Real-Time Scene Understanding Using Deep Neural Networks for RoboCup SPL

Convolutional neural networks (CNNs) are the state-of-the-art method for most computer vision tasks. But, the deployment of CNNs on mobile or embedded platforms is challenging because of CNNs' excessive computational requirements. We present an end-to-end neural network solution to scene understanding for robot soccer. We compose two key neural networks: one to perform semantic segmentation on an image, and another to propagate class labels between consecutive frames. We trained our networks on synthetic datasets and fine-tuned them on a set consisting of real images from a Nao robot. Furthermore, we investigate and evaluate several practical methods for increasing the efficiency and performance of our networks. Finally, we present RoboDNN, a C++ neural network library designed for fast inference on the Nao robots.