Urban road area recognition in ITS based on mean shift method

【摘要】 <正> A color-based visual technique is described based on the mean shift image segmentation method providing relevant information for robust localization of the visible road area in Urban Intelligent Transportation System (U-ITS). The traffic image sequences are firstly trained to extract the background and then segmented into separated parts by the mean shift method as initialization, regions with the number of pixels not less than a threshold and with more uniform surfaces with the "same" color compared to their environment are filtered as recognized road area. The algorithm given in this paper can present road area recognition with arbitrary shapes, which is fit for unstructured road applications in urban cities very well.更多还原

【Abstract】 A color-based visual technique is described based on the mean shift image segmentation method providing relevant information for robust localization of the visible road area in Urban Intelligent Transportation System (U-ITS). The traffic image sequences are firstly trained to extract the background and then segmented into separated parts by the mean shift method as initialization, regions with the number of pixels not less than a threshold and with more uniform surfaces with the "same" color compared to their environment are filtered as recognized road area. The algorithm given in this paper can present road area recognition with arbitrary shapes, which is fit for unstructured road applications in urban cities very well.更多还原