# Convolutional Patch Networks with Spatial Prior for Road Detection and Urban Scene Understanding Source: [Convolutional Patch Networks with Spatial Prior for Road Detection and Urban Scene Understanding]() Collection index: [llms.txt]() Data updated: 2025-10-25T20:04:28.118Z Authors: Clemens-Alexander Brust, Sven Sickert, Marcel Simon, Erik Rodner, Joachim Denzler Published: 2015-02-23T08:47:37.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Drivable Region Segmentation on Thermal-Road (test)](): Drivable Region Segmentation; Thermal-Road (test); Error Rate (campus): 36.4. ## Original sources and implementation [Original paper]() [PDF]()