Research Article
Object Extraction of Tennis Video Based on Deep Learning
Table 5
Extraction candidate area and extraction speed of HyperNet model.
| | Frame number | Bounding box | Speed |
| | Frame 26 | 31 | 1.462 s | | Frame 39 | 26 | 1.261 s | | Frame 137 | 44 | 1.572 s | | Frame 294 | 16 | 1.021 s | | Frame 96 | 35 | 1.417 s | | Frame 319 | 26 | 1.258 s | | Frame 283 | 29 | 1.342 s |
|
|
