2026-05-27T12:11:45Zhttps://riuma.uma.es/rest/oai/request

oai:riuma.uma.es:10630/296902026-02-03T11:07:26Zcom_10630_2254col_10630_37953

Foreground detection by competitive learning for varying input distributions López-Rubio, Ezequiel Molina-Cabello, Miguel Ángel Luque-Baena, Rafael Marcos Domínguez-Merino, Enrique Visión por ordenador Reconocimiento de formas (Informática) Copyright Owner. Versión definitiva disponible en el DOI indicado. López-Rubio, E., Molina-Cabello, M. A., Luque-Baena, R. M., & Domínguez, E. (2018). Foreground detection by competitive learning for varying input distributions. International journal of neural systems, 28(05), 1750056. One of the most important challenges in computer vision applications is the background modeling, especially when the background is dynamic and the input distribution might not be stationary, i.e. the distribution of the input data could change with time (e.g. changing illuminations, waving trees, water, etc.). In this work, an unsupervised learning neural network is proposed which is able to cope with progressive changes in the input distribution. It is based on a dual learning mechanism which manages the changes of the input distribution separately from the cluster detection. The proposal is adequate for scenes where the background varies slowly. The performance of the method is tested against several state-of-the-art foreground detectors both quantitatively and qualitatively, with favorable results. 2024-02-02T09:47:35Z 2024-02-02T09:47:35Z 2018 journal article López-Rubio E, Molina-Cabello MA, Luque-Baena RM, Domínguez E. Foreground Detection by Competitive Learning for Varying Input Distributions. Int J Neural Syst. 2018 Jun;28(5):1750056. doi: 10.1142/S0129065717500563. https://hdl.handle.net/10630/29690 10.1142/S0129065717500563 eng open access World Scientific Publishing