pattern recognition (pp. 593-600). IEEE.
URL de la licencia: https://creativecommons.org/licenses/by/3.0/deed.es
Pistas Educativas está bajo la Licencia Creative Commons Atribución 3.0 No portada. 
TECNOLÓGICO NACIONAL DE MÉXICO / INSTITUTO TECNOLÓGICO DE CELAYA
Antonio García Cubas Pte #600 esq. Av. Tecnológico, Celaya, Gto. México
Tel. 461 61 17575 Ext 5450 y 5146
pistaseducativas@itcelaya.edu.mx