Serial-parallel Multi-Scale Feature Fusion for Anatomy-Oriented Hand Joint Detection
This work addresses accurate hand joint detection for applications in computer vision and human-computer interaction, representing an incremental improvement.
The paper tackles hand joint detection from single unmarked images by proposing a two-stage network with serial-parallel multi-scale feature fusion, achieving state-of-the-art results on five datasets.
Accurate hand joints detection from images is a fundamental topic which is essential for many applications in computer vision and human computer interaction. This paper presents a two stage network for hand joints detection from single unmarked image by using serial-parallel multi-scale feature fusion. In stage I, the hand regions are located by a pre-trained network, and the features of each detected hand region are extracted by a shallow spatial hand features representation module. The extracted hand features are then fed into stage II, which consists of serially connected feature extraction modules with similar structures, called "multi-scale feature fusion" (MSFF). A MSFF contains parallel multi-scale feature extraction branches, which generate initial hand joint heatmaps. The initial heatmaps are then mutually reinforced by the anatomic relationship between hand joints. The experimental results on five hand joints datasets show that the proposed network overperforms the state-of-the-art methods.