A Review and Comparative Study of Explainable Deep Learning Models Applied on Action Recognition in Real Time
-
Published:2023-04-27
Issue:9
Volume:12
Page:2027
-
ISSN:2079-9292
-
Container-title:Electronics
-
language:en
-
Short-container-title:Electronics
Author:
Mahmoudi Sidi Ahmed1ORCID, Amel Otmane1, Stassin Sédrick1ORCID, Liagre Margot1, Benkedadra Mohamed12ORCID, Mancas Matei2ORCID
Affiliation:
1. ILIA Lab, Faculty of Engineering, University of Mons, 7000 Mons, Belgium 2. ISIA Lab, Faculty of Engineering, University of Mons, 7000 Mons, Belgium
Abstract
Video surveillance and image acquisition systems represent one of the most active research topics in computer vision and smart city domains. The growing concern for public and workers’ safety has led to a significant increase in the use of surveillance cameras that provide high-definition images and even depth maps when 3D cameras are available. Consequently, the need for automatic techniques for behavior analysis and action recognition is also increasing for several applications such as dangerous actions detection in railway stations or construction sites, event detection in crowd videos, behavior analysis, optimization in industrial sites, etc. In this context, several computer vision and deep learning solutions have been proposed recently where deep neural networks provided more accurate solutions, but they are not so efficient in terms of explainability and flexibility since they remain adapted for specific situations only. Moreover, the complexity of deep neural architectures requires the use of high computing resources to provide fast and real-time computations. In this paper, we propose a review and a comparative analysis of deep learning solutions in terms of precision, explainability, computation time, memory size, and flexibility. Experimental results are conducted within simulated and real-world dangerous actions in railway construction sites. Thanks to our comparative analysis and evaluation, we propose a personalized approach for dangerous action recognition depending on the type of collected data (image) and users’ requirements.
Funder
company of Infrabel Project Field Worker Protection with AI
Subject
Electrical and Electronic Engineering,Computer Networks and Communications,Hardware and Architecture,Signal Processing,Control and Systems Engineering
Reference84 articles.
1. Mahmoudi, S.A., Sharif, H., Ihaddadene, N., and Djeraba, C. (2008, January 20–22). Abnormal event detection in real time video. Proceedings of the 1st International Workshop on Multimodal Interactions Analysis of Users in a Controlled Environment, ICMI, Chania, Greece. 2. Benabbas, Y., Lablack, A., Ihaddadene, N., and Djeraba, C. (2010, January 23–26). Action Recognition Using Direction Models of Motion. Proceedings of the 2010 20th International Conference on Pattern Recognition, Istanbul, Turkey. 3. Mahmoudi, S.A., Kierzynka, M., and Manneback, P. (2013, January 3–5). Real-time GPU-based motion detection and tracking using full HD videos. Proceedings of the Intelligent Technologies for Interactive Entertainment: 5th International ICST Conference, INTETAIN 2013, Mons, Belgium. 4. Motion Pattern Extraction and Event Detection for Automatic Visual Surveillance;Benabbas;Eurasip Jbenabbas2 Video Process.,2011 5. Real-time motion tracking using optical flow on multiple GPUs;Mahmoudi;Bull. Pol. Acad. Sci. Tech. Sci.,2014
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Action recognition in compressed domains: A survey;Neurocomputing;2024-02 2. A Comparative Analysis of Deep Learning-Based Object Detectors for Embedded Systems;2023 IEEE 12th International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS);2023-09-07 3. Basketball action recognition based on the combination of YOLO and a deep fuzzy LSTM network;The Journal of Supercomputing;2023-09-05
|
|