Human Activity Recognition in Real-Times Environments using Skeleton Joints

Kumar, Ajay; Kumar, Anil; Singh, Satish Kumar; Kala, Rahul

doi:10.9781/ijimai.2016.379

Cited by 7 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are many works on gesture recognition for different purposes, some focusing on the whole body [6] while others focusing on a specific part as eyes [7] or hands [8]. Despite of the vast number of research works that have been published, there have been several limitations.…”

Section: Introductionmentioning

confidence: 99%

Gesture Recognition of RGB and RGB-D Static Images Using Convolutional Neural Networks

Khari¹,

Garg²,

Crespo³

et al. 2019

IJIMAI

View full text Add to dashboard Cite

In this era, the interaction between Human and Computers has always been a fascinating field. With the rapid development in the field of Computer Vision, gesture based recognition systems have always been an interesting and diverse topic. Though recognizing human gestures in the form of sign language is a very complex and challenging task. Recently various traditional methods were used for performing sign language recognition but achieving high accuracy is still a challenging task. This paper proposes a RGB and RGB-D static gesture recognition method by using a fine-tuned VGG19 model. The fine-tuned VGG19 model uses a feature concatenate layer of RGB and RGB-D images for increasing the accuracy of the neural network. Finally, on an American Sign Language (ASL) Recognition dataset, the authors implemented the proposed model. The authors achieved 94.8% recognition rate and compared the model with other CNN and traditional algorithms on the same dataset.

show abstract

Section: Introductionmentioning

confidence: 99%

Gesture Recognition of RGB and RGB-D Static Images Using Convolutional Neural Networks

Khari¹,

Garg²,

Crespo³

et al. 2019

IJIMAI

View full text Add to dashboard Cite

show abstract

“…Some works consider using data from sensors of smartphones and other devices [2,3], as well as from wearable sensors [4,5,6]. There are also methods for human activity recognition by image or video [7,8]. One of these methods is to recognize the image in which there is a person performing a certain activity.…”

Section: Methods Of Human Activity Recognitionmentioning

confidence: 99%

Multi-Label Human Activity Recognition on Image Using Deep Learning

Nikolaev¹

2019

Proceedings of the 7th Scientific Conference on Information Technologies for Intelligent Decision Making Support (ITIDS 2019)

View full text Add to dashboard Cite

This paper describes the model of convolutional neural network which is designed for multi-label human activity recognition. The possibilities of using activity recognition systems in the daily life of a person are considered. As part of this work, the study is conducted for the method of recognizing human activity on an image that can be obtained from a surveillance camera. To obtain more accurate recognition results, the network model used technology of transfer learning. Several pre-trained convolutional networks are considered using two types of transfer learning in order to find the best solution. The deep learning networks for solving the problem are implemented in Python using deep learning libraries. Considered models are trained to recognize binary multi-label human activity. Training and testing are performed on images collected by the author. The article also provides the obtained training and testing results of different models of convolutional neural networks. The data obtained are tabulated and also presented in graphical form.

show abstract

“…In[16], the authors proposed a human action recognition algorithm exploiting the skeleton provided by Microsoft Kinect and discussed its application to AAL…”

mentioning

confidence: 99%

First Person Vision for Activity Prediction Using Probabilistic Modeling

Noor

Uddin

2018

Mehran Univ. res. j. eng. technol.

View full text Add to dashboard Cite

Identifying activities of daily living is an important area of research with applications in smart-homes and healthcare for elderly people. It is challenging due to reasons like human self-occlusion, complex natural environment and the human behavior when performing a complicated task. From psychological studies, we know that human gaze is closely linked with the thought process and we tend to “look” at the objects before acting on them. Hence, we have used the object information present in gaze images as the context and formed the basis for activity prediction. Our system is based on HMM (Hidden Markov Models) and trained using ANN (Artificial Neural Network). We begin with extracting motion information from TPV (Third Person Vision) streams and object information from FPV (First Person Vision) cameras. The advantage of having FPV is that the object information forms the context of the scene. When context is included as input to the HMM for activity recognition, the precision increases. For testing, we used two standard datasets from TUM (Technische Universitaet Muenchen) and GTEA Gaze+ (Georgia Tech Egocentric Activities). In the first round, we trained our ANNs only with activity information and in the second round added the object information as well. We saw a significant increase in the precision (and accuracy) of predicted activities from 55.21% (respectively 85.25%) to 77.61% (respectively 93.5%). This confirmed our initial hypothesis that including the focus of attention of the actor in the form of object seen in FPV can help in predicting activities better.

show abstract

Human Activity Recognition in Real-Times Environments using Skeleton Joints

Cited by 7 publications

References 22 publications

Gesture Recognition of RGB and RGB-D Static Images Using Convolutional Neural Networks

Gesture Recognition of RGB and RGB-D Static Images Using Convolutional Neural Networks

Multi-Label Human Activity Recognition on Image Using Deep Learning

First Person Vision for Activity Prediction Using Probabilistic Modeling

Contact Info

Product

Resources

About