Mobile Device Based Outdoor Navigation With On-Line Learning Neural Network: A Comparison With Convolutional Neural Network

Zejia Zhengj, Juyang Weng; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2016, pp. 11-18

Abstract


Outdoor navigation is challenging with its dynamic environments. Traditional autonomous navigation systems construct 3D driving scenes to recognize open and occupied voxels by using laser range scanners, which are not available on mobile devices. Existing image-based navigation methods are costly in computation thus cannot be deployed onto a mobile device. We present an on-line learning neural network for real-time outdoor navigation using only the computational resources available on a standard mobile device. The network is trained to recognize the most relevant object in current navigation setting and make corresponding decisions. The network is compared with state of the art image classifier, the Convolutional Neural Network. Comparisons show that our network requires a minimal number of updates and converges significantly faster to better performance. The network successfully navigated in long-duration testing and blindfolded testing under sunny and cloudy weather conditions.

Related Material


[pdf]
[bibtex]
@InProceedings{Zhengj_2016_CVPR_Workshops,
author = {Zhengj, Zejia and Weng, Juyang},
title = {Mobile Device Based Outdoor Navigation With On-Line Learning Neural Network: A Comparison With Convolutional Neural Network},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2016}
}