A light-weight real-time applicable hand gesture recognition system for automotive applications

Abstract

We present a novel approach for improved handgesture recognition by a single time-of-flight(ToF) sensor in an automotive environment. As the sensor's lateral resolution is comparatively low, we employ a learning approach comprising multiple processing steps, including PCA-based cropping, the computation of robust point cloud descriptors and training of a Multilayer perceptron (MLP) on a large database of samples. A sophisticated temporal fusion technique boosts the overall robustness of recognition by taking into account data coming from previous classification steps. Overall results are very satisfactory when evaluated on a large benchmark set of ten different hand poses, especially when it comes to generalization on previously unknown persons.

A Dynamic Gesture Recognition Interface for Smart Home Control based on Croatian Sign Language

“…The use of specialized hardware for hand gesture acquisition primarily bridges certain steps in the process that would otherwise have to be taken into account, such as hand segmentation, hand detection, and hand orientation, finger isolation, etc. Traditional approaches in the problem of gesture classification were based on hidden Markov models (HMMs) [24], support vector machines (SVMs) [25], conditional random fields (CRFs) [26], and multi-layer perceptron (MLP) [27]. In recent years, research interests have been shifted from a sensor-based approach to a vision-based approach, thanks to rapid advancement in the field of deep learning-based computer vision.…”

Hand Gesture Recognition in Automotive Human–Machine Interaction Using Depth Cameras

“…Ref. [36] contributed a preprocessing method using principal component analysis (PCA) to effectively crop the data, such that it only contains the palm and the fingers. In contrast to other possible cropping procedures, as recurrent neural networks or similar models, the strength of PCA lies in the fact that this unsupervised machine learning methods needs no training and operates fast, using only lower order statistics.…”

“…Ref. [36] demonstrated an in-car dynamic hand gesture recognition system relying on a PCA-based preprocessing procedure. In these experiments, we considered dynamic hand gestures as listed in Table 8, each defined by a starting and an ending hand posture sstart and send as illustrated in Figure 14.…”

Control and Guidance of Low-Cost Robots via Gesture Perception for Monitoring Activities in the Home

“…Thus, considerable progress has been made in this area and a number of algorithms addressing different aspects of the problem have been previously proposed. Techniques and methods to improve the pre-processing algorithms and to reduce the quantization error caused by low resolution of Kinect [ 15 ] for hand recognition include methods based on local shape detection using superpixel and colour segmentation techniques [ 16 ], approaches for hand gesture recognition using learning techniques such as PCA and multilayer perceptron on a large database of samples [ 17 ] and so forth. This paper proposes a system based on state machine that extracts accurate 3D hand gestures using a three-dimensional descriptor.…”

“…Our system uses the skeleton information from Kinect to produce markless hand extraction similar to [ 16 ] however, unlike that work in that we use a global descriptor instead of local shape of superpixels to retain the overall shapes of gestures to be recognized. Also, our training phase does not require as much data and time as in [ 17 ]. Current methods are generally based on appearance or models and they are dependent on the image features, invariance properties and number of gestures to be recognized [ 12 , 18 ].…”