Convolutional Patch Networks with Spatial Prior for Road Detection and Urban Scene Understanding
This work addresses pixel-wise labeling challenges in computer vision for applications like autonomous driving and urban analysis, offering a practical guideline for training such networks.
The paper tackles road detection and urban scene understanding by introducing convolutional patch networks that incorporate spatial priors, achieving state-of-the-art results on the KITTI and LabelMeFacade datasets.
Classifying single image patches is important in many different applications, such as road detection or scene understanding. In this paper, we present convolutional patch networks, which are convolutional networks learned to distinguish different image patches and which can be used for pixel-wise labeling. We also show how to incorporate spatial information of the patch as an input to the network, which allows for learning spatial priors for certain categories jointly with an appearance model. In particular, we focus on road detection and urban scene understanding, two application areas where we are able to achieve state-of-the-art results on the KITTI as well as on the LabelMeFacade dataset. Furthermore, our paper offers a guideline for people working in the area and desperately wandering through all the painstaking details that render training CNs on image patches extremely difficult.