Detection of moving objects in railway using vision

In this paper, a new strategy to detect motion object in railway is presented, using vision and principal components analysis (PCA). For this purpose, a set of images of the railway static environment is first captured to obtain the transformation matrix that used in PCA. By means of this matrix, the successive images are projected in the transformation space and recovered. The motion detection is performed, evaluating the Euclidean distance between the original and recovered images. The image regions whose Euclidean distance are greater than a threshold, are considered like belonging to motion objects. The new of our system is the utilization of a method to obtain an adaptive threshold that allows to classify, within an image, zones without motion (background) and motion objects. A system with dynamic adjustment of this threshold is proposed, which it compensates to a great extent, illumination and others environmental conditions variations founded in outdoor spaces. Anyway, to show the validity and robustness of this method, the system has been implemented practically.