Optimizing Hand Region Detection in MediaPipe Holistic Full-Body Pose Estimation to Improve Accuracy and Avoid Downstream Errors
This paper addresses a critical flaw in MediaPipe Holistic's hand Region of Interest (ROI) prediction, which struggles with non-ideal hand orientations, affecting sign language recognition accuracy. We propose a data-driven approach to enhance ROI estimation, leveraging an enriched feature set including additional hand keypoints and the z-dimension. Our results demonstrate better estimates, with higher Intersection-over-Union compared to the current method. Our code and optimizations are available at https://github.com/sign-language-processing/mediapipe-hand-crop-fix.
Code (1)
Tasks
Pose EstimationSign Language RecognitionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Real-time Bangla Sign Language Translator
The human body communicates through various meaningful gestures, with sign language using hands being a prominent example. Bangla Sign Language Translation (BSLT) aims to bridge communication gaps for the deaf and mute c…
Sign Language TranslationTranslationVirtual Ring Try-On
This paper presents an innovative approach that enables the users to capture their hand and try the jewel ring on their hand. The user captures the image of the hand using the React Native base GUI of the mobile applicat…
Object DetectionEvaluation of Pose Estimation Systems for Sign Language Translation
Many sign language translation (SLT) systems operate on pose sequences instead of raw video to reduce input dimensionality, improve portability, and partially anonymize signers. The choice of pose estimator is often trea…
Sign Language TranslationPose EstimationFall Detection from Indoor Videos using MediaPipe and Handcrafted Feature
Falls are a common cause of fatal injuries and hospitalization. However, having fall detection on person, in particular for senior citizens can prove to be critical. Presently,there are handheld, ambient detector and vis…
EMPATH: MediaPipe-Aided Ensemble Learning with Attention-Based Transformers for Accurate Recognition of Bangla Word-Level Sign Language
In this paper, we introduce EMPATH, an advanced computational framework developed to substantially enhance the recognition of Bangla Sign Language (BdSL). By integrating Ensemble Learning, MediaPipe Holistic for gesture …
Ensemble LearningSign Language Recognition