|
| Key points and Visible Part Fusion Attention Network for Occluded Pedestrian Detection |
|
| Abstract: |
| Aiming at the problem of low detection accuracy of pedestrian in occluded scenes, this paper propose an key points and visible part fusion network for occluded pedestrian detection. The proposed algorithm constructs two attention modules by introducing human key points and the bounding box of visible parts respectively, which suppress the occluded parts in the channel features and spatial features of pedestrian features respectively. Experimental results on CityPersons and Caltech datasets demonstrate the effectiveness of the proposed algorithm. The MR (Miss Rate) is reduced to 40.78 on the Heavy subset of the CityPersons dataset and surpasses many outstanding methods. |
| Hits: 0 |
| Download times: 0 |
| The National Science Fund for Distinguished Young Scholars |
| Download reader |
