Abstract | ||
---|---|---|
In this paper, we introduce a video-based wildfire detection scheme based on a computationally efficient additive deep neural network, which we call AddNet. This AddNet is based on a multiplication-free vector operator, which performs only addition and sign manipulation operations. In this regard, we construct a dot product-like operation from the mf-operator and use it to define dense and convolutional feed-forwarding passes in AddNet. We train AddNet on images taken from forestry surveillance cameras. Our experiments show that AddNet can achieve a time-saving by 12.4% when compared to an equivalent regular convolutional neural network (CNN). Furthermore, the smoke recognition performance of AddNet is as good as regular CNNs and substantially better than binary-weight neural networks. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1007/s11760-019-01600-7 | Signal, Image and Video Processing |
Keywords | DocType | Volume |
Computationally efficient, Neural network, Additive neural network, Real-time, Forest fire detection | Journal | 14 |
Issue | ISSN | Citations |
4 | 1863-1703 | 3 |
PageRank | References | Authors |
0.43 | 0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hongyi Pan | 1 | 6 | 2.58 |
Diaa Badawi | 2 | 6 | 3.93 |
Xi Zhang | 3 | 16 | 7.62 |
Cem Emre Akbas | 4 | 8 | 3.73 |