Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
7.3
3.4
Journals
Sensors
Special Issues
Computer Vision-Based Human Activity Recognition
sensors-logo
Submit to Special Issue Submit Abstract to Special Issue Review for Sensors Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Computer Vision-Based Human Activity Recognition

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Sensing and Imaging".

Deadline for manuscript submissions: 20 July 2025 | Viewed by 5943

Special Issue Editor

Dr. Stefan Poslad

E-Mail Website
Guest Editor
Director, IoT2US Lab, Queen Mary University of London, London, UK
Interests: Internet of Things; ubiquitous computing; smart environments; spatial-awareness; pervasive games; security; privacy
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Humans perform a common set of (physical) activities of daily living (ADLs) necessary for self-care and living independently, involving body-part versus whole-body movement. Yet, humans also perform a richer variety of ADLs applied to entertainment, health, sports, surveillance, transport, leisure, and work, involving single and groups of humans scaling up to large crowds. Increasing (and autonomous) automation, changes to the physical environment, and the ageing yet increasing population will affect our ADLs. Hence, recognising, modelling, and analysing ADLs are essential and have many benefits and applications. Whilst a range of sensors can be used for human activity recognition (HAR), the focus here is on the use of computer vision (CV) used for HAR that includes a range of cameras—micro to macro, short-range to remote, stationary versus mobile, and visible versus non-visible light—and can involve the use of hybrid (non-visual plus) visual sensor fusion. This is being driven by advances in micro-sensors, cheaper high-resolution cameras, the increased embedding of cameras into the environment, and improvements in computer vision object recognition and artificial intelligence. Note that most HAR goes beyond pure human recognition and involves relevant physical object recognition to greatly aid this too. This SI targets innovations that support the narrative given above. It also includes new methods and designs for systems based on the Internet of Things; cyber-physical and embedded systems; sensor data acquisition; sensor data fusion; data analytics involving probabilistic and digital twin models to classify, predict, and simulate HAR; data science and AI; and data visualisation and decision support for HAR. Note that accepted papers need to have a viable computer vision-sensing element for HAR. 

Dr. Stefan Poslad
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • human activity recognition (HAR)
  • activities of daily living (ADLs)
  • computer vision (CV)
  • sensor data fusion for CV
  • AI and data science for CV

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (5 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

14 pages, 772 KiB  
Article
Leveraging Artificial Occluded Samples for Data Augmentation in Human Activity Recognition
by Eirini Mathe, Ioannis Vernikos, Evaggelos Spyrou and Phivos Mylonas
Sensors 2025, 25(4), 1163; https://doi.org/10.3390/s25041163 - 14 Feb 2025
Viewed by 543
Abstract
A significant challenge in human activity recognition lies in the limited size and diversity of training datasets, which can lead to overfitting and the poor generalization of deep learning models. Common solutions include data augmentation and transfer learning. This paper introduces a novel [...] Read more.
A significant challenge in human activity recognition lies in the limited size and diversity of training datasets, which can lead to overfitting and the poor generalization of deep learning models. Common solutions include data augmentation and transfer learning. This paper introduces a novel data augmentation method that simulates occlusion by artificially removing body parts from skeleton representations in training datasets. This contrasts with previous approaches that focused on augmenting data with rotated skeletons. The proposed method increases dataset size and diversity, enabling models to handle a broader range of scenarios. Occlusion, a common challenge in real-world HAR, occurs when body parts or external objects block visibility, disrupting activity recognition. By leveraging artificially occluded samples, the proposed methodology enhances model robustness, leading to improved recognition performance, even on non-occluded activities. Full article
(This article belongs to the Special Issue Computer Vision-Based Human Activity Recognition)
►▼ Show Figures

Figure 1

19 pages, 3693 KiB  
Article
Real-Time On-Device Continual Learning Based on a Combined Nearest Class Mean and Replay Method for Smartphone Gesture Recognition
by Heon-Sung Park, Min-Kyung Sung, Dae-Won Kim and Jaesung Lee
Sensors 2025, 25(2), 427; https://doi.org/10.3390/s25020427 - 13 Jan 2025
Viewed by 899
Abstract
Sensor-based gesture recognition on mobile devices is critical to human–computer interaction, enabling intuitive user input for various applications. However, current approaches often rely on server-based retraining whenever new gestures are introduced, incurring substantial energy consumption and latency due to frequent data transmission. To [...] Read more.
Sensor-based gesture recognition on mobile devices is critical to human–computer interaction, enabling intuitive user input for various applications. However, current approaches often rely on server-based retraining whenever new gestures are introduced, incurring substantial energy consumption and latency due to frequent data transmission. To address these limitations, we present the first on-device continual learning framework for gesture recognition. Leveraging the Nearest Class Mean (NCM) classifier coupled with a replay-based update strategy, our method enables continuous adaptation to new gestures under limited computing and memory resources. By employing replay buffer management, we efficiently store and revisit previously learned instances, mitigating catastrophic forgetting and ensuring stable performance as new gestures are added. Experimental results on a Samsung Galaxy S10 device demonstrate that our method achieves over 99% accuracy while operating entirely on-device, offering a compelling synergy between computational efficiency, robust continual learning, and high recognition accuracy. This work demonstrates the potential of on-device continual learning frameworks that integrate NCM classifiers with replay-based techniques, thereby advancing the field of resource-constrained, adaptive gesture recognition. Full article
(This article belongs to the Special Issue Computer Vision-Based Human Activity Recognition)
►▼ Show Figures

Figure 1

15 pages, 2250 KiB  
Article
Video-Based Plastic Bag Grabbing Action Recognition: A New Video Dataset and a Comparative Study of Baseline Models
by Pei Jing Low, Bo Yan Ng, Nur Insyirah Mahzan, Jing Tian and Cheung-Chi Leung
Sensors 2025, 25(1), 255; https://doi.org/10.3390/s25010255 - 4 Jan 2025
Viewed by 790
Abstract
Recognizing the action of plastic bag taking from CCTV video footage represents a highly specialized and niche challenge within the broader domain of action video classification. To address this challenge, our paper introduces a novel benchmark video dataset specifically curated for the task [...] Read more.
Recognizing the action of plastic bag taking from CCTV video footage represents a highly specialized and niche challenge within the broader domain of action video classification. To address this challenge, our paper introduces a novel benchmark video dataset specifically curated for the task of identifying the action of grabbing a plastic bag. Additionally, we propose and evaluate three distinct baseline approaches. The first approach employs a combination of handcrafted feature extraction techniques and a sequential classification model to analyze motion and object-related features. The second approach leverages a multiple-frame convolutional neural network (CNN) to exploit temporal and spatial patterns in the video data. The third approach explores a 3D CNN-based deep learning model, which is capable of processing video data as volumetric inputs. To assess the performance of these methods, we conduct a comprehensive comparative study, demonstrating the strengths and limitations of each approach within this specialized domain. Full article
(This article belongs to the Special Issue Computer Vision-Based Human Activity Recognition)
►▼ Show Figures

Figure 1

19 pages, 2352 KiB  
Article
Empowering Efficient Spatio-Temporal Learning with a 3D CNN for Pose-Based Action Recognition
by Ziliang Ren, Xiongjiang Xiao and Huabei Nie
Sensors 2024, 24(23), 7682; https://doi.org/10.3390/s24237682 - 30 Nov 2024
Viewed by 1099
Abstract
Action recognition based on 3D heatmap volumes has received increasing attention recently because it is suitable for application to 3D CNNs to improve the recognition performance of deep networks. However, it is difficult for models to capture global dependencies due to their restricted [...] Read more.
Action recognition based on 3D heatmap volumes has received increasing attention recently because it is suitable for application to 3D CNNs to improve the recognition performance of deep networks. However, it is difficult for models to capture global dependencies due to their restricted receptive field. To effectively capture long-range dependencies and balance computations, a novel model, PoseTransformer3D with Global Cross Blocks (GCBs), is proposed for pose-based action recognition. The proposed model extracts spatio-temporal features from processed 3D heatmap volumes. Moreover, we design a further recognition framework, RGB-PoseTransformer3D with Global Cross Complementary Blocks (GCCBs), for multimodality feature learning from both pose and RGB data. To verify the effectiveness of this model, we conducted extensive experiments on four popular video datasets, namely FineGYM, HMDB51, NTU RGB+D 60, and NTU RGB+D 120. Experimental results show that the proposed recognition framework always achieves state-of-the-art recognition performance, substantially improving multimodality learning through action recognition. Full article
(This article belongs to the Special Issue Computer Vision-Based Human Activity Recognition)
►▼ Show Figures

Figure 1

21 pages, 10905 KiB  
Article
Low-Cost Non-Wearable Fall Detection System Implemented on a Single Board Computer for People in Need of Care
by Vanessa Vargas, Pablo Ramos, Edwin A. Orbe, Mireya Zapata and Kevin Valencia-Aragón
Sensors 2024, 24(17), 5592; https://doi.org/10.3390/s24175592 - 29 Aug 2024
Cited by 1 | Viewed by 2087
Abstract
This work aims at proposing an affordable, non-wearable system to detect falls of people in need of care. The proposal uses artificial vision based on deep learning techniques implemented on a Raspberry Pi4 4GB RAM with a High-Definition IR-CUT camera. The CNN architecture [...] Read more.
This work aims at proposing an affordable, non-wearable system to detect falls of people in need of care. The proposal uses artificial vision based on deep learning techniques implemented on a Raspberry Pi4 4GB RAM with a High-Definition IR-CUT camera. The CNN architecture classifies detected people into five classes: fallen, crouching, sitting, standing, and lying down. When a fall is detected, the system sends an alert notification to mobile devices through the Telegram instant messaging platform. The system was evaluated considering real daily indoor activities under different conditions: outfit, lightning, and distance from camera. Results show a good trade-off between performance and cost of the system. Obtained performance metrics are: precision of 96.4%, specificity of 96.6%, accuracy of 94.8%, and sensitivity of 93.1%. Regarding privacy concerns, even though this system uses a camera, the video is not recorded or monitored by anyone, and pictures are only sent in case of fall detection. This work can contribute to reducing the fatal consequences of falls in people in need of care by providing them with prompt attention. Such a low-cost solution would be desirable, particularly in developing countries with limited or no medical alert systems and few resources. Full article
(This article belongs to the Special Issue Computer Vision-Based Human Activity Recognition)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-5
Back to TopTop