Table 3 Comparison of hand detection accuracy on recorded videos between Faster-RCNN and Mediapipe.
From: Visual imitation learning from one-shot demonstration for multi-step robot pick and place tasks
Faster-RCNN | MediaPipe | |
|---|---|---|
Video 1 | \(100.00\%\) | \(93.99\%\) |
Video 2 | \(95.76\%\) | \(8.86\%\) |
Video 3 | \(99.82\%\) | \(15.74\%\) |
Video 4 | \(92.59\%\) | \(9.94\%\) |
Video 5 | \(91.67\%\) | \(12.50\%\) |
