Spatial temporal graph convolutional networks for skeleton-based dynamic hand gesture recognition

The main core purpose of artificial emotional intelligence is to recognize human emotions. Technologies such as facial, semantic, or brainwave recognition applications have been widely proposed. However, the abovementioned recognition techniques for emotional features require a large number of training samples to obtain high accuracy. Human behaviour pattern can be trained and recognized by the continuous movement of the Spatial Temporal Graph Convolution Network (ST-GCN). However, this technology does not distinguish between the speed of delicate emotions, and the speed of human behaviour and delicate changes of emotions cannot be effectively distinguished. This research paper proposes Spatial Temporal Variation Convolutional Network training for human emotion recognition, using skeleton detection technology to calculate the degree of skeleton point change between consecutive actions and using the nearest neighbour algorithm to classify speed levels and train the ST-GCN recognition model to obtain the emotional state. Application of the speed change recognition ability of the Spatial Temporal Variation Graph Convolution Network (STV-GCN) to artificial emotional intelligence calculation makes it possible to efficiently recognize the delicate actions of happy, sad, fear, and angry in human behaviour. The STV-GCN technology proposed in this paper is compared with ST-GCN and can effectively improve the recognition accuracy by more than 50%.

MuViH: Multi-View Hand gesture dataset and recognition pipeline for human–robot interaction in a collaborative robotic finishing platform

In autonomous driving scenarios, pedestrian trajectory prediction is an important research direction. Based on the spatio-temporal graph convolutional neural network, we propose a new pedestrian trajectory prediction algorithm. The new algorithm constructs a series of new models around pedestrian intention estimation. The construction of the estimation algorithm considers the following aspects: the contextual information of pedestrians and the surrounding environment, the “pedestrian ego-vehicle” interaction combined with the vehicle speed estimation, the pedestrian’s own skeletal structure information and body language estimation, which includes head joints and the relative structural relationship of the torso joints, including whether it is out of the same plane, is rotated, and so on. Skeleton information feature extraction and construction adopts the method of graph convolutional neural network to structure pedestrians into joints in the form of graphs in non-Euclidean space, and further adopts spatial temporal graph convolutional network for feature extraction and learning. The new method is named a “head-torso”-based spatial temporal graph convolutional network (HT-STGCN). On the dataset PID, the novel method achieves substantial improvements over mainstream methods. Experimental results show that combining HT-STGCN with observed action can improve trajectory prediction.

Human hand recognition plays an important role in a wide range of applications ranging from sign language translators, gesture recognition, augmented reality, surveillance and medical image processing to various Human Computer Interaction (HCI) domains. Human hand is a complex articulated object consisting of many connected parts and joints. Therefore, for applications that involve HCI one can find many challenges to establish a system with high detection and recognition accuracy for hand posture and/or gesture. Hand posture is defined as a static hand configuration without any movement involved. Meanwhile, hand gesture is a sequence of hand postures connected by continuous motions. During the past decades, many approaches have been presented for hand posture and/or gesture recognition. In this paper, we provide a survey on approaches which are based on Hidden Markov Models (HMM) for hand posture and gesture recognition for HCI applications.

Hand gesture recognition is an important area of research in the field of Human Computer Interaction (HCI). The geometric attributes of the hand play an important role in hand shape reconstruction and gesture recognition. That said, fingertips are one of the important attributes for the detection of hand gestures and can provide valuable information from hand images. Many methods are available in scientific literature for fingertips detection with an open hand but very poor results are available for fingertips detection when the hand is closed. This paper presents a new method for the detection of fingertips in a closed hand using the corner detection method and an advanced edge detection algorithm. It is important to note that the skin color segmentation methodology did not work for fingertips detection in a closed hand. Thus the proposed method applied Gabor filter techniques for the detection of edges and then applied the corner detection algorithm for the detection of fingertips through the edges. To check the accuracy of the method, this method was tested on a vast number of images taken with a webcam. The method resulted in a higher accuracy rate of detections from the images. The method was further implemented on video for testing its validity on real time image capturing. These closed hand fingertips detection would help in controlling an electro-mechanical robotic hand via hand gesture in a natural way.

Hand gesture for communication has proven effective for humans, and active research is ongoing in replicating the same success in computer vision systems. Human–computer interaction can be significantly improved from advances in systems that are capable of recognizing different hand gestures. In contrast to many earlier works, which consider the recognition of significantly differentiable hand gestures, and therefore often selecting a few gestures from the American Sign Language (ASL) for recognition, we propose applying deep learning to the problem of hand gesture recognition for the whole 24 hand gestures obtained from the Thomas Moeslund’s gesture recognition database. We show that more biologically inspired and deep neural networks such as convolutional neural network and stacked denoising autoencoder are capable of learning the complex hand gesture classification task with lower error rates. The considered networks are trained and tested on data obtained from the above-mentioned public database; results comparison is then made against earlier works in which only small subsets of the ASL hand gestures are considered for recognition.

The use of hand gestures provides a natural alternative to cumbersome interface devices for Human-Computer Interaction (HCI) systems. However, real-time recognition of dynamic micro hand gestures from video streams is challenging for in-vehicle scenarios since (i) the gestures should be performed naturally without distracting the driver, (ii) micro hand gestures occur within very short time intervals at spatially constrained areas, (iii) the performed gesture should be recognized only once, and (iv) the entire architecture should be designed lightweight as it will be deployed to an embedded system. In this work, we propose an HCI system for dynamic recognition of driver micro hand gestures, which can have a crucial impact in automotive sector especially for safety related issues. For this purpose, we initially collected a dataset named Driver Micro Hand Gestures (DriverMHG), which consists of RGB, depth and infrared modalities. The challenges for dynamic recognition of micro hand gestures have been addressed by proposing a lightweight convolutional neural network (CNN) based architecture which operates online efficiently with a sliding window approach. For the CNN model, several 3-dimensional resource efficient networks are applied and their performances are analyzed. Online recognition of gestures has been performed with 3D-MobileNetV2, which provided the best offline accuracy among the applied networks with similar computational complexities. The final architecture is deployed on a driver simulator operating in real-time. We make DriverMHG dataset and our source code publicly available 1.1https://www.mmk.ei.tum.de/DriverMHG/

Dynamics of human body skeletons convey significant information for human action recognition. Conventional approaches for modeling skeletons usually rely on hand-crafted parts or traversal rules, thus resulting in limited expressive power and difficulties of generalization. In this work, we propose a novel model of dynamic skeletons called Spatial-Temporal Graph Convolutional Networks (ST-GCN), which moves beyond the limitations of previous methods by automatically learning both the spatial and temporal patterns from data. This formulation not only leads to greater expressive power but also stronger generalization capability. On two large datasets, Kinetics and NTU-RGBD, it achieves substantial improvements over mainstream methods.

Considerable effort has been put toward the development of intelligent and natural interfaces between users and computer systems. In line with this endeavor, several modes of information (e.g., visual, audio, and pen) that are used either individually or in combination have been proposed. The use of gestures to convey information is an important part of human communication. Hand gesture recognition is widely used in many applications, such as in computer games, machinery control (e.g., crane), and thorough mouse replacement. Computer recognition of hand gestures may provide a natural computer interface that allows people to point at or to rotate a computer-aided design model by rotating their hands. Hand gestures can be classified into two categories: static and dynamic. The use of hand gestures as a natural interface serves as a motivating force for research on gesture taxonomy, its representations, and recognition techniques. This paper summarizes the surveys carried out in human--computer interaction (HCI) studies and focuses on different application domains that use hand gestures for efficient interaction. This exploratory survey aims to provide a progress report on static and dynamic hand gesture recognition (i.e., gesture taxonomies, representations, and recognition techniques) in HCI and to identify future directions on this topic.

Stationary hand gesture recognition can be applied in a variety of domains such as human-computer interaction (HCI), remote control, virtual reality etc. Hand gesture recognition is mainly the study of detection and recognition of various hand gestures like Sign Language hand gestures, by a computer. This work is focused on three main issues in developing a gesture recognition system. These are (i) Threshold (ii) illumination normalization (iii) user independent gesture recognition based on fusion of Moments. It is very demanding to segment hand regions from the static hand gesture color images, due to unreliable light conditions and composite background. Since skin pixels can vary with different explanation condition, to find the range of skin pixels, becomes a hard task in case of color space based skin color segmentation. These methods propose a learning algorithm based on customized clustering expanse to remove person skin color regions from the stationary hand gesture color descriptions. To improve the performance of classification, two feature synthesis strategies have been proposed in this work.

Recently hand gesture recognition via millimeter-wave radar has attracted a lot of research attention for human-computer interaction. Encouraged by the ability of deep learning models in successfully tackling hand gesture recognition tasks, we propose a deep neural network (DNN) model namely, Res3DTENet that aims to classify dynamic hand gestures using the radio frequency (RF) signals. We propose a scheme that improves the convolutional process of 3DCNNs with residual skip connection (Res3D) to emphasize local-global information and enriches the intra-frame spatio-temporal feature representation. A multi-head attention transformer encoder (TE) network has been trained over the spatio-temporal features to refine the inter-frame temporal dependencies of range-Doppler sequences. The experiments are carried out on the publicly available Soli hand gesture data set. Based on our extensive experiments, we show that the proposed network achieves improved gesture recognition accuracy than the state-of-the-art hand gesture recognition methods.

In recent years, the increasing labor burden in Japanese agriculture hs become a serious issue, driving the development of robots to assist in transporting harvested crops. This study proposes a method that recognizes the action transitions of agricultural workers and enables smooth transport assistance by utilizing three-dimensional skeletal information obtained from RGB-D images. Specifically, we employ Spatial Temporal Graph Convolutional Networks (ST-GCN) to detect the transition from "harvesting" to "loading." The recognition results are used to control the robot so that it approaches the worker before the loading action begins. The proposed method introduces a new labeling scheme tailored to harvesting and crop-loading motions, thereby improving recognition performance with ST-GCN. Evaluation experiments verified its generalization capability to different harvesting postures and workers, demonstrating an 18.7% improvement in action transition recognition accuracy compared with conventional methods. Furthermore, in robot-following experiments with the proposed method implemented, we confirmed that the system could both recognize action transitions and adjust the target following distance before the worker started loading. These results show that an ST-GCN specialized for agricultural tasks can effectively recognize harvesting action transitions, contributing to reducing the burden on workers during crop transportation.

The interaction between human and machine can be achieved by implementing human gesture applications which are known as human computer interaction (HCI). It has been developed several years ago, and now we can easily find it in many applications in real world e.g. in virtual reality, games, robotics, sign language recognition, etc. Gesture recognition has the potential to offer a natural way of communication between humans and machines. The most popular methods in human gesture application are hand gesture recognition. Several of hand gesture recognition methods still have the same problem when trying to recognize hand gesture accurately because of the existence of the uncontrolled environment problem, especially complex background. This study offered a method that can handle complex background in hand gesture recognition by analyzing pattern in spatio temporal domain. The system could reduce irregular noise in complex background significantly that affected to recognize the hand gesture. The experiment had been conducted using 180 videos with a total of 15 gestures. The result showed that the proposed method could recognize 15 hand gestures with accuracy of 98.33%.

Interacting with mobile devices can be challenging in adverse working environments. Using hand gestures for interaction can overcome severe usability issues that users face when working with mobile devices in industrial settings. This chapter is dedicated to the design, implementation, and evaluation of mobile information systems with hand gesture recognition as means for human computer interaction. The chapter provides a concise theoretical background on human gestural interaction and gesture recognition, guidelines for the design of gesture vocabularies, recommendations for proper implementation, and parameterization of robust and reliable recognition algorithms on energy-efficient 8-bit architectures. It additionally presents an elaborated process for participatory design and evaluation of gesture vocabularies to ensure high usability in the actual context of use. The chapter concludes with a case study that proves the suitability of the proposed framework for the design of efficient and reliable hand gesture-based user interfaces.

In this paper, we address the problem of cross-view action recognition from a monocular RGB camera. This topic has been considered extremely challenging due to the lack of 3D information in 2D images. Exploiting the advances in 3D pose estimation from a single RGB camera, we propose a new framework termed DeepVI, for cross-view action recognition without the need for pose alignment. Virtual viewpoints are used to augment the variability of training data along with the use of an end-to-end Deep Neural Network (DNN). The proposed network is composed of two modules. The first one, called SmoothNet, implicitly smooths skeleton joint trajectories using revisited temporal convolution in order to reduce the noise in the estimated 3D skeletons. The second module consists of a state-of-the-art approach designed for action recognition based on Spatial Temporal Graph Convolutional Networks (ST-GCN [40]). Experiments have been conducted in cross-view settings on two datasets, namely, NTU RGB-D and Northwestern-UCLA. The obtained results show the effectiveness of the proposed framework.