Airport Pavement Snow and Ice State Perception Based on Improved YOLOX-s
Aimed at the lack of awarness of safety and airworthiness state perception ability of airport ice runway and the new demand of interaction of runway surface condition report, a multi-scale feature fusion based ice and snow state perception model of airport runway is proposed. Based on the YOLOX-s mo...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Journal of Shanghai Jiao Tong University
2023-10-01
|
| Series: | Shanghai Jiaotong Daxue xuebao |
| Subjects: | |
| Online Access: | https://xuebao.sjtu.edu.cn/article/2023/1006-2467/1006-2467-57-10-1292.shtml |
| _version_ | 1797643684408197120 |
|---|---|
| author | XING Zhiwei, KAN Ben, LIU Zishuo, LI Biao, LUO Qian |
| author_facet | XING Zhiwei, KAN Ben, LIU Zishuo, LI Biao, LUO Qian |
| author_sort | XING Zhiwei, KAN Ben, LIU Zishuo, LI Biao, LUO Qian |
| collection | DOAJ |
| description | Aimed at the lack of awarness of safety and airworthiness state perception ability of airport ice runway and the new demand of interaction of runway surface condition report, a multi-scale feature fusion based ice and snow state perception model of airport runway is proposed. Based on the YOLOX-s model, first, the global context block (GC block) is introduced into the backbone feature extraction network to obtain more abundant shallow and deep features. Then, the PANet networks in neck are replaced with the bi-directional feature pyramid network (BiFPN) to improve the feature fusion ability. Afterwards, an adaptive spatial feature fusion (ASFF) structure is added to the tail of the enhanced feature extraction network to further enhance the feature fusion effect. Finally, α-EIoU is used to optimize the loss function to improve the convergence speed and accuracy of the model. The experimental results show that the improved YOLOX-s model has an average accuracy of 91.53% in the snow and ice pollutant data set obtained from the runway snow and ice experimental system, which is 4.68% higher than the original YOLOX-s model, and can provide decision-making support for airport runway snow removal operations. |
| first_indexed | 2024-03-11T14:18:28Z |
| format | Article |
| id | doaj.art-b3bff95ec48d43169db104c3d28be5e6 |
| institution | Directory Open Access Journal |
| issn | 1006-2467 |
| language | zho |
| last_indexed | 2024-03-11T14:18:28Z |
| publishDate | 2023-10-01 |
| publisher | Editorial Office of Journal of Shanghai Jiao Tong University |
| record_format | Article |
| series | Shanghai Jiaotong Daxue xuebao |
| spelling | doaj.art-b3bff95ec48d43169db104c3d28be5e62023-11-01T00:32:09ZzhoEditorial Office of Journal of Shanghai Jiao Tong UniversityShanghai Jiaotong Daxue xuebao1006-24672023-10-0157101292130410.16183/j.cnki.jsjtu.2022.303Airport Pavement Snow and Ice State Perception Based on Improved YOLOX-sXING Zhiwei, KAN Ben, LIU Zishuo, LI Biao, LUO Qian01. School of Electronic Information and Automation, Civil Aviation University of China, Tianjin 300300, China;2. AVIC Tianjin Aviation Machinery and Electricity Co., Ltd., Tianjin 300308, China;3. Engineering Technology Research Centre, Second Research Institute of Civil Aviation Administration of China, Chengdu 610041, ChinaAimed at the lack of awarness of safety and airworthiness state perception ability of airport ice runway and the new demand of interaction of runway surface condition report, a multi-scale feature fusion based ice and snow state perception model of airport runway is proposed. Based on the YOLOX-s model, first, the global context block (GC block) is introduced into the backbone feature extraction network to obtain more abundant shallow and deep features. Then, the PANet networks in neck are replaced with the bi-directional feature pyramid network (BiFPN) to improve the feature fusion ability. Afterwards, an adaptive spatial feature fusion (ASFF) structure is added to the tail of the enhanced feature extraction network to further enhance the feature fusion effect. Finally, α-EIoU is used to optimize the loss function to improve the convergence speed and accuracy of the model. The experimental results show that the improved YOLOX-s model has an average accuracy of 91.53% in the snow and ice pollutant data set obtained from the runway snow and ice experimental system, which is 4.68% higher than the original YOLOX-s model, and can provide decision-making support for airport runway snow removal operations.https://xuebao.sjtu.edu.cn/article/2023/1006-2467/1006-2467-57-10-1292.shtmlpavement snow and ice state perceptionyolox-sglobal context block (gc block)bi-directional feature pyramid network (bifpn)adaptive spatial feature fusion (asff)<i>α</i>-eiou loss function |
| spellingShingle | XING Zhiwei, KAN Ben, LIU Zishuo, LI Biao, LUO Qian Airport Pavement Snow and Ice State Perception Based on Improved YOLOX-s Shanghai Jiaotong Daxue xuebao pavement snow and ice state perception yolox-s global context block (gc block) bi-directional feature pyramid network (bifpn) adaptive spatial feature fusion (asff) <i>α</i>-eiou loss function |
| title | Airport Pavement Snow and Ice State Perception Based on Improved YOLOX-s |
| title_full | Airport Pavement Snow and Ice State Perception Based on Improved YOLOX-s |
| title_fullStr | Airport Pavement Snow and Ice State Perception Based on Improved YOLOX-s |
| title_full_unstemmed | Airport Pavement Snow and Ice State Perception Based on Improved YOLOX-s |
| title_short | Airport Pavement Snow and Ice State Perception Based on Improved YOLOX-s |
| title_sort | airport pavement snow and ice state perception based on improved yolox s |
| topic | pavement snow and ice state perception yolox-s global context block (gc block) bi-directional feature pyramid network (bifpn) adaptive spatial feature fusion (asff) <i>α</i>-eiou loss function |
| url | https://xuebao.sjtu.edu.cn/article/2023/1006-2467/1006-2467-57-10-1292.shtml |
| work_keys_str_mv | AT xingzhiweikanbenliuzishuolibiaoluoqian airportpavementsnowandicestateperceptionbasedonimprovedyoloxs |