Embedded Deep Learning for Vehicular Edge Computing

The accuracy of object recognition has been greatly improved due to the rapid development of deep learning, but the deep learning generally requires a lot of training data and the training process is very slow and complex. In this work, an Intel Movidius" Neural Compute Stick along with Raspberry Pi 3 Model B is used to analyze the objects in the real time images and videos for vehicular edge computing. The results shown in this study tells how the stick performs in conjunction with different operating systems and processing power.