YEEHaD: YOLO-based extremely efficient hand detection

Gibran Benitez-Garcia; Hiroki Takahashi

doi:10.1117/12.3017906

2 May 2024 YEEHaD: YOLO-based extremely efficient hand detection

Gibran Benitez-Garcia, Hiroki Takahashi

Proceedings Volume 13164, International Workshop on Advanced Imaging Technology (IWAIT) 2024; 131640A (2024) https://doi.org/10.1117/12.3017906
Event: International Workshop on Advanced Imaging Technology (IWAIT) 2024, 2024, Langkawi, Malaysia

Abstract

This paper presents YEEHaD, an Extremely Efficient Hand Detection approach based on YOLO architecture. We replace the Cross Stage Partial (CSP) blocks of YOLOv5 with HG blocks, which utilize lightweight convolutions with the squeeze and excitation technique, enhancing detection efficiency without compromising performance. YEEHaD demonstrates remarkable computational efficiency, maintaining under 3 GFLOPs and using fewer than 1.1M parameters. We conduct extensive evaluations of YEEHaD’s performance on two public datasets and provide manual annotations of hand locations of about 40K frames from the NVGesture dataset. Its detection accuracy is comparable with heavier versions of YOLOv5, achieving 99.45 mAP@0.5 on the Hagrid dataset and 99.43 mAP@0.5 on the NVGesture dataset. Additionally, we analyze YEEHaD’s performance on standard desktop GPUs and two GPU-embedded devices. Our model can run at 220 FPS on a standard 2080Ti GPU. This adaptability is explored in-depth, showcasing its potential in different hardware environments. Finally, we delve into the possibility of fine-tuning YEEHaD for hand gesture recognition (HGR), offering insights into the balance between efficiency and effectiveness in HGR applications.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Gibran Benitez-Garcia and Hiroki Takahashi "YEEHaD: YOLO-based extremely efficient hand detection", Proc. SPIE 13164, International Workshop on Advanced Imaging Technology (IWAIT) 2024, 131640A (2 May 2024); https://doi.org/10.1117/12.3017906

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available