Abstract | ||
---|---|---|
Pedestrian detection is a key problem for automatic driving, and the results have been improved significantly via deep convolutional networks. However, there is still room to improve the performance of pedestrian detection by carefully dealing with some critical issues. To take advantages of more discriminative information for pedestrian detection, we propose a novel architecture to auto-choose semantic as well as specific information among the feature maps at different levels and integrate valuable information among the feature maps in multi-scales. Particularly, our architecture consists of feature maps concatenating in different levels and feature maps integrating with multi-scales. Both the operations are equipped with a competitive attention block. The architecture has the ability to obtain more efficient and discriminating features for pedestrian detection. In comparison with the other prevailing models, our architecture provides superior performance. The promising results achieved through experimentation with this architecture achieve a new state-of-the-art on Caltech dataset. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/ACCESS.2019.2896201 | IEEE ACCESS |
Keywords | Field | DocType |
Pedestrian detection,feature fusion,competitive attention,semantic supervision | Computer vision,Feature fusion,Computer science,Artificial intelligence,Pedestrian detection,Distributed computing | Journal |
Volume | ISSN | Citations |
7 | 2169-3536 | 1 |
PageRank | References | Authors |
0.36 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhichang Chen | 1 | 1 | 0.36 |
Li Zhang | 2 | 4 | 2.18 |
Khattak Abdul Mateen | 3 | 1 | 0.36 |
Wanlin Gao | 4 | 8 | 3.35 |
Minjuan Wang | 5 | 304 | 41.52 |