Spatio-Temporal Analysis for Human Action Detection and Recognition in Uncontrolled Environments

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.

Various motion detection methods have been proposed in the past decade, but there are seldom attempts to investigate the advantages and disadvantages of different detection mechanisms so that they can complement each other to achieve a better performance. Toward such a demand, this paper proposes a human action detection and recognition framework to bridge the semantic gap between low-level pixel intensity change and the high-level understanding of the meaning of an action. To achieve a robust estimation of the region of action with the complexities of an uncontrolled background, we propose the combination of the optical flow field and Harris3D corner detector to obtain a new spatial-temporal estimation in the video sequences. The action detection method, considering the integrated motion information, works well with the dynamic background and camera motion, and demonstrates the advantage of the proposed method of integrating multiple spatial-temporal cues. Then the local features (SIFT and STIP) extracted from the estimated region of action are used to learn the Universal Background Model (UBM) for the action recognition task. The experimental results on KTH and UCF YouTube Action (UCF11) data sets show that the proposed action detection and recognition framework can not only better estimate the region of action but also achieve better recognition accuracy comparing with the peer work.

Video based Human Action Recognition (HAR) is an active research field of Machine Learning (ML) and human detection in videos is the most important step in action recognition. Recently, several techniques and algorithms have been proposed to increase the accuracy of HAR process, but margin of improvement still exists. Detection and classification of human actions is a challenging task due to random changes in human appearance, clothes, illumination, and background. In this article, an efficient technique to classify human actions by utilizing steps like removing redundant frames from videos, extracting Segments of Interest (SoIs), feature descriptor mining through Geodesic Distance (GD), 3D Cartesian-plane Features (3D-CF), Joints MOCAP (JMOCAP) and n-way Point Trajectory Generation (nPTG). A Neuro Fuzzy Classifier (NFC) is used at the end for the classification purpose. The proposed technique is tested on two publicly available datasets including HMDB-51 and Hollywood2, and achieved an accuracy of 82.55% and 91.99% respectively. These efficient results prove the validity of proposed model.

Video and image analysis technologies have made human action recognition as an interesting field and used in many practical application systems such as visual surveillance systems, healthcare monitoring systems, 3D games and smart home. In this paper, we address the challenges of automatic tracking, detection and recognition of three-dimensional human pose-based actions from sequences of depth maps. Specifically, we have designed our proposed idea into a probabilistic framework: 1) dividing each action into meaningful ordered temporal segments, 2) using pixel-neighboring intensity difference approach to identify human shape region from the confused scenes, 3) introducing a robust spatiotemporal features to extract 3D joints information via local distance features and depth human shape information to get motion variation features and 4) finally these sets of features are merged together and their feature vectors are further reduced and discriminated to get optimal vectors for real-world applications. Next, the augmented features are enhanced and symbolized by Linde-Buzo-Gray clustering algorithm for better action recognition. With these symbols, each action hidden Markov model (HMM) is trained and tested for action recognition. The experimental results demonstrated our proposed approach on three challenging depth video datasets: IM-DepthActions, MSRAction3D and MSRDailyActivity3D, producing significantly improved results over the state-of-the-art methods: especially for those actions that are not easily discernible by the existing methods.

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.

Human action detection and recognition has become a significant topic in computer vision research over the last two decades. Intelligent techniques (such as machine learning and deep learning) have grown in popularity as a result of technological advancements in visual data. Due to the exponential growth of video data generated by surveillance cameras, intelligent systems are in great demand for detecting specific human activities. In this work, we critically examine the state-of-the-art (SOA) methodologies for human activity detection (HAD) approaches. The study illustrates a generic classification for HAD methods anda paradigm shift is observed from traditional to modern deep learning-based techniques. We also provide an analysis of publicly available datasets for the classification of human activities. The paper outlines various open research issues as well as future directions for HAD methods. Due to problems such as a dynamic and complex background, camera motion, occlusion, and bad weather, it is evident that detecting human behaviors in surveillance videos is a challenging task. Convolution neural networks (CNNs) are used in the bulk of HAD techniques, prompting researchers to look at sequence learning models like Recurrent Neural Networks (RNNs) and Long-Short-Term Neural Networks (LSTM). Furthermore, our analysis indicates that only a few research articles on the detection of anomalous behavior have been published, with the majority of the work focusing on human action detection. Furthermore, existing HAD deep learning models could be improved by including the notion of transfer learning, which saves training time and enhances accuracy.

Human action recognition and localization is a challenging vision task with promising applications. To tackle this problem, recently developed commodity depth sensor (e.g., Microsoft Kinect) has opened up new opportunities with several developed human motion features based on depth image for action representation. However, how depth information can be effectively adopted in the middle or high level representation in action detection, in particular, the depth induced three dimensional contextual information for modeling interactions between human-human, human-object and human-surroundings has yet been explored. In this paper, we propose a novel action recognition and localization framework which effectively fuses depth-induced contextual information from different levels of the processing pipeline for understanding various interactions. First, depth image is combined with grayscale image for more robust human subject and object detection. Second, three dimensional spatial and temporal relationship among human subjects or objects is represented based on the combination of grayscale and depth images. Third, depth information is further utilized to represent different types of indoor scenes. Finally, we fuse these multiple stage depth-induced contextual information to yield an unified action detection framework. Extensive experiments on a challenging grayscale + depth human action detection benchmark database demonstrate the effectiveness of the depth-induced contextual information and the high detection accuracy of the proposed framework.

Human Activity Detection and Action Recognition in videos using Convolutional Neural Networks

Human Activity Recognition (HAR) is widely used in many applications and HAR using smartphone only has been proved to be effective, flexible and unobtrusive for activity recognition. In this paper, a two-layer and multi-strategy HAR framework is proposed to overcome the major challenge of HAR using smartphone only, i.e., the variation in orientation and position of the device. In the first layer, the activities are classified into different groups with high accuracy and for each group in the second layer, the appropriate strategy is designed according to the characteristics of the group to improve the recognition performance. For static activity group, the transitional activities are introduced to help classifying the activities indirectly. For dynamic activity group sensitive to the position variation of the smartphone, a position-assisted strategy is proposed to alleviate the influence of position variation. The simulation results demonstrate the effectiveness of the proposed two-layer multi-strategy HAR framework.

Many organisations face challenges in accurately and efficiently identifying human activities using manually operated CCTV cameras and small datasets, particularly in densely populated and dynamic environments. This paper presents a real‐time human activity detection and recognition system that leverages You Only Look Once version 8 (YOLOv8) for object detection and integrates the deep simple online real‐time tracking algorithm for associate frames, robust tracking and individual identity preservation. Evaluated on a combination of public and experimental datasets containing over 10,000 frames, the system achieves notable enhancements in efficiency along with accuracy. Through data preprocessing and algorithm optimisation, the Adam optimiser outperformed stochastic gradient descent (SGD) by more than 5% in accuracy. K ‐fold cross‐validation was applied to reduce overfitting, while anchor boxes of varying scales and aspect ratios improved the detection of objects of different sizes. The aspect ratio, which is used to mitigate the effect of object size and control edge‐orientation issues by computing the ratio of width to height of the bounding boxes in YOLOv8, plays a crucial role in object detection.YOLOv8l, combined with DeepSORT, delivers state‐of‐the‐art results, achieving a mean average precision of 96.1% in mixed datasets. The system assigns unique IDs to track individuals, enabling precise frame association during motion in crowded areas, which is crucial for maintaining accuracy in complex environments. This study presents a robust and scalable model, offering a significant improvement for public surveillance technology.

Indoor activity monitoring methods ensure the well-being and security of elderly and visually impaired people living in their houses. These systems utilize numerous technologies and sensors to monitor day-to-day activities, including medication adherence, movement, and sleep patterns, providing a comprehensive view of the user’s overall health and daily life. The accuracy and adaptability of deep learning (DL) models make human activity recognition (HAR) a valuable tool for enhancing effectiveness, security, and personalized experiences in indoor environments. HAR, utilizing DL techniques, innovates indoor monitoring by enabling precise understanding and detection of human actions. Deep neural networks (DNNs) analyze data from multiple sensors, such as cameras or accelerometers, to distinguish between various action patterns. DL models mechanically remove and learn discriminating features, making them suitable for identifying intricate human activities in sensor data. Nevertheless, selecting the appropriate DL architectures and optimizing their parameters is crucial for achieving improved solutions. This study proposes an Improved Pelican Optimisation for Indoor Activity Recognition in Persons with Disabilities using the Recurrent Neural Network (IPOIAR-DPRNN) method. The primary aim of the IPOIAR-DPRNN method is to enhance indoor activity detection systems for individuals with disabilities. Initially, the image pre-processing stage applies adaptive bilateral filtering (ABF) to reduce unwanted distortions or artefacts in the image. Furthermore, the EfficientNetB7 method is employed for the feature extraction process. For the detection and classification of indoor activities, the bidirectional long short-term memory with multi-head self-attention (BiLSTM-MHSA) technique is used. Additionally, the improved pelican optimization algorithm (IPOA)-based hyperparameter tuning is performed to enhance the detection results of the BiLSTM-MHSA technique. The validation of the IPOIAR-DPRNN approach is examined using the Florence 3D Actions dataset, and the outcomes are measured against various metrics. The comparison study of the IPOIAR-DPRNN approach revealed a superior accuracy value of 97.11% compared to existing techniques.

SUMMARYRemote surveillance of large‐scale equipment such as power plants and building complexes is important to prevent serious attacks and troubles. Automatic human action recognition can reduce the burdens of the surveillance. Multiview video is useful for human action recognition, because it provides robustness to the changes of people's appearance by orientation and occlusion. One problem of conventional multiview action recognition is that it requires both detection and tracking before action recognition. Human pose and motion vary depending on the person's action, and such variances may cause detection and tracking error. To solve this problem, previous work has proposed simultaneous action recognition and location estimation for single‐view videos using Hough voting. In this paper, we extend the Hough voting approach to simultaneous multiview action recognition and location estimation. Our proposed method independently casts votes for the action labels and spatiotemporal reference positions of actions in each view and integrates them using homographical transformations in the multiview extension. We evaluated our method and confirmed that it achieved high accuracy in action recognition and location estimation. The contribution of this paper is that it enables multiview action recognition without prior human detection and tracking.

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 the actions, plans, and goals of a person in an unconstrained environment is a key feature that future robotic systems will need in order to achieve a natural human-machine interaction. Indeed, we humans are constantly understanding and predicting the actions and goals of others, which allows us to interact in intuitive and safe ways. While action and plan recognition are tasks that humans perform naturally and with little effort, they are still an unresolved problem from the point of view of artificial intelligence. The immense variety of possible actions and plans that may be encountered in an unconstrained environment makes current approaches be far from human-like performance. In addition, while very different types of algorithms have been proposed to tackle the problem of activity, plan, and goal (intention) recognition, these tend to focus in only one part of the problem (e.g., action recognition), and techniques that address the problem as a whole have been not so thoroughly explored. This review is meant to provide a general view of the problem of activity, plan, and goal recognition as a whole. It presents a description of the problem, both from the human perspective and from the computational perspective, and proposes a classification of the main types of approaches that have been proposed to address it (logic-based, classical machine learning, deep learning, and brain-inspired), together with a description and comparison of the classes. This general view of the problem can help on the identification of research gaps, and may also provide inspiration for the development of new approaches that address the problem in a unified way.

Human Activity Recognition (HAR) is the automatic detection and understanding of human motion behavior based on data extracted from video camera, ambient sensors or wearable sensors which particularly has recently attracted increased attention from both researchers and industry. However, for running practical HAR systems on wearable devices, there are some requirements such as design and development of small, lightweight, powerful, and low-cost smart sensors. In this context, data must be continuously collected, and edge computing is a viable solution, which is an energy-efficient technique, offering real-time response and privacy requirements for HAR applications. Rather than sending data to the cloud, edge computing is a local process that minimizes the data transmission time and responds with low latency. Recently, HAR system designers have adopted deep learning techniques inspired by their outstanding performance in many application areas and achieved relevant gain in activity recognition performance, however, these techniques were not demonstrated suitable for running on resource constrained devices. Thus, designing energy-efficient deep learning models is critical for realizing efficient HAR for mobile applications. In this work, we present a lightweight framework for the deployment of low-power but accurate HAR systems for these devices. We also implement and run the system in a microcontroller and analyze computational cost and energy consumption, and how different system configurations and deep learning model complexity influence on that.