We perform local contrast normalization [54] to the RGB input.
We use median frequency balancing [14] where the weight assigned to a class in the loss function is the ratio of the median of class frequencies computed on the entire training set divided by the class frequency.
use the code for training CamVid, here is the sample result
when the arch segnet-vgg16 change to segnet-vgg19, the detail about pedestrian is more clear.