Rule Of Thumb: Deep derotation for improved fingertip detection
This work addresses fingertip detection for hand pose estimation, but it is incremental as it builds on existing state-of-the-art methods without introducing a fundamentally new approach.
The paper tackles the problem of per-frame fingertip detection in depth images by integrating a deep convolutional neural network for global orientation regression with an in-plane image derotation scheme, DeROT, resulting in significant classification improvements over baseline methods.
We investigate a novel global orientation regression approach for articulated objects using a deep convolutional neural network. This is integrated with an in-plane image derotation scheme, DeROT, to tackle the problem of per-frame fingertip detection in depth images. The method reduces the complexity of learning in the space of articulated poses which is demonstrated by using two distinct state-of-the-art learning based hand pose estimation methods applied to fingertip detection. Significant classification improvements are shown over the baseline implementation. Our framework involves no tracking, kinematic constraints or explicit prior model of the articulated object in hand. To support our approach we also describe a new pipeline for high accuracy magnetic annotation and labeling of objects imaged by a depth camera.