Single-Shot Person Re-Identification based on Unsupervised Saliency Information
Fuente:
Redalyc
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Artículo científico |
| Lingua: | en |
| Pubblicazione: |
Universidad de las Ciencias Informáticas
2020
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1876425280844726272 |
|---|---|
| author | Reynolds León Guerra |
| author_facet | Reynolds León Guerra |
| contents | Single-Shot Person Re-Identification based on Unsupervised Saliency Information Reynolds León Guerra Edel B. García Reyes Computación Maps Saliency Features Person re Deep learning Person re-identification task is important in video surveillance to improve security in public place. In recent years there is a lot of investigation about this thematic. However, the performance in these algorithms is affected by different problems in the scenes, for example, complex background, atmospheric conditions, etc. Some methods as deep learning and saliency descriptor have been used to solve these problems in the real world. In this paper, we developed a method based on the combination of convolutional neural network without fine-tuning and a saliency descriptor to weight all the information present into a person image. Feature maps are extracted from the last convolutional layer of a neural network and merged with other salient map obtained in spatial domain. Finally, different features are generated based on color histograms and local binary patterns. To verify the effectiveness of our proposal, the method is validated using VIPeR dataset and compared with others state of the art algorithms. The results shown that our proposal is easy to implement and is comparable with other approach using the Cumulative Matching Characteristic curve. 2020 artículo científico 1994-1536 https://www.redalyc.org/articulo.oa?id=378365833005 https://www.redalyc.org/journal/3783/378365833005/ https://www.redalyc.org/journal/3783/378365833005/html/ https://www.redalyc.org/journal/3783/378365833005/378365833005.epub https://www.redalyc.org/journal/3783/378365833005/movil en http://www.redalyc.org/revista.oa?id=3783 Revista Cubana de Ciencias Informáticas application/pdf Universidad de las Ciencias Informáticas Revista Cubana de Ciencias Informáticas (Cuba) Num.2 Vol.14 |
| format | Artículo científico |
| id | redalyc_378365833005 |
| institution | Redalyc |
| language | en |
| publishDate | 2020 |
| publisher | Universidad de las Ciencias Informáticas |
| spellingShingle | Single-Shot Person Re-Identification based on Unsupervised Saliency Information Reynolds León Guerra Computación Maps Saliency Features Person re Deep learning Single-Shot Person Re-Identification based on Unsupervised Saliency Information Reynolds León Guerra Edel B. García Reyes Computación Maps Saliency Features Person re Deep learning Person re-identification task is important in video surveillance to improve security in public place. In recent years there is a lot of investigation about this thematic. However, the performance in these algorithms is affected by different problems in the scenes, for example, complex background, atmospheric conditions, etc. Some methods as deep learning and saliency descriptor have been used to solve these problems in the real world. In this paper, we developed a method based on the combination of convolutional neural network without fine-tuning and a saliency descriptor to weight all the information present into a person image. Feature maps are extracted from the last convolutional layer of a neural network and merged with other salient map obtained in spatial domain. Finally, different features are generated based on color histograms and local binary patterns. To verify the effectiveness of our proposal, the method is validated using VIPeR dataset and compared with others state of the art algorithms. The results shown that our proposal is easy to implement and is comparable with other approach using the Cumulative Matching Characteristic curve. 2020 artículo científico 1994-1536 https://www.redalyc.org/articulo.oa?id=378365833005 https://www.redalyc.org/journal/3783/378365833005/ https://www.redalyc.org/journal/3783/378365833005/html/ https://www.redalyc.org/journal/3783/378365833005/378365833005.epub https://www.redalyc.org/journal/3783/378365833005/movil en http://www.redalyc.org/revista.oa?id=3783 Revista Cubana de Ciencias Informáticas application/pdf Universidad de las Ciencias Informáticas Revista Cubana de Ciencias Informáticas (Cuba) Num.2 Vol.14 |
| title | Single-Shot Person Re-Identification based on Unsupervised Saliency Information |
| topic | Computación Maps Saliency Features Person re Deep learning |
| url | https://www.redalyc.org/articulo.oa?id=378365833005 https://www.redalyc.org/journal/3783/378365833005/ https://www.redalyc.org/journal/3783/378365833005/html/ https://www.redalyc.org/journal/3783/378365833005/378365833005.epub https://www.redalyc.org/journal/3783/378365833005/movil |