Deep Texture Manifold for Ground Terrain Recognition

03/29/2018
by   Jia Xue, et al.
4

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 sim- ilar 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). Lever- aging 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.

READ FULL TEXT

page 1

page 2

page 3

page 5

research
01/01/2020

Histogram Layers for Texture Analysis

We present a histogram layer for artificial neural networks (ANNs). An e...
research
09/22/2020

Differential Viewpoints for Ground Terrain Material Recognition

Computational surface modeling that underlies material recognition has t...
research
05/23/2019

Multi-level Texture Encoding and Representation (MuLTER) based on Deep Neural Networks

In this paper, we propose a multi-level texture encoding and representat...
research
12/08/2016

Deep TEN: Texture Encoding Network

We propose a Deep Texture Encoding Network (Deep-TEN) with a novel Encod...
research
12/07/2016

Differential Angular Imaging for Material Recognition

Material recognition for real-world outdoor surfaces has become increasi...
research
04/17/2020

Modeling Extent-of-Texture Information for Ground Terrain Recognition

Ground Terrain Recognition is a difficult task as the context informatio...
research
09/03/2021

Model-Based Parameter Optimization for Ground Texture Based Localization Methods

A promising approach to accurate positioning of robots is ground texture...

Please sign up or login with your details

Forgot password? Click here to reset