Cargando…
Centered Multi-Task Generative Adversarial Network for Small Object Detection
Despite the breakthroughs in accuracy and efficiency of object detection using deep neural networks, the performance of small object detection is far from satisfactory. Gaze estimation has developed significantly due to the development of visual sensors. Combining object detection with gaze estimati...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8347084/ https://www.ncbi.nlm.nih.gov/pubmed/34372431 http://dx.doi.org/10.3390/s21155194 |
_version_ | 1783734999380393984 |
---|---|
author | Wang, Hongfeng Wang, Jianzhong Bai, Kemeng Sun, Yong |
author_facet | Wang, Hongfeng Wang, Jianzhong Bai, Kemeng Sun, Yong |
author_sort | Wang, Hongfeng |
collection | PubMed |
description | Despite the breakthroughs in accuracy and efficiency of object detection using deep neural networks, the performance of small object detection is far from satisfactory. Gaze estimation has developed significantly due to the development of visual sensors. Combining object detection with gaze estimation can significantly improve the performance of small object detection. This paper presents a centered multi-task generative adversarial network (CMTGAN), which combines small object detection and gaze estimation. To achieve this, we propose a generative adversarial network (GAN) capable of image super-resolution and two-stage small object detection. We exploit a generator in CMTGAN for image super-resolution and a discriminator for object detection. We introduce an artificial texture loss into the generator to retain the original feature of small objects. We also use a centered mask in the generator to make the network focus on the central part of images where small objects are more likely to appear in our method. We propose a discriminator with detection loss for two-stage small object detection, which can be adapted to other GANs for object detection. Compared with existing interpolation methods, the super-resolution images generated by CMTGAN are more explicit and contain more information. Experiments show that our method exhibits a better detection performance than mainstream methods. |
format | Online Article Text |
id | pubmed-8347084 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-83470842021-08-08 Centered Multi-Task Generative Adversarial Network for Small Object Detection Wang, Hongfeng Wang, Jianzhong Bai, Kemeng Sun, Yong Sensors (Basel) Article Despite the breakthroughs in accuracy and efficiency of object detection using deep neural networks, the performance of small object detection is far from satisfactory. Gaze estimation has developed significantly due to the development of visual sensors. Combining object detection with gaze estimation can significantly improve the performance of small object detection. This paper presents a centered multi-task generative adversarial network (CMTGAN), which combines small object detection and gaze estimation. To achieve this, we propose a generative adversarial network (GAN) capable of image super-resolution and two-stage small object detection. We exploit a generator in CMTGAN for image super-resolution and a discriminator for object detection. We introduce an artificial texture loss into the generator to retain the original feature of small objects. We also use a centered mask in the generator to make the network focus on the central part of images where small objects are more likely to appear in our method. We propose a discriminator with detection loss for two-stage small object detection, which can be adapted to other GANs for object detection. Compared with existing interpolation methods, the super-resolution images generated by CMTGAN are more explicit and contain more information. Experiments show that our method exhibits a better detection performance than mainstream methods. MDPI 2021-07-31 /pmc/articles/PMC8347084/ /pubmed/34372431 http://dx.doi.org/10.3390/s21155194 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Wang, Hongfeng Wang, Jianzhong Bai, Kemeng Sun, Yong Centered Multi-Task Generative Adversarial Network for Small Object Detection |
title | Centered Multi-Task Generative Adversarial Network for Small Object Detection |
title_full | Centered Multi-Task Generative Adversarial Network for Small Object Detection |
title_fullStr | Centered Multi-Task Generative Adversarial Network for Small Object Detection |
title_full_unstemmed | Centered Multi-Task Generative Adversarial Network for Small Object Detection |
title_short | Centered Multi-Task Generative Adversarial Network for Small Object Detection |
title_sort | centered multi-task generative adversarial network for small object detection |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8347084/ https://www.ncbi.nlm.nih.gov/pubmed/34372431 http://dx.doi.org/10.3390/s21155194 |
work_keys_str_mv | AT wanghongfeng centeredmultitaskgenerativeadversarialnetworkforsmallobjectdetection AT wangjianzhong centeredmultitaskgenerativeadversarialnetworkforsmallobjectdetection AT baikemeng centeredmultitaskgenerativeadversarialnetworkforsmallobjectdetection AT sunyong centeredmultitaskgenerativeadversarialnetworkforsmallobjectdetection |