Abstract | ||
---|---|---|
On-road risk detection and alert system is a crucial and important task in our day to day life. Deep Learning approaches have got much attention in solving this noble task. In this paper, we have performed a comparative study on two recent architectures that handle the on-road risk detection task, which are Block-Wise Detection and Modular Selective Network (MS-Net). In the Block-Wise Detection, we have used the VGG19, VGG19-BN, and ResNet family as the backbone network. On the other hand, for MS-Net we have used the ResNet-44 as the router and ResNet-101 as the expert network. In this experiment, we evaluate our model on an “on-road risk detection dataset”, which was created by our research group using an RGB-D sensor mounted on a senior car. On this dataset, we can achieve an accuracy of 89.40% for MS-Net. For the Block-Wise Detection model, we can achieve an accuracy of 90.51% if we use ResNet-50 as the backbone network. However, if we choose the network models used in MS-Net, we can double the inference speed. Thus, compared with Block-Wise Detection, we think the overall performance of MS-NET is better, and is potentially more useful for driving assistance of elderly drivers. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/iCAST51195.2020.9319484 | 2020 11th International Conference on Awareness Science and Technology (iCAST) |
Keywords | DocType | ISSN |
Obstacle Detection,Deep Learning,Convolutional Neural Network | Conference | 2325-5986 |
ISBN | Citations | PageRank |
978-1-7281-9120-1 | 0 | 0.34 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Huitao Wang | 1 | 0 | 0.34 |
Kai Su | 2 | 0 | 0.34 |
Intisar M. D. Chowdhury | 3 | 0 | 0.34 |
Qiangfu Zhao | 4 | 214 | 62.36 |
Yoichi Tomioka | 5 | 7 | 5.54 |