Human Behavior Analysis: A Survey on Action Recognition
The visual recognition and understanding of human actions remain an active research domain of computer vision, being the scope of various research works over the last two decades. The problem is challenging due to its many interpersonal variations in appearance and motion dynamics between humans, wi...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-09-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/18/8324 |
| _version_ | 1797520405148205056 |
|---|---|
| author | Bruno Degardin Hugo Proença |
| author_facet | Bruno Degardin Hugo Proença |
| author_sort | Bruno Degardin |
| collection | DOAJ |
| description | The visual recognition and understanding of human actions remain an active research domain of computer vision, being the scope of various research works over the last two decades. The problem is challenging due to its many interpersonal variations in appearance and motion dynamics between humans, without forgetting the environmental heterogeneity between different video images. This complexity splits the problem into two major categories: action classification, recognising the action being performed in the scene, and spatiotemporal action localisation, concerning recognising multiple localised human actions present in the scene. Previous surveys mainly focus on the evolution of this field, from handcrafted features to deep learning architectures. However, this survey presents an overview of both categories and respective evolution within each one, the guidelines that should be followed and the current benchmarks employed for performance comparison between the state-of-the-art methods. |
| first_indexed | 2024-03-10T07:56:18Z |
| format | Article |
| id | doaj.art-a3deec5ff5f94d3289c2117e202781dd |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T07:56:18Z |
| publishDate | 2021-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-a3deec5ff5f94d3289c2117e202781dd2023-11-22T11:50:55ZengMDPI AGApplied Sciences2076-34172021-09-011118832410.3390/app11188324Human Behavior Analysis: A Survey on Action RecognitionBruno Degardin0Hugo Proença1IT-Instituto de Telecomunicações, University of Beira Interior, 6201-001 Covilhã, PortugalIT-Instituto de Telecomunicações, University of Beira Interior, 6201-001 Covilhã, PortugalThe visual recognition and understanding of human actions remain an active research domain of computer vision, being the scope of various research works over the last two decades. The problem is challenging due to its many interpersonal variations in appearance and motion dynamics between humans, without forgetting the environmental heterogeneity between different video images. This complexity splits the problem into two major categories: action classification, recognising the action being performed in the scene, and spatiotemporal action localisation, concerning recognising multiple localised human actions present in the scene. Previous surveys mainly focus on the evolution of this field, from handcrafted features to deep learning architectures. However, this survey presents an overview of both categories and respective evolution within each one, the guidelines that should be followed and the current benchmarks employed for performance comparison between the state-of-the-art methods.https://www.mdpi.com/2076-3417/11/18/8324action detectionbiometricshuman action recognitionhuman activity analysis |
| spellingShingle | Bruno Degardin Hugo Proença Human Behavior Analysis: A Survey on Action Recognition Applied Sciences action detection biometrics human action recognition human activity analysis |
| title | Human Behavior Analysis: A Survey on Action Recognition |
| title_full | Human Behavior Analysis: A Survey on Action Recognition |
| title_fullStr | Human Behavior Analysis: A Survey on Action Recognition |
| title_full_unstemmed | Human Behavior Analysis: A Survey on Action Recognition |
| title_short | Human Behavior Analysis: A Survey on Action Recognition |
| title_sort | human behavior analysis a survey on action recognition |
| topic | action detection biometrics human action recognition human activity analysis |
| url | https://www.mdpi.com/2076-3417/11/18/8324 |
| work_keys_str_mv | AT brunodegardin humanbehavioranalysisasurveyonactionrecognition AT hugoproenca humanbehavioranalysisasurveyonactionrecognition |