Scene-parsing for disaster environments by means of a convolutional neural network

抄録

Disaster robotics poses particular challenges for computer vision, both in terms of image material characteristics (due to motion blur, difficult light conditions, lack of up/down orientation, etc.), and in terms of learning data (limited availability, difficulty of annotation due to image quality, etc.). We developed a system for real-time scene-parsing, intended for use in a support system for operators of remote-controlled mobile robots employed in disaster areas. Our testbed is video footage gathered by a snake-like mobile robot exploring an (artificial) collapsed building environment. The core of the system is a relatively small-scale convolutional neural network. Our approach combines pixel-level learning with superpixel-level classification, in an effort to learn efficiently from a relatively small number of partially annotated frames. Our classification system is capable of real-time operation, and demonstrates that convolutional neural networks can be employed effectively even under the harsh conditions imposed by disaster robotics.