Deep Texture Manifold for Ground Terrain Recognition

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 1 .

Towards Universal Representation for Unseen Action Recognition

“…This makes sense since objects and scenes could serve as the basis to construct arbitrary action videos and the semantic representation can alleviate such visual gaps. The motivation can also be ascribed to the success of CNNs [49,51,48]. With the help of off-the-shelf object detectors, such methods [28] could even perform zero-shot spatio-temporal action localization.…”

Frequency-Temporal Disagreement Adaptation for Robotic Terrain Classification via Vibration in a Dynamic Environment

“…All algorithms will be evaluated on the computer based on the gathered data. Among the terrains listed in [ 46 ], we select six terrains on which a robot is most likely to traverse to do the experiment. As shown in Figure 3 , some of them are artificial terrains (e.g., asphalt road), while some are natural ones (e.g., natural grass).…”

Deep Residual Texture Network for Terrain Recognition

“…However, this tandem method is to extract the texture features after the convolution features, and there is no effective fusion of the convolution features and the texture features. Later, Xue et al [34] proposed DEP that inputs the output features of the convolution layer into the coding layer and the pooling layer at the same time. It can not only extract the texture features of the image, but also preserve the convolution features of the CNN.…”

“…In [34], Xue et al expressed texture features by the orderless characteristic of texture, but the texture features can have different expressions in fact. In this paper, we want to extract the detailed information in the texture feature.…”