Fusing and refining convolutional neural network models for assembly action recognition in smart manufacturing

Human activity recognition is a very active research on pervasive computing and mobile health application. Many human activity systems based on inertial measurement unit (IMU) sensor data were proposed in the past few years. These systems mainly use IMU sensor placed on he torso and limbs to collect data and utilize supervised machine learning algorithms on sensor data. One main issue of these systems is that wearing multiple on-body IMU sensors may bring inconvenience to users' daily life. The other issue of these exiting methods is that an activity recognition model that is trained on a specific subject does not work well when being applied to predict another subject's activities since IMU activity data always carry information that is specific to the human subject who conducts the activities. In our work, inspired by the principle of domain adaption, we proposed a new deep-learning activity recognition model based on an adversarial network which can remove the subject-specific information within the IMU activity data and extract subject-independent features shared by the data collected on different subjects. We also for the first time use data collected from insole based IMU sensors on 8 participants for 5 common activities to build a new real world human activity dataset which can minimize the inconvenience for users to wear. We conducted experiments with our new real-world dataset. Results show that our subject independent activity recognition model outperforms state-of-art supervised learning techniques and eliminates the effects of individual differences between subjects successfully. The average recognition accuracy under the leave-one-out (L1O) condition achieves 99.0% which is higher than the performance of traditional human activity recognition system based on CNNs.

Clinicians lack objective means for monitoring if their knee osteoarthritis patients are improving outside of the clinic (e.g., at home). Previous human activity recognition (HAR) models using wearable sensor data have only used data from healthy people and such models are typically imprecise for people who have medical conditions affecting movement. HAR models designed for people with knee osteoarthritis have classified rehabilitation exercises but not the clinically relevant activities of transitioning from a chair, negotiating stairs and walking, which are commonly monitored for improvement during therapy for this condition. Therefore, it is unknown if a HAR model trained on data from people who have knee osteoarthritis can be accurate in classifying these three clinically relevant activities. Therefore, we collected inertial measurement unit (IMU) data from 18 participants with knee osteoarthritis and trained convolutional neural network models to identify chair, stairs and walking activities, and phases. The model accuracy was 85% at the first level of classification (activity), 89–97% at the second (direction of movement) and 60–67% at the third level (phase). This study is the first proof-of-concept that an accurate HAR system can be developed using IMU data from people with knee osteoarthritis to classify activities and phases of activities.

There are several large datasets available that are captured from motion tracking systems which could be useful to train wearable human activity recognition (HAR) systems, if only their spatial data could be mapped into the equivalent inertial measurement unit (IMU) data that would be sensed on the body. In this paper, we describe a mapping from 3D Vicon motion tracking data to data collected from a BlueSense on-body IMU. We characterise the error incurred in order to discern the extent to which it is possible to generate useful training data for a wearable activity recognition system from data collected with a motion capture system. We analyse this by mapping Vicon motion tracking data to rotational velocity and linear acceleration at the head, and compare this to actual gyroscope and accelerometer data collected by an IMU mounted on the head. In a 15 min dataset comprising three static activities—sitting, standing and lying down—we find that 95% of the reconstructed gyroscope data is within an error of [−7.25;+7.46] \(deg \cdot s^{-1}\), while 95% of the reconstructed accelerometer data was contained within [−96.1;+72.9] \(m \cdot G\). However, when we introduce more movement by including data collected while walking this increases to [−19.0;+18.2] \(deg \cdot s^{-1}\) for the gyroscope and [−208;+186] \(m \cdot G\) for the accelerometer. We conclude that generating accurate IMU data from motion capture datasets is possible and could be useful in providing larger volumes of data for activity recognition tasks and in helping enable advanced, data-hungry techniques such as deep learning to be employed on a larger scale within the domain of human activity recognition.

Human Activity Recognition (HAR) is pivotal in ubiquitous computing, offering benefits to human-centric services such as health monitoring, smart homes, and eldercare systems. HAR leverages smartphones, smartwatches, and other wearable devices to collect sensory data annotated with activity labels, which are then used to train machine learning or deep learning models for automatic activity recognition. Effective HAR systems must integrate information from multiple modalities to accurately assist users. This paper introduces the XAttentionHAR model, an innovative cross-modality attention-based ensemble model for HAR. Our approach utilizes a self-attention module to extract features within each modality and an inter-domain cross-attention module to capture and integrate long-term dependencies across domains. The cross-modality attention mechanism enhances the fusion of diverse modalities, enriching the semantic information. We conducted extensive experiments on the WISDM public dataset, which includes accelerometer and gyroscope data from smartwatches and smartphones. Our results demonstrate that XAttentionHAR outperforms other state-of-the-art methods in activity recognition, achieving 98.48% accuracy for smartphone-based HAR and 98.73% accuracy for smartwatch-based HAR, paving the way for improved human-centric services.

Visual attention mechanism has been widely used in computer vision and plays a vital role in the research of human action recognition. In this paper, we explore a novel moving target detection mechanism for human action recognition and propose a new 3D CNN (3D Convolutional Neural Network) model, dubbed LaM-2SRN (Local Features Enhanced and Moving target detected 2Stream-ResNet) for extracting and learning attention-enhanced spatiotemporal features. The contributions of this paper are as follow: First, the traditional CAM (Class Activation Map) based visual attention algorithm is used to obtain the optical flow information of the human region, thus eliminating the influence of irrelevant optical flow information (such as background clutter). Second, the ViBe algorithm is used to identify the moving target in the continuous frame, retain the optical flow information of the moving target, and make it complement with the optical flow information of the human region, to obtain a complete motion descriptor. After the motion information is marked in the video frame, we put the marked video frames and the original video frames into the 3D CNN and 2D CNN models respectively, to acquired mixed descriptor, which serves as the basis for video classification. Different from most of the previous target detection algorithms, this paper not only detects the human target, but also detects the moving foreground targets in the video, so that the pre-trained CNN model can obtain more complete motion information from videos. We use RGB-only video data for evaluation on two benchmarks: UCF101 and HMDB51, the experimental results demonstrate that our LaM-2SRN is comparable to the previous state-of-the-art algorithms.

With the rapid development of the computer and sensor field, inertial sensor data have been widely used in human activity recognition. At present, most relevant studies divide human activities into basic actions and transitional actions, in which basic actions are classified by unified features, while transitional actions usually use context information to determine the category. For the existing single method that cannot well realize human activity recognition, this paper proposes a human activity classification and recognition model based on smartphone inertial sensor data. The model fully considers the feature differences of different properties of actions, uses a fixed sliding window to segment the human activity data of inertial sensors with different attributes and, finally, extracts the features and recognizes them on different classifiers. The experimental results show that dynamic and transitional actions could obtain the best recognition performance on support vector machines, while static actions could obtain better classification effects on ensemble classifiers; as for feature selection, the frequency-domain feature used in dynamic action had a high recognition rate, up to 99.35%. When time-domain features were used for static and transitional actions, higher recognition rates were obtained, 98.40% and 91.98%, respectively.

In order to realize high-accuracy recognition of aerobics actions, a highly applicable deep learning model and faster data processing methods are required. Therefore, it is a major difficulty in the field of research on aerobics action recognition. Based on this, this paper studies the application of the convolution neural network (CNN) model combined with the pyramid algorithm in aerobics action recognition. Firstly, the basic architecture of the convolution neural network model based on the pyramid algorithm is proposed. Combined with the application strategy of the common recognition model in aerobics action recognition, the traditional aerobics action capture information is processed. Through the characteristics of different aerobics actions, different accurate recognition is realized, and then, the error of the recognition model is evaluated. Secondly, the composite recognition function of the convolution neural network model in this application is constructed, and the common data layer effect recognition method is used in the optimization recognition. Aiming at the shortcomings of the composite recognition function, the pyramid algorithm is used to improve the convolution neural network recognition model by deep learning optimization. Finally, through the effectiveness comparison experiment, the results show that the convolution neural network model based on the pyramid algorithm is more efficient than the conventional recognition method in aerobics action recognition.

Recently, a significant amount of literature concerning machine learning techniques has focused on automatic recognition of activities performed by people. The main reason for this considerable interest is the increasing availability of devices able to acquire signals which, if properly processed, can provide information about human activities of daily living (ADL). The recognition of human activities is generally performed by machine learning techniques that process signals from wearable sensors and/or cameras appropriately arranged in the environment. Whatever the type of sensor, activities performed by human beings have a strong subjective characteristic that is related to different factors, such as age, gender, weight, height, physical abilities, and lifestyle. Personalization models have been studied to take into account these subjective factors and it has been demonstrated that using these models, the accuracy of machine learning algorithms can be improved. In this work we focus on the recognition of human activities using signals acquired by the accelerometer embedded in a smartphone. The contributions of this research are mainly three. A first contribution is the definition of a clear validation model that takes into account the problem of personalization and which thus makes it possible to objectively evaluate the performances of machine learning algorithms. A second contribution is the evaluation, on three different public datasets, of a personalization model which considers two aspects: the similarity between people related to physical aspects (age, weight, and height) and similarity related to intrinsic characteristics of the signals produced by these people when performing activities. A third and last contribution is the development of a personalization model that considers both the physical and signal similarities. The experiments show that the employment of personalization models improves, on average, the accuracy, thus confirming the soundness of the approach and paving the way for future investigations on this topic.

Human action recognition is a fundamental research problem in computer vision. The accuracy of human action recognition has important applications. In this book chapter, the authors use a YOLOv7-based model for human action recognition. To evaluate the performance of the model, the action recognition results of YOLOv7 were compared with those using CNN+LSTM, YOLOv5, and YOLOv4. Furthermore, a small human action dataset suitable for YOLO model training is designed. This data set is composed of images extracted from KTH, Weizmann, MSR data sets. In this book chapter, the authors make use of this data set to verify the experimental results. The final experimental results show that using the YOLOv7 model for human action recognition is very convenient and effective, compared with the previous YOLO model.

Human activity recognition (AR) has begun to mature as a field, but for AR research to thrive, large, diverse, high quality, AR data sets must be publically available and AR methodology must be clearly documented and standardized. In the process of comparing our AR research to other efforts, however, we found that most AR data sets are sufficiently limited as to impact the reliability of existing research results, and that many AR research papers do not clearly document their experimental methodology and often make unrealistic assumptions. In this paper we outline problems and limitations with AR data sets and describe the methodology problems we noticed, in the hope that this will lead to the creation of improved and better documented data sets and improved AR experimental methodology. Although we cover a broad array of methodological issues, our primary focus is on an often overlooked factor, model type, which determines how AR training and test data are partitioned---and how AR models are evaluated. Our prior research indicates that personal, hybrid, and impersonal/universal models yield dramatically different performance [30], yet many research studies do not highlight or even identify this factor. We make concrete recommendations to address these issues and also describe our own publically available AR data sets.

Human action recognition is a research hotspot in the field of ambient intelligence, serving as a foundation for the Internet of Healthcare Things (IoHT) and smart home wellness, with extensive application value. Currently, most research primarily focuses on the performance of single-modal approach for human action recognition. However, single-modal data cannot adequately capture the action characteristics of the human body. For instance, camera data lacks detailed micro-motion information, while radar data lacks visual appearance information. This limitation makes human action recognition systems susceptible to complex covariate influences. To address this issue, this paper proposes a Multi-Modal Fusion Model, M2FM, to accurately recognize various complex human action from millimeter-wave radar signals and video data. In the millimeter-wave radar branch, a LFNet network is constructed to capture richly hierarchical human action representation by extracting micro-Doppler feature and cadence velocity feature simultaneously. Specially, a Linear Feedforward Neural Network (LFNN) module is designed for modeling global-local feature of human action. In the video branch, a lightweight Transformer-based video analysis and action recognition network, STL-Former, is developed. Specially, an Agent downSampling (AS) attention module and a Linear Maxpooling (LM) attention module are designed to achieve context-aware downsampling with global receptive field and spatial vector sequence downsampling, respectively. Additionally, a multi-scale Linear attention (Litner) module is designed for modeling the spatio-temporal information of human action. Finally, the outputs from two branches are fused by a filter-based Dempster-Shafer theory. The experimental results on a self-collected Multi-modal Human Action Dataset, JH-MHAD, show that the M2FM model outperforms other advanced models, with an average recognition accuracy of 99.3% for eight different human actions, and it demonstrates strong adaptability under different conditions.

The recognition of sports action is an important research subject, which is conducive to the improvement of athletes’ own level. To improve the accuracy of multi-modal data action recognition, based on the Transformer module, this study introduces a multi-head attention mechanism, fuses multi-modal data, and constructs a multi-stream structured object relationship inference network. Based on PointNet++ network and combining five different data fusion frameworks, a motion recognition model that integrates RGB data and 3D skeleton point cloud is constructed. The results showed that the Top-1 accuracy of multi-stream structured object relationship inference network was 42.5% and 42.7%, respectively, which was better than other algorithms. The accuracy of the multi-modal fusion model was improved by 15.6% and 5.1% compared with the single mode, and by 5.4% and 2.6% compared with the dual mode, which showed its superiority in the action recognition task. This showed that the fusion of multi-modal data can provide more abundant information, so as to improve the accuracy of action recognition. The accuracy of the action recognition model combining RGB data and 3D skeleton point cloud was 84.3%, 87.5%, 90.2%, 90.6% and 91.2% after the combination of different strategies, which effectively compensated for the problem of missing information in 3D skeleton point cloud and significantly improved the accuracy of action recognition. With a small amount of data, the Top-1 accuracy of the multi-stream structured object relationship inference network in this study was superior to other algorithms, showing its advantages in dealing with complex action recognition tasks. In addition, the action recognition model that fuses RGB data and 3D skeleton point cloud also achieved higher accuracy, which is better than other algorithms. This study can meet the needs of motion recognition in different scenarios and has certain reference value.

An automatic human action representation and recognition technique is proposed in this paper. Appearance-change problem due to human wearing dresses and body shapes is also investigated in this study for automatic human action recognition. A tuned eigenspace technique is proposed for automatic human posture and/or motion recognition that successfully overcome the preceding problems. We employ image pre-processing by Gaussian and Sobel edge filter, called the first stage tuning, for reducing a dress effect, and a mean eigenspace produced by taking a mean of the similar postures, called the second stage tuning, for avoiding the preceding problems. An eigenspace called a tuned eigenspace is obtained from the mentioned processes and it is used for further recognition of unfamiliar postures and actions. The proposed method is compared with a related technique and the robustness of this approach is presented.

Understanding semantic meaning of human actions captured in unconstrained environments has broad applications in fields ranging from patient monitoring, human-computer interaction, to surveillance systems. However, while great progresses have been achieved on automatic human action detection and recognition in videos that are captured in controlled/constrained environments, most existing approaches perform unsatisfactorily on videos with uncontrolled/unconstrained conditions (e.g., significant camera motion, background clutter, scaling, and light conditions). To address this issue, the authors propose a robust human action detection and recognition framework that works effectively on videos taken in controlled or uncontrolled environments. Specifically, the authors integrate the optical flow field and Harris3D corner detector to generate a new spatial-temporal information representation for each video sequence, from which the general Gaussian mixture model (GMM) is learned. All the mean vectors of the Gaussian components in the generated GMM model are concatenated to create the GMM supervector for video action recognition. They build a boosting classifier based on a set of sparse representation classifiers and hamming distance classifiers to improve the accuracy of action recognition. The experimental results on two broadly used public data sets, KTH and UCF YouTube Action, show that the proposed framework outperforms the other state-of-the-art approaches on both action detection and recognition.

Scene image and human skeleton-based dual-stream human action recognition