Small Object Detection Algorithm Based on Feature Pyramid-Enhanced Fusion SSD

In order to improve the detection rate of the traditional single-shot multibox detection algorithm in small object detection, a feature-enhanced fusion SSD object detection algorithm based on the pyramid network is proposed. Firstly, the selected multiscale feature layer is merged with the scale-inv...

Full description

Saved in:
Bibliographic Details
Main Authors: Haotian Li, Kezheng Lin, Jingxuan Bai, Ao Li, Jiali Yu
Format: Article
Language:English
Published: Wiley 2019-01-01
Series:Complexity
Online Access:http://dx.doi.org/10.1155/2019/7297960
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832552107894374400
author Haotian Li
Kezheng Lin
Jingxuan Bai
Ao Li
Jiali Yu
author_facet Haotian Li
Kezheng Lin
Jingxuan Bai
Ao Li
Jiali Yu
author_sort Haotian Li
collection DOAJ
description In order to improve the detection rate of the traditional single-shot multibox detection algorithm in small object detection, a feature-enhanced fusion SSD object detection algorithm based on the pyramid network is proposed. Firstly, the selected multiscale feature layer is merged with the scale-invariant convolutional layer through the feature pyramid network structure; at the same time, the multiscale feature map is separately converted into the channel number using the scale-invariant convolution kernel. Then, the obtained two sets of pyramid-shaped feature layers are further feature fused to generate a set of enhanced multiscale feature maps, and the scale-invariant convolution is performed again on these layers. Finally, the obtained layer is used for detection and localization. The final location coordinates and confidence are output after nonmaximum suppression. Experimental results on the Pascal VOC 2007 and 2012 datasets confirm that there is a 8.2% improvement in mAP compared to the original SSD and some existing algorithms.
format Article
id doaj-art-0566763d7e634f0cb39d784aa69a8414
institution Kabale University
issn 1076-2787
1099-0526
language English
publishDate 2019-01-01
publisher Wiley
record_format Article
series Complexity
spelling doaj-art-0566763d7e634f0cb39d784aa69a84142025-02-03T05:59:31ZengWileyComplexity1076-27871099-05262019-01-01201910.1155/2019/72979607297960Small Object Detection Algorithm Based on Feature Pyramid-Enhanced Fusion SSDHaotian Li0Kezheng Lin1Jingxuan Bai2Ao Li3Jiali Yu4School of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080, ChinaSchool of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080, ChinaSchool of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080, ChinaSchool of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080, ChinaState Grid Zhejiang Electric Power Co., Ltd., Research Institute, Hangzhou 310014, ChinaIn order to improve the detection rate of the traditional single-shot multibox detection algorithm in small object detection, a feature-enhanced fusion SSD object detection algorithm based on the pyramid network is proposed. Firstly, the selected multiscale feature layer is merged with the scale-invariant convolutional layer through the feature pyramid network structure; at the same time, the multiscale feature map is separately converted into the channel number using the scale-invariant convolution kernel. Then, the obtained two sets of pyramid-shaped feature layers are further feature fused to generate a set of enhanced multiscale feature maps, and the scale-invariant convolution is performed again on these layers. Finally, the obtained layer is used for detection and localization. The final location coordinates and confidence are output after nonmaximum suppression. Experimental results on the Pascal VOC 2007 and 2012 datasets confirm that there is a 8.2% improvement in mAP compared to the original SSD and some existing algorithms.http://dx.doi.org/10.1155/2019/7297960
spellingShingle Haotian Li
Kezheng Lin
Jingxuan Bai
Ao Li
Jiali Yu
Small Object Detection Algorithm Based on Feature Pyramid-Enhanced Fusion SSD
Complexity
title Small Object Detection Algorithm Based on Feature Pyramid-Enhanced Fusion SSD
title_full Small Object Detection Algorithm Based on Feature Pyramid-Enhanced Fusion SSD
title_fullStr Small Object Detection Algorithm Based on Feature Pyramid-Enhanced Fusion SSD
title_full_unstemmed Small Object Detection Algorithm Based on Feature Pyramid-Enhanced Fusion SSD
title_short Small Object Detection Algorithm Based on Feature Pyramid-Enhanced Fusion SSD
title_sort small object detection algorithm based on feature pyramid enhanced fusion ssd
url http://dx.doi.org/10.1155/2019/7297960
work_keys_str_mv AT haotianli smallobjectdetectionalgorithmbasedonfeaturepyramidenhancedfusionssd
AT kezhenglin smallobjectdetectionalgorithmbasedonfeaturepyramidenhancedfusionssd
AT jingxuanbai smallobjectdetectionalgorithmbasedonfeaturepyramidenhancedfusionssd
AT aoli smallobjectdetectionalgorithmbasedonfeaturepyramidenhancedfusionssd
AT jialiyu smallobjectdetectionalgorithmbasedonfeaturepyramidenhancedfusionssd