Abstract:Precise localization is crucial to many computer vision tasks. Optical flow can help by providing motion boundaries which can serve as proxy for object boundaries. This paper investigates how useful these motion boundaries are in improving semantic segmentation. As there is no dataset readily available for this task, we compute the motion boundary maps with a pre-trained model from Weinzaepfel et al. (CVPR 2015) on the CamVid dataset. With these motion boundary maps and the corresponding RGB images, we train a convolutional neural network end-to-end, for the task of semantic segmentation. The experimental results show that the network has learned to incorporate the motion boundaries and that these improve the object localization.
Enter your feedback below and we'll get back to you as soon as possible.