No abstract

Conventional surface crack segmentation requires images manually labelled by a trained expert. It is a challenging task as cracks can vary in orientation and size, with some parts of cracks only being one pixel wide. Further, available training data for crack segmentation is sparse. In this work we propose to automate this annotation task, by introducing a fully convolutional U-Net based architecture for semantic segmentation of surface cracks which allows for the use of small datasets through a patch based training process. Our proposed configuration makes use of residual connections inside the convolutional blocks as well as including an attention based gating mechanism between the encoder and decoder section of this architecture, which only propagates relevant activations further. Using our proposed architecture we achieve new state of the art results in two different crack datasets, outperforming the previous best results in two metrics each.

No abstract

No abstract

This paper describes the prototype implementation of a pervasive, wearable augmented reality (AR) system based on a full bodymotion-capture system using low-power wireless sensors. The system uses body motion to visualize and interact with virtual objects populating AR settings. Body motion is used to implement a whole body gesture-driven interface to manipulate the virtual objects. Gestures are mapped to correspondent behaviors for virtual objects, such as controlling the playback and volume of virtual audio players or displaying a virtual object's metadata.