A PointNet-Based Solution for 3D Hand Gesture Recognition

Gesture recognition is an intensively researched area for several reasons. One of the most important reasons is because of this technology's numerous application in various domains (e.g., robotics, games, medicine, automotive, etc.) Additionally, the introduction of three-dimensional (3D) image acquisition techniques (e.g., stereovision, projected-light, time-of-flight, etc.) overcomes the limitations of traditional two-dimensional (2D) approaches. Combined with the larger availability of 3D sensors (e.g., Microsoft Kinect, Intel RealSense, photonic mixer device (PMD), CamCube, etc.), recent interest in this domain has sparked. Moreover, in many computer vision tasks, the traditional statistic top approaches were outperformed by deep neural network-based solutions. In view of these considerations, we proposed a deep neural network solution by employing PointNet architecture for the problem of hand gesture recognition using depth data produced by a time of flight (ToF) sensor. We created a custom hand gesture dataset, then proposed a multistage hand segmentation by designing filtering, clustering, and finding the hand in the volume of interest and hand-forearm segmentation. For comparison purpose, two equivalent datasets were tested: a 3D point cloud dataset and a 2D image dataset, both obtained from the same stream. Besides the advantages of the 3D technology, the accuracy of the 3D method using PointNet is proven to outperform the 2D method in all circumstances, even the 2D method that employs a deep neural network.