Optimization and evaluation of deep architectures for ambient awareness on a sidewalk
Abstract
We optimize and compare the performance of different deep learning architectures for awareness on a sidewalk using small form factor devices such as Raspberry Pi 3. Our main objective is to find deep learning architecture that is complex enough to accurately classify a set obstacles on the sidewalk. Out selection criteria are: minimum number of parameters, lower power consumption, and robustness against the effect of the diurnal cycle. In particular, we compare the performance of GoogleNet, ResNet, and VGG-16 on a database constructed for AS applications. Empirical evaluation on AS database suggests that the performance of ResNet is superior compared to other architectures e.g., 99.46% and 97.69% on RGB and La b respectively. To further our objective we optimize the hyperparameters of ResNet to find architecture with a lower number of parameters without losing accuracy. Furthermore, we investigate the efficacy of different color spaces to address problems related to the diurnal cycle and power usage without sacrificing accuracy and generalizability.
Publication Title
Proceedings of the International Joint Conference on Neural Networks
Recommended Citation
Yeasin, M., & Ahmed, F. (2017). Optimization and evaluation of deep architectures for ambient awareness on a sidewalk. Proceedings of the International Joint Conference on Neural Networks, 2017-May, 2692-2697. https://doi.org/10.1109/IJCNN.2017.7966186
