Human behaviour recognition with mid‐level representations for crowd understanding and analysis
Abstract Crowd understanding and analysis have received increasing attention for couples of decades, and development of human behaviour recognition strongly supports the application of crowd understanding and analysis. Human behaviour recognition usually seeks to automatically analyse ongoing moveme...
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Wiley
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/90e51ef616c14f9a8510351812599a83 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:90e51ef616c14f9a8510351812599a83 |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:90e51ef616c14f9a8510351812599a832021-11-29T03:38:15ZHuman behaviour recognition with mid‐level representations for crowd understanding and analysis1751-96671751-965910.1049/ipr2.12147https://doaj.org/article/90e51ef616c14f9a8510351812599a832021-12-01T00:00:00Zhttps://doi.org/10.1049/ipr2.12147https://doaj.org/toc/1751-9659https://doaj.org/toc/1751-9667Abstract Crowd understanding and analysis have received increasing attention for couples of decades, and development of human behaviour recognition strongly supports the application of crowd understanding and analysis. Human behaviour recognition usually seeks to automatically analyse ongoing movements and actions in different camera views by using various machine learning methodologies in unknown video clips or image sequences. Compared to other data modalities such as documents and images, processing video data demands much higher computational and storage resources. The idea of using middle level semantic concepts to represent human actions from videos is explored and it is argued that these semantic attributes enable the construction of more descriptive methods for human action recognition. The mid‐level attributes, initialized by a cluster processing, are built upon low level features and fully utilize the discrepancies in different action classes, which can capture the importance of each attribute for each action class. In this way, the representation is constructed to be semantically rich and capable of highly discriminative performance even paired with simple linear classifiers. The method is verified on three challenging datasets (KTH, UCF50 and HMDB51), and the experimental results demonstrate that our method achieves better results than the baseline methods on human action recognition.Bangyong SunNianzeng YuanShuying LiSiyuan WuNan WangWileyarticlePhotographyTR1-1050Computer softwareQA76.75-76.765ENIET Image Processing, Vol 15, Iss 14, Pp 3414-3424 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
Photography TR1-1050 Computer software QA76.75-76.765 |
| spellingShingle |
Photography TR1-1050 Computer software QA76.75-76.765 Bangyong Sun Nianzeng Yuan Shuying Li Siyuan Wu Nan Wang Human behaviour recognition with mid‐level representations for crowd understanding and analysis |
| description |
Abstract Crowd understanding and analysis have received increasing attention for couples of decades, and development of human behaviour recognition strongly supports the application of crowd understanding and analysis. Human behaviour recognition usually seeks to automatically analyse ongoing movements and actions in different camera views by using various machine learning methodologies in unknown video clips or image sequences. Compared to other data modalities such as documents and images, processing video data demands much higher computational and storage resources. The idea of using middle level semantic concepts to represent human actions from videos is explored and it is argued that these semantic attributes enable the construction of more descriptive methods for human action recognition. The mid‐level attributes, initialized by a cluster processing, are built upon low level features and fully utilize the discrepancies in different action classes, which can capture the importance of each attribute for each action class. In this way, the representation is constructed to be semantically rich and capable of highly discriminative performance even paired with simple linear classifiers. The method is verified on three challenging datasets (KTH, UCF50 and HMDB51), and the experimental results demonstrate that our method achieves better results than the baseline methods on human action recognition. |
| format |
article |
| author |
Bangyong Sun Nianzeng Yuan Shuying Li Siyuan Wu Nan Wang |
| author_facet |
Bangyong Sun Nianzeng Yuan Shuying Li Siyuan Wu Nan Wang |
| author_sort |
Bangyong Sun |
| title |
Human behaviour recognition with mid‐level representations for crowd understanding and analysis |
| title_short |
Human behaviour recognition with mid‐level representations for crowd understanding and analysis |
| title_full |
Human behaviour recognition with mid‐level representations for crowd understanding and analysis |
| title_fullStr |
Human behaviour recognition with mid‐level representations for crowd understanding and analysis |
| title_full_unstemmed |
Human behaviour recognition with mid‐level representations for crowd understanding and analysis |
| title_sort |
human behaviour recognition with mid‐level representations for crowd understanding and analysis |
| publisher |
Wiley |
| publishDate |
2021 |
| url |
https://doaj.org/article/90e51ef616c14f9a8510351812599a83 |
| work_keys_str_mv |
AT bangyongsun humanbehaviourrecognitionwithmidlevelrepresentationsforcrowdunderstandingandanalysis AT nianzengyuan humanbehaviourrecognitionwithmidlevelrepresentationsforcrowdunderstandingandanalysis AT shuyingli humanbehaviourrecognitionwithmidlevelrepresentationsforcrowdunderstandingandanalysis AT siyuanwu humanbehaviourrecognitionwithmidlevelrepresentationsforcrowdunderstandingandanalysis AT nanwang humanbehaviourrecognitionwithmidlevelrepresentationsforcrowdunderstandingandanalysis |
| _version_ |
1718407659394170880 |