SWDet: Anchor-Based Object Detector for Solid Waste Detection in Aerial Images
As we all know, waste pollution is one of the most serious environmental issues in the world. Efficient detection of solid waste (SW) in aerial images can improve subsequent waste classification and automatic sorting on the ground. However, traditional methods have some problems, such as poor genera...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2023-01-01
|
Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9935119/ |
_version_ | 1811178392800722944 |
---|---|
author | Liming Zhou Xiaohan Rao Yahui Li Xianyu Zuo Yang Liu Yinghao Lin Yong Yang |
author_facet | Liming Zhou Xiaohan Rao Yahui Li Xianyu Zuo Yang Liu Yinghao Lin Yong Yang |
author_sort | Liming Zhou |
collection | DOAJ |
description | As we all know, waste pollution is one of the most serious environmental issues in the world. Efficient detection of solid waste (SW) in aerial images can improve subsequent waste classification and automatic sorting on the ground. However, traditional methods have some problems, such as poor generalization and limited detection performance. This article presents an anchor-based object detector for solid waste in aerial images (SWDet). Specifically, we construct asymmetric deep aggregation (ADA) network with structurally reparameterized asymmetric blocks to extract waste features with inconspicuous appearance. Besides, considering the waste with blurred boundaries caused by the resolution of aerial images, this article constructs efficient attention fusion pyramid network (EAFPN) to obtain contextual information and multiscale geospatial information via attention fusion. And the model can capture the scattering features of irregular shape waste. In addition, we construct the dataset for solid waste aerial detection (SWAD) by collecting aerial images of SW in Henan Province, China, to validate the effectiveness of our method. Experimental results show that SWDet outperforms most of existing methods for SW detection in aerial images. |
first_indexed | 2024-04-11T06:18:27Z |
format | Article |
id | doaj.art-5daf2acda79445b7b17ec7548cec8f8d |
institution | Directory Open Access Journal |
issn | 2151-1535 |
language | English |
last_indexed | 2024-04-11T06:18:27Z |
publishDate | 2023-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
spelling | doaj.art-5daf2acda79445b7b17ec7548cec8f8d2022-12-22T04:40:59ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352023-01-011630632010.1109/JSTARS.2022.32189589935119SWDet: Anchor-Based Object Detector for Solid Waste Detection in Aerial ImagesLiming Zhou0https://orcid.org/0000-0001-8741-0827Xiaohan Rao1https://orcid.org/0000-0001-5641-9087Yahui Li2https://orcid.org/0000-0002-6807-2970Xianyu Zuo3https://orcid.org/0000-0002-5675-2362Yang Liu4https://orcid.org/0000-0001-7018-646XYinghao Lin5https://orcid.org/0000-0002-5048-3536Yong Yang6https://orcid.org/0000-0003-1156-8497Henan Key Laboratory of Big Data Analysis and Processing, Henan University, Kaifeng, ChinaHenan Key Laboratory of Big Data Analysis and Processing, Henan University, Kaifeng, ChinaHenan Key Laboratory of Big Data Analysis and Processing, Henan University, Kaifeng, ChinaHenan Key Laboratory of Big Data Analysis and Processing, Henan University, Kaifeng, ChinaHenan Province Engineering Research Center of Spatial Information Processing and Shenzhen Research Institute, Henan University, Kaifeng, ChinaHenan Key Laboratory of Big Data Analysis and Processing, Henan University, Kaifeng, ChinaInstitute of Plant Stress Biology, State Key Laboratory of Cotton Biology, Department of Biology, Kaifeng, ChinaAs we all know, waste pollution is one of the most serious environmental issues in the world. Efficient detection of solid waste (SW) in aerial images can improve subsequent waste classification and automatic sorting on the ground. However, traditional methods have some problems, such as poor generalization and limited detection performance. This article presents an anchor-based object detector for solid waste in aerial images (SWDet). Specifically, we construct asymmetric deep aggregation (ADA) network with structurally reparameterized asymmetric blocks to extract waste features with inconspicuous appearance. Besides, considering the waste with blurred boundaries caused by the resolution of aerial images, this article constructs efficient attention fusion pyramid network (EAFPN) to obtain contextual information and multiscale geospatial information via attention fusion. And the model can capture the scattering features of irregular shape waste. In addition, we construct the dataset for solid waste aerial detection (SWAD) by collecting aerial images of SW in Henan Province, China, to validate the effectiveness of our method. Experimental results show that SWDet outperforms most of existing methods for SW detection in aerial images.https://ieeexplore.ieee.org/document/9935119/Asymmetric block (AB)attention fusionremote sensingsolid waste (SW)waste detectionYOLOv5 |
spellingShingle | Liming Zhou Xiaohan Rao Yahui Li Xianyu Zuo Yang Liu Yinghao Lin Yong Yang SWDet: Anchor-Based Object Detector for Solid Waste Detection in Aerial Images IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Asymmetric block (AB) attention fusion remote sensing solid waste (SW) waste detection YOLOv5 |
title | SWDet: Anchor-Based Object Detector for Solid Waste Detection in Aerial Images |
title_full | SWDet: Anchor-Based Object Detector for Solid Waste Detection in Aerial Images |
title_fullStr | SWDet: Anchor-Based Object Detector for Solid Waste Detection in Aerial Images |
title_full_unstemmed | SWDet: Anchor-Based Object Detector for Solid Waste Detection in Aerial Images |
title_short | SWDet: Anchor-Based Object Detector for Solid Waste Detection in Aerial Images |
title_sort | swdet anchor based object detector for solid waste detection in aerial images |
topic | Asymmetric block (AB) attention fusion remote sensing solid waste (SW) waste detection YOLOv5 |
url | https://ieeexplore.ieee.org/document/9935119/ |
work_keys_str_mv | AT limingzhou swdetanchorbasedobjectdetectorforsolidwastedetectioninaerialimages AT xiaohanrao swdetanchorbasedobjectdetectorforsolidwastedetectioninaerialimages AT yahuili swdetanchorbasedobjectdetectorforsolidwastedetectioninaerialimages AT xianyuzuo swdetanchorbasedobjectdetectorforsolidwastedetectioninaerialimages AT yangliu swdetanchorbasedobjectdetectorforsolidwastedetectioninaerialimages AT yinghaolin swdetanchorbasedobjectdetectorforsolidwastedetectioninaerialimages AT yongyang swdetanchorbasedobjectdetectorforsolidwastedetectioninaerialimages |