Continuous Ground-Truth Construction and a Recovery Policy for Air--Water Robotic Tracking
Visual tracking across the air-water interface is challenged by splashes, bubbles, refraction, reflections, and abrupt appearance changes that can temporarily invalidate observations.
ProofPaper ↗
Key points
- This setting poses two coupled difficulties: first, for evaluation, image-only annotation cannot reliably describe the target's physical location during visual blindness; second, for online tracking, corrupted observations can contaminate motion estimates and appearance templates.
- We address the first difficulty with a construction pipeline that synchronizes camera frames with motion-capture poses, projects known target geometry, corrects underwater projection with a medium-gated residual, and subjects the annotations to manual review.
- We further introduce a Cross-Medium Recovery Policy (CMRP) centered on confidence-triggered template selection.
- On selected cross-medium transition and occlusion-recovery intervals, CMRP increases MixFormerV2 tracking coverage from 47.91% to 50.43% relative to Official updating, while mean loss-to-recovery latency over successfully recovered videos decreases from 55.3 to 49.3 frames.
Sources (1)
- [1]Continuous Ground-Truth Construction and a Recovery Policy for Air--Water Robotic TrackingarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 02:11 AM
Visual tracking across the air-water interface is challenged by splashes, bubbles, refraction, reflections, and abrupt appearance changes that can temporarily invalidate observations.
This setting poses two coupled difficulties: first, for evaluation, image-only annotation cannot reliably describe the target's physical location during visual blindness; second, for online tracking, corrupted observations can contaminate motion estimates and appearance templates.
Extractive summary: sentences quoted from the sources.