Novel side pose classification model of stretching gestures using three-layer LSTM

Solongontuya, Boldmaa; Cheoi, Kyung Joo; Kim, Mi-Hye

doi:10.1007/s11227-021-03684-w

Cited by 9 publications

(3 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To further validate the superiority of the methods in this paper over other methods, the comparison methods chosen in this paper are mainly RNN [26], LSTM [27], graph CNN based reference [28], dual-stream CNN based reference [29], and two-dimensional graph convolution-based reference [30]. *e accuracy of action recognition obtained by various methods on two publicly available datasets is shown in Table 3 and Figure 9.…”

Section: Experimental Discussionmentioning

confidence: 99%

A Multimodal Information Fusion Model for Robot Action Recognition with Time Series

Zhang¹,

Li²,

Qian³

2022

Journal of Electrical and Computer Engineering

View full text Add to dashboard Cite

The current robotics field, led by a new generation of information technology, is moving into a new stage of human-machine collaborative operation. Unlike traditional robots that need to use isolation rails to maintain a certain safety distance from people, the new generation of human-machine collaboration systems can work side by side with humans without spatial obstruction, giving full play to the expertise of people and machines through an intelligent assignment of operational tasks and improving work patterns to achieve increased efficiency. The robot’s efficient and accurate recognition of human movements has become a key factor in measuring robot performance. Usually, the data for action recognition is video data, and video data is time-series data. Time series describe the response results of a certain system at different times. Therefore, the study of time series can be used to recognize the structural characteristics of the system and reveal its operation law. As a result, this paper proposes a time series-based action recognition model with multimodal information fusion and applies it to a robot to realize friendly human-robot interaction. Multifeatures can characterize data information comprehensively, and in this study, the spatial flow and motion flow features of the dataset are extracted separately, and each feature is input into a bidirectional long and short-term memory network (BiLSTM). A confidence fusion method was used to obtain the final action recognition results. Experiment results on the publicly available datasets NTU-RGB + D and MSR Action 3D show that the method proposed in this paper can improve action recognition accuracy.

show abstract

Section: Experimental Discussionmentioning

confidence: 99%

A Multimodal Information Fusion Model for Robot Action Recognition with Time Series

Zhang¹,

Li²,

Qian³

2022

Journal of Electrical and Computer Engineering

View full text Add to dashboard Cite

show abstract

“…Researchers now are more interested in using computer vision techniques because they are cheaper than other methods and provide more benefits. Solongontuya et al [ 39 ] proposed a new stretching-side-pose classification system that uses a three-layer long short-term memory (LSTM) network for four rehabilitation treatment exercises: bird dog, cat camel, cobra stretch, and pelvic tilt. It enables patients to rehabilitate themselves at home.…”

Section: Related Workmentioning

confidence: 99%

A New Home-Based Upper- and Lower-Limb Telerehabilitation Platform with Experimental Validation

et al. 2023

View full text Add to dashboard Cite

The world is witnessing interesting challenges in several fields, including medicine. Solutions to many of these challenges are being developed in the field of artificial intelligence. As a result, artificial intelligence techniques can be used in telerehabilitation to facilitate the work of doctors and to find methods that can be used to better treat methods that can be used to better treat patients. Motion rehabilitation is an essential procedure for elderly people and patients undergoing physiotherapy after physical procedures such as surgery for the anterior cruciate ligament (ACL), a frozen shoulder. To regain normal motion, the patient must participate in rehabilitation sessions. Furthermore, telerehabilitation has become a significant trend in research studies because of the COVID-19 pandemic, which is continuing to affect the world through the delta and the omicron variants, and other epidemics. In addition, because of other special issues like the vastness of the desert area in Algeria and the lack of facilities, it is ideal to avoid requiring patients to travel for all of their rehabilitation sessions; patients should be able to perform their rehabilitation exercises at home. Thus, telerehabilitation could lead to promising developments in this field. Therefore, our project’s goal is to develop a website for telerehabilitation that can be used to facilitate rehabilitation from a distance. We also want to track the progress of patients’ range of motion (ROM) in real time using artificial intelligence techniques, by controlling the angles of the motion of a limbs about a joint.

show abstract

“…Several studies suggested to use body pose estimation for driver assistance system [ 42 ] and head pose estimation for distraction detection [ 43 , 44 ]. There are multiple studies of using body pose estimation to classify daily activity actions [ 45 ] and human movements [ 46 ]. However, there is little attention given to use full body pose estimation in classifying distraction actions.…”

Section: Literature Reviewmentioning

confidence: 99%

Optimally-Weighted Image-Pose Approach (OWIPA) for Distracted Driver Detection and Classification

Koay

Chuah

Chow

et al. 2021

Sensors

View full text Add to dashboard Cite

Distracted driving is the prime factor of motor vehicle accidents. Current studies on distraction detection focus on improving distraction detection performance through various techniques, including convolutional neural networks (CNNs) and recurrent neural networks (RNNs). However, the research on detection of distracted drivers through pose estimation is scarce. This work introduces an ensemble of ResNets, which is named Optimally-weighted Image-Pose Approach (OWIPA), to classify the distraction through original and pose estimation images. The pose estimation images are generated from HRNet and ResNet. We use ResNet101 and ResNet50 to classify the original images and the pose estimation images, respectively. An optimum weight is determined through grid search method, and the predictions from both models are weighted through this parameter. The experimental results show that our proposed approach achieves 94.28% accuracy on AUC Distracted Driver Dataset.

show abstract

Novel side pose classification model of stretching gestures using three-layer LSTM

Cited by 9 publications

References 34 publications

A Multimodal Information Fusion Model for Robot Action Recognition with Time Series

A Multimodal Information Fusion Model for Robot Action Recognition with Time Series

A New Home-Based Upper- and Lower-Limb Telerehabilitation Platform with Experimental Validation

Optimally-Weighted Image-Pose Approach (OWIPA) for Distracted Driver Detection and Classification

Contact Info

Product

Resources

About