Gesture Recognition by Using Depth Data: Comparison of Different Methodologies

Abstract

In this chapter, the problem of gesture recognition in the context of human computer interaction is considered. Several classifiers based on different approaches such as neural network (NN), support vector machine (SVM), hidden Markov model (HMM), deep neural network (DNN), and dynamic time warping (DTW) are used to build the gesture models. The performance of each methodology is evaluated considering different users performing the gestures. This performance analysis is required as the users perform gestures in a personalized way and with different velocity. So the problems concerning the different lengths of the gesture in terms of number of frames, the variability in its representation, and the generalization ability of the classifiers have been analyzed.

Human Gesture Recognition in Computer Vision Research

“…China has also made some tremendous growth as far as computer vision-based gesture recognition goes [9], including the advancement of a technique of gesture detection based on perceived changes in picture transformation, and employed a discretization parameter model of visual picture in motion for identification of 120 movements. Also, a solution was presented for solving dynamic gesture identification via self-discovering sparse representation.…”

Towards Intelligent Retail: Automated on-Shelf Availability Estimation Using a Depth Camera

“…While 2D images convey detailed information about the surveyed scene and allow for accurate detection of planogram anomalies or ruptures, results are highly affected by occlusions due to perspective effects. As an alternative, RGB-D sensors, i.e., depth sensing devices that work in association with RGB cameras by augmenting conventional 2D images with distance information in a per pixel basis, have been demonstrated to be successful in different fields, such as indoor and outdoor environment mapping [16], [17] and gesture recognition [18]. An application of RGB-D sensors in the context of intelligent retail can be found in [19], where a top-view RGB-D camera is employed to monitor shoppers' behaviors.…”