Human Activity Recognition: Review, Taxonomy and Open Challenges
Nowadays, Human Activity Recognition (HAR) is being widely used in a variety of domains, and vision and sensor-based data enable cutting-edge technologies to detect, recognize, and monitor human activities. Several reviews and surveys on HAR have already been published, but due to the constantly gro...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/17/6463 |
| _version_ | 1797493203075596288 |
|---|---|
| author | Muhammad Haseeb Arshad Muhammad Bilal Abdullah Gani |
| author_facet | Muhammad Haseeb Arshad Muhammad Bilal Abdullah Gani |
| author_sort | Muhammad Haseeb Arshad |
| collection | DOAJ |
| description | Nowadays, Human Activity Recognition (HAR) is being widely used in a variety of domains, and vision and sensor-based data enable cutting-edge technologies to detect, recognize, and monitor human activities. Several reviews and surveys on HAR have already been published, but due to the constantly growing literature, the status of HAR literature needed to be updated. Hence, this review aims to provide insights on the current state of the literature on HAR published since 2018. The ninety-five articles reviewed in this study are classified to highlight application areas, data sources, techniques, and open research challenges in HAR. The majority of existing research appears to have concentrated on daily living activities, followed by user activities based on individual and group-based activities. However, there is little literature on detecting real-time activities such as suspicious activity, surveillance, and healthcare. A major portion of existing studies has used Closed-Circuit Television (CCTV) videos and Mobile Sensors data. Convolutional Neural Network (CNN), Long short-term memory (LSTM), and Support Vector Machine (SVM) are the most prominent techniques in the literature reviewed that are being utilized for the task of HAR. Lastly, the limitations and open challenges that needed to be addressed are discussed. |
| first_indexed | 2024-03-10T01:16:38Z |
| format | Article |
| id | doaj.art-f25e45ac75ce4d9ab15f73b93789f5dc |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T01:16:38Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-f25e45ac75ce4d9ab15f73b93789f5dc2023-11-23T14:08:55ZengMDPI AGSensors1424-82202022-08-012217646310.3390/s22176463Human Activity Recognition: Review, Taxonomy and Open ChallengesMuhammad Haseeb Arshad0Muhammad Bilal1Abdullah Gani2Department of Computer Science, National University of Computer and Emerging Sciences, Chiniot-Faisalabad Campus, Chiniot 35400, PakistanDepartment of Software Engineering, National University of Computer and Emerging Sciences, Chiniot-Faisalabad Campus, Chiniot 35400, PakistanFaculty of Computing and Informatics, University Malaysia Sabah, Kota Kinabalu 88400, Sabah, MalaysiaNowadays, Human Activity Recognition (HAR) is being widely used in a variety of domains, and vision and sensor-based data enable cutting-edge technologies to detect, recognize, and monitor human activities. Several reviews and surveys on HAR have already been published, but due to the constantly growing literature, the status of HAR literature needed to be updated. Hence, this review aims to provide insights on the current state of the literature on HAR published since 2018. The ninety-five articles reviewed in this study are classified to highlight application areas, data sources, techniques, and open research challenges in HAR. The majority of existing research appears to have concentrated on daily living activities, followed by user activities based on individual and group-based activities. However, there is little literature on detecting real-time activities such as suspicious activity, surveillance, and healthcare. A major portion of existing studies has used Closed-Circuit Television (CCTV) videos and Mobile Sensors data. Convolutional Neural Network (CNN), Long short-term memory (LSTM), and Support Vector Machine (SVM) are the most prominent techniques in the literature reviewed that are being utilized for the task of HAR. Lastly, the limitations and open challenges that needed to be addressed are discussed.https://www.mdpi.com/1424-8220/22/17/6463human activity recognitioncomputer visionCCTVsensorsmachine learning |
| spellingShingle | Muhammad Haseeb Arshad Muhammad Bilal Abdullah Gani Human Activity Recognition: Review, Taxonomy and Open Challenges Sensors human activity recognition computer vision CCTV sensors machine learning |
| title | Human Activity Recognition: Review, Taxonomy and Open Challenges |
| title_full | Human Activity Recognition: Review, Taxonomy and Open Challenges |
| title_fullStr | Human Activity Recognition: Review, Taxonomy and Open Challenges |
| title_full_unstemmed | Human Activity Recognition: Review, Taxonomy and Open Challenges |
| title_short | Human Activity Recognition: Review, Taxonomy and Open Challenges |
| title_sort | human activity recognition review taxonomy and open challenges |
| topic | human activity recognition computer vision CCTV sensors machine learning |
| url | https://www.mdpi.com/1424-8220/22/17/6463 |
| work_keys_str_mv | AT muhammadhaseebarshad humanactivityrecognitionreviewtaxonomyandopenchallenges AT muhammadbilal humanactivityrecognitionreviewtaxonomyandopenchallenges AT abdullahgani humanactivityrecognitionreviewtaxonomyandopenchallenges |