Survey on 3D Hand Gesture Recognition

Abstract

3D hand gesture recognition has attracted increasing research interests in computer vision, pattern recognition and human-computer interaction. The emerging depth sensors greatly inspired various hand gesture recognition approaches and applications, which were severely limited in the 2D domain with conventional cameras. This paper presents a survey of some recent works on hand gesture recognition using 3D depth sensors. We first review the commercial depth sensors and public datasets which are widely used in this field. Then, we review the state-of-the-art research for 3D hand gesture recognition in four aspects: 3D hand modeling, static hand gesture recognition, hand trajectory gesture recognition and continuous hand gesture recognition. While the emphasis is on 3D hand gesture recognition approaches, the related applications and typical systems are also briefly summarized for practitioners.

HD: Efficient Hand Detection and Tracking

“…With these techniques combined, our HD system is capable of detecting human hands in a number of different scenarios such as person hand detection and tracking for Parkinson's disease diagnosis or for stroke recovery monitoring. Other potential applications could be 3D hand tracking [52] and gesture control for serious game [53], HRI and rehabilitation interactions [54] as well as individual finger processing for sign-language communication between deaf/non-deaf people [55]. …”

Gestural Interaction for Virtual Reality Environments through Data Gloves

“…From these works, it has been identified the following specified shortcomings [3,4,5,6,7,8,9,10,11,12,13,14,15]:…”

Three-Dimensional Integral Imaging for Gesture Recognition Under Occlusions

“…Even more recent is the trend to incorporate 3D sensory due to its potential to segment (parts of) the human body and disambiguate actions [5], [8], [27].…”

“…Several reasons can explain this fact, such as the difficulty of addressing the problem, the elusiveness of the term and the complexity of formalizing it, and the lack of datasets [4] which include occlusions to promote a systematic study and benchmarking. Often, the occlusion considered is self-occlusion or, in the case of hand gestures, the occlusion due to the hand-manipulated object [8]. Recently, the influence of external occlusion on different known action descriptors has been studied [18].…”