Deep Texture Manifold for Ground Terrain Recognition

Jia Xue, Hang Zhang, Kristin Dana; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 558-567

Abstract


We present a texture network called Deep Encoding Pooling Network (DEP) for the task of ground terrain recognition. Recognition of ground terrain is an important task in establishing robot or vehicular control parameters, as well as for localization within an outdoor environment. The architecture of DEP integrates orderless texture details and local spatial information and the performance of DEP surpasses state-of-the-art methods for this task. The GTOS database (comprised of over 30,000 images of 40 classes of ground terrain in outdoor scenes) enables supervised recognition. For evaluation under realistic conditions, we use test images that are not from the existing GTOS dataset, but are instead from hand-held mobile phone videos of similar terrain. This new evaluation dataset, GTOS-mobile, consists of 81 videos of 31 classes of ground terrain such as grass, gravel, asphalt and sand. The resultant network shows excellent performance not only for GTOS-mobile, but also for more general databases (MINC and DTD). Leveraging the discriminant features learned from this network, we build a new texture manifold called DEP-manifold. We learn a parametric distribution in feature space in a fully supervised manner, which gives the distance relationship among classes and provides a means to implicitly represent ambiguous class boundaries. The source code and database are publicly available.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Xue_2018_CVPR,
author = {Xue, Jia and Zhang, Hang and Dana, Kristin},
title = {Deep Texture Manifold for Ground Terrain Recognition},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}
}