Deeply learning a discriminative spatial–temporal feature for robot action understanding

Human action recognition is essential in many real-world scenarios, such as video surveillance, human–computer interaction, and behavior analysis. Despite the progress in deep learning, issues such as occlusion, distraction from the background, and motion pattern variability still exist, thus restricting the generalization ability of current models. Most methods are based only on spatial or temporal features and cannot efficiently capture both in one framework, causing lower accuracy in realistic situations. In response to these shortcomings, a multilevel feature extraction approach was proposed by integrating spatial and temporal features to improve the action recognition precision. The method captures RGB frames, optical flow, spatial saliency maps, and temporal saliency maps to enable an overall inspection of video streams. Efficient feature extraction was achieved by applying a pre-trained Inception V3 model and then bidirectional gated recurrent units (Bi-GRUs) to include sequential modeling. An attention mechanism was also included to boost the classification process by focusing on key temporal segments. UCF101 and HMDB51 benchmark datasets evaluated the efficiency of the strategy. The model’s accuracy was 98.13% on UCF101 and 81.45% on HMDB51, which validated the superior discrimination ability of the model in processing heterogeneous human actions. These results confirm that the provided framework is an efficient and discriminative action recognition approach, thus suitable for applications requiring extensive motion analysis and real-time deployment.

Understanding human behavior and human action recognition are both essential components of effective surveillance video analysis for the purpose of guaranteeing public safety. However, existing approaches such as three-dimensional convolutional neural networks (3D CNN) and two-stream neural networks (2SNN) have computational hurdles due to the significant parameterization they require. In this paper, we offer HARNet, a specialized lightweight residual 3D CNN that is built on directed acyclic graphs and was created expressly to handle these issues and achieve effective human action detection. The suggested method presents an innovative pipeline for creating spatial motion data from raw video inputs, which makes successful latent representation learning of human motions easier to accomplish. This generated input is then supplied into HARNet, which processes spatial and motion information in a single stream in an effective manner, maximizing the benefits of both types of cues. The use of traditional machine learning classifiers is done in order to further improve the discriminative capacity of the features that have been learned. To be more specific, we use the latent representations that are stored in HARNet’s fully connected layer and use them as our deep learnt features. After that, these features are entered into the Support Vector Machine (SVM) classifier in order to accomplish action recognition. In order to evaluate the HARNet-SVM method that was developed, empirical tests were run on commonly used action recognition datasets such as UCF101, HMDB51, and the KTH dataset. These tests were carried out in order to gather data for the evaluation. The experimental results show that our method is superior to other state-of-the-art approaches, achieving considerable performance increases of 2.75% on UCF101, 10.94% on HMDB51, and 0.18% on the KTH dataset. These results were obtained by running the method on each dataset separately. Our findings demonstrate the usefulness of HARNet’s lightweight design and highlight the significance of utilizing SVM classifiers with deep learnt features for the purpose of accurate and computationally efficient human activity recognition in surveillance videos. This work helps to the advancement of surveillance technology, which in turn makes video analysis in applications that take place in the real world safer and more dependable.

Recognizing different human actions from still images or videos is an important research area in the computer vision and artificial intelligence domains. It represents a key step for a wide range of applications including: human-computer interaction, ambient assisted living, intelligent driving and video surveillance. However, unless the many research works being involved, there are still many challenges ahead including: the high changes in human body shapes, clothing and viewpoint changes and the conditions of system acquisition (illumination variations, occlusions, etc.). With the emergence of new deep learning techniques, many approaches are recently proposed for Human Action Recognition (HAR). Compared with conventional machine learning methods, deep learning techniques have more powerful learning ability. The most wide-spread deep learning approach is the Convolutional Neural Network (CNN/ConvNets). It has shown remarkable achievements due to its precision and robustness. As a branch of neural network, 3D CNN is a relatively new technique in the field of deep learning. In this paper, we propose a HAR approach based on a 3D CNN model. We apply the developed model to recognize human actions of KTH and J-HMDB datasets, and we achieve state of the art performance in comparison to baseline methods.

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.

Human Action Recognition (HAR) has grown significantly because of its many uses, including real-time surveillance and human-computer interaction. Various variations in routine human actions make the recognition process of action more difficult. In this paper, we proposed a novel deep learning architecture known as Inverted Bottleneck Residual with Self-Attention (InBRwSA). The proposed architecture is based on two different modules. In the first module, 6-parallel inverted bottleneck residual blocks are designed, and each block is connected with a skip connection. These blocks aim to learn complex human actions in many convolutional layers. After that, the second module is designed based on the self-attention mechanism. The learned weights of the first module are passed to self-attention, extract the most essential features, and can easily discriminate complex human actions. The proposed architecture is trained on the selected datasets, whereas the hyperparameters are chosen using the particle swarm optimization (PSO) algorithm. The trained model is employed in the testing phase for the feature extraction from the self-attention layer and passed to the shallow wide neural network classifier for the final classification. The HMDB51 and UCF 101 are frequently used as action recognition standard datasets. These datasets are chosen to allow for meaningful comparison with earlier research. UCF101 dataset has a wide range of activity classes, and HMDB51 has varied real-world behaviors. These features test the generalizability and flexibility of the presented model. Moreover, these datasets define the evaluation scope within a particular domain and guarantee relevance to real-world circumstances. The proposed technique is tested on both datasets, and accuracies of 78.80% and 91.80% were achieved, respectively. The ablation study demonstrated that a margin of error value of 70.1338 ± 3.053 (±4.35%) and 82.7813 ± 2.852 (±3.45%) for the confidence level 95%,1.960σx̄ is obtained for HMDB51 and UCF datasets respectively. The training time for the highest accuracy for HDMB51 and UCF101 is 134.09 and 252.10 seconds, respectively. The proposed architecture is compared with several pre-trained deep models and state-of-the-art (SOTA) existing techniques. Based on the results, the proposed architecture outperformed existing techniques.

Video-based human action recognition is one of the most important and challenging areas of research in the field of computer vision. Human action recognition has found many pragmatic applications in video surveillance, human-computer interaction, entertainment, autonomous driving, etc. Owing to the recent development of deep learning methods for human action recognition, the performance of action recognition has significantly enhanced for challenging datasets. Deep learning techniques are mainly used for recognizing actions in images and videos comprising of Euclidean data. A recent development in deep learning methods is the extension of these techniques to non-Euclidean data or graph data with many nodes and edges. Human body skeleton resembles a graph, therefore, the graph convolutional network (GCN) is applicable to the non-Euclidean body skeleton. In the past few years, GCN has emerged as an important tool for skeleton-based action recognition. Therefore, we conduct a survey using GCN methods for action recognition. Herein, we present a comprehensive overview of recent GCN techniques for action recognition, propose a taxonomy for the categorization of GCN techniques for action recognition, carry out a detailed study of the benchmark datasets, enlist relevant resources and open-source codes, and finally provide an outline for future research directions and trends. To the best of authors' knowledge, this is the first survey for action recognition using GCN techniques.

In order to improve the accuracy of human action recognition in video and the computational efficiency of large data sets, an action recognition algorithm based on multiple features and modified deep learning model is proposed. First, the deep network pre-training process is used to learn and optimize the RBM parameters, and the deep belief nets (DBN) model is constructed through deep learning. Then, human 13 joint points and critical points of optical flow are automatically extracted by DBN model. Second, these more abstract and more effective human motion features are combined to represent human actions. Ultimately, the entire DBN network structure is fine-tuned by support vector machine (SVM) algorithm to classify human actions. We demonstrate that human 13 joint points and critical points of optical flow are two very effective human action characterizations, our proposed approach greatly reduces the required samples, and shortens the training time of the samples, can efficiently process large data sets and can effectively recognize novel actions. We performed experiments on the KTH data set, Weizmann data set, the ballet data set and UCF101 data set to evaluate the proposed method, the experiment results show that the average recognition accuracy is over 98%, which validates its effectiveness, and show that our results are stable, reliable, and significantly better than the results of two state-of-the-art approaches on four different data sets. So, it lays a good theoretical foundation for practical applications.

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.

With the rise of computer vision, it is becoming more and more important to accurately recognize and evaluate human actions. However, the complexity, intraclass differences, and viewing angle changes of human actions significantly impact the accuracy of identification human actions. This paper proposed an action recognition and evaluation method based on skeleton information extraction. Briefly, We use Lightweight OpenPose to extract the key points of human skeleton and perform processing work, including video data cutting, deleting some key points, supplementing missing key points, filtering processing, feature extraction, etc. Through an in-depth exploration of related theoretical technologies, we proposed a model for recognition and evaluation of human table tennis actions with an ordinary camera. The support vector machine algorithm (SVM) classification model is used to identify table tennis actions in real-time. Then the dynamic time regularization (DTW) algorithm calculates the similarity of each human skeleton key point in the action sequence. The low-scoring bone key points are marked to evaluate the human table tennis action in real time. The results show that a recognition rate of more than 95% is achieved in the test set, which proves the method's effectiveness. In addition, we compared the results with previous work using inertial sensors for action recognition, which shows our method can preserve the same accuracy with a much lower cost of implementation.

Human detection and action recognition form the basis for understanding human behaviors. Human detection is used to detect the positions of humans, and action recognition is able to recognize the action of specific humans. However, numerous approaches have been used to handle action recognition and human detection separately. Therefore, three main issues still exist when independent methods of human detection and action recognition are combined, 1) intrinsic errors in object detection impact the performance of action recognition, 2) features common to action recognition and object detection are missed, 3) the combination also has an impact on processing speed. We propose a single framework for human detection and action recognition to solve these issues. It is based on a hierarchical structure called Boosted Randomized Trees. The nodes are trained such that the upper nodes detect humans from the background, while the lower nodes recognize action. We were able to improve both human detection and action recognition rates over earlier hierarchical structure approaches with the proposed method.

Human activity recognition is an important research area of computer vision. There is an urgent mechanism to automatically detect and retrieve semantic events in videos based on video contents. Low-level video sequence content is translated into high-level video sequence content is a interesting research topic in recent years. Its applications include automated video surveillance schemes, intensive care systems, airports, analysis of the physical condition of people and a variety of systems which include human-computer interfaces. Automatic recognition of high level activities which refers combination of multiple simple human actions. By recognizing high level human action from video sequence helps to construct many important applications. Human activity can be analyzed in many ways. In this paper, wave pattern is used to identify different human activities. This pattern is generated by using texture features (energy) for the extracted foreground objects. Various kinds of human actions are analyzed and classified. The system consists of following stages: object detection, feature parameter extraction, pattern generation and classification. Gaussian mixture model is used for extracting foreground object from background image. Pre-processing is done in order to reduce the noise content from each and every frame. Then wave pattern is generated by using energy function. K-Nearest Neighboring is used to classify the different human activities. From this wave pattern presence of objects, direction of moving object, no of objects presented in foreground frame are observed. By using this information human activities in each frame are classified using K-NN. Two different types of dataset namely KTH dataset and WEIZMANN dataset is used. The accuracy rate of the system is 93.33%.

Understanding and recognizing human actions automatically have several applications in computer vision and human-machine interaction. In this paper, we aim to identify human actions in a short video automatically on KTH Dataset. We represented videos involving human actions into feature vector, which is invariant to small changes in the video and thus makes classification easier. We developed our model under reasonable assumptions that performs well. Our method achieves an average accuracy of 91.67% on 8 subjects with varying actions and gaits. We also compared our results with various algorithms and achieved good accuracy.

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.

This research proposes a vision-based online human action recognition system. This system uses deep learning methods to recognise human action under moving camera circumstances. The proposed system consists of five stages: human detection, human tracking, feature extraction, action classification and fusion. The system uses three kinds of input information: colour intensity, short-term dynamic information and skeletal joints. In the human detection stage, a two-dimensional (2D) pose estimator method is used to detect a human. In the human tracking stage, a deep SORT tracking method is used to track the human. In the feature extraction stage, three kinds of features, spatial, temporal and structural, are extracted to analyse human actions. In the action classification stage, three kinds of features of human actions are respectively classified by three kinds of long short-term memory (LSTM) classifiers. In the fusion stage, a fusion method is used to leverage the three output results from the LSTM classifiers. This study constructs a computer vision and image understanding (CVIU) Moving Camera Human Action dataset (CVIU dataset), containing 3,646 human action sequences, including 11 types of single human actions and 5 types of interactive human actions. This dataset was used to train and evaluate the proposed system. Experimental results showed that the recognition rates of spatial features, temporal features and structural features were 96.64%, 81.87% and 68.10%, respectively. Finally, the fusion result of human action recognition for indoor smart mobile robots in this study was 96.84%.

Action recognition, a field within human-centered computing, is vital for identifying and understanding human actions, benefiting applications like surveillance, autonomous vehicles, and human-computer interaction. Artificial intelligence’s enduring goal is to develop robust models for perceiving and understanding the visual world around us. Deep neural networks have shown exceptional performance in various tasks, profoundly impacting real-world applications, including action prediction and recognition, which have advanced significantly in recent years. Most work in visual human action recognition focuses on single viewpoints or modalities from complete observation. Yet, the real significance lies in predicting future actions from incomplete observations to prevent real-world tragedies. With the availability of multiple cameras and data from multiple modalities (RGB, Depth, and Skeleton) available today, it becomes possible to model human action in multi-view and multi-modality context, minimizing the data loss due to occlusions and signal quality issues to improve recognition accuracy on the strength of state-of-the-art deep learning models. However, deep neural network models are susceptible to adversarial attacks, where imperceptible perturbations can compromise action recognition model performance. This thesis focuses on identifying latent vulnerabilities and proposing a defense mechanism against such threats in a multi-modality and multi-view setting. This work introduces an efficient and effective attack mechanism that perturbs skeleton data by targeting key joints and segments while employing a graph attention mechanism that learns the semantics to perturb other modalities. Additionally, an approach has been developed that not only adds noise but also alters the visual spatial structure of skeleton data through generative modeling. Furthermore, this dissertation introduces a defense mechanism known as the Collaborative Knowledge Distillation Network, which leverages graph attention and knowledge distillation techniques. This network leverages the knowledge from compromised multi-view data and integrates information from clean data to address incomplete observations and noisy action videos, enhancing the robustness of action recognition models for real-world applications.