Accurate Hand Keypoint Localization on Mobile Devices
This work addresses the problem of efficient hand keypoint estimation for mobile device applications, representing an incremental improvement in computational performance.
The paper tackles 2D hand keypoint localization from color images by proposing a CNN-based method that computes heatmaps for keypoints, achieving accuracy comparable to or better than state-of-the-art methods while significantly improving computational efficiency, making it suitable for mobile applications.
We present a novel approach for 2D hand keypoint localization from regular color input. The proposed approach relies on an appropriately designed Convolutional Neural Network (CNN) that computes a set of heatmaps, one per hand keypoint of interest. Extensive experiments with the proposed method compare it against state of the art approaches and demonstrate its accuracy and computational performance on standard, publicly available datasets. The obtained results demonstrate that the proposed method matches or outperforms the competing methods in accuracy, but clearly outperforms them in computational efficiency, making it a suitable building block for applications that require hand keypoint estimation on mobile devices.