Towards Deep Learning based Hand Keypoints Detection for Rapid Sequential Movements from RGB Images

TL;DR

This paper introduces a new hand keypoints benchmark dataset for rapid finger movements and evaluates existing methods, aiming to improve cognitive assessments through hand pose estimation from RGB images.

Contribution

The paper presents a novel dataset focused on rapid finger movements and provides a comprehensive evaluation of current hand keypoint detection methods on this dataset.

Findings

Existing methods show varying performance on rapid finger movements

The new dataset enables benchmarking for cognitive behavior monitoring

Results highlight challenges in hand keypoint detection for quick motions

Abstract

Hand keypoints detection and pose estimation has numerous applications in computer vision, but it is still an unsolved problem in many aspects. An application of hand keypoints detection is in performing cognitive assessments of a subject by observing the performance of that subject in physical tasks involving rapid finger motion. As a part of this work, we introduce a novel hand key-points benchmark dataset that consists of hand gestures recorded specifically for cognitive behavior monitoring. We explore the state of the art methods in hand keypoint detection and we provide quantitative evaluations for the performance of these methods on our dataset. In future, these results and our dataset can serve as a useful benchmark for hand keypoint recognition for rapid finger movements.