Egocentric hand-tracking annotation platform with difficulty-aware frame classification.
Built an egocentric hand-tracking annotation platform. Core challenge: automatically classify first-person video frames into 5 categories — no_hands, low_lighting, occluded, dexterous_pose, easy.
"Started simple: uniform 2fps sampling + single MediaPipe detector in IMAGE mode. Got 70% no_hands, 20% dexterous, 10% easy — but zero occlusion or low-lighting detection. Clear failure: occlusion, lighting, and complex poses were invisible."