This paper discusses the maintenance optimization of arailway track, based on the observation of two dependent randomlyincreasing deterioration indicators. These two indicators are mod-elled through a bivariate Gamma process constructed by trivariatereduction. Empirical and maximum likelihood estimators are givenfor the process parameters and tested on simulated data. The EMalgorithm is used to compute the maximum likelihood estimators. Abivariate Gamma process is then fitted to real data of railway trackdeterioration. Preventive maintenance scheduling is studied, ensuringthat the railway track keeps a good quality with a high probability.The results are compared to those based on both indicators takenseparately, and also on one single indicator (usually taken for currenttrack maintenance). The results based on the joined information areproved to be safer than the other ones, which shows the interest ofthe bivariate model.