Airport small object detection based on feature enhancement
Abstract Video object detection is essential for airport surface surveillance, but the objects on the scene are mostly small objects with low resolution, they have no obvious feature information. Due to the scale differences of the objects and the fixed receptive field on the feature maps, detectors...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-09-01
|
| Series: | IET Image Processing |
| Online Access: | https://doi.org/10.1049/ipr2.12387 |
| _version_ | 1818010030752923648 |
|---|---|
| author | Xuan Zhu Binbin Liang Daoyong Fu Guoxin Huang Fan Yang Wei Li |
| author_facet | Xuan Zhu Binbin Liang Daoyong Fu Guoxin Huang Fan Yang Wei Li |
| author_sort | Xuan Zhu |
| collection | DOAJ |
| description | Abstract Video object detection is essential for airport surface surveillance, but the objects on the scene are mostly small objects with low resolution, they have no obvious feature information. Due to the scale differences of the objects and the fixed receptive field on the feature maps, detectors cannot model multi‐scale context information and cover all objects. In addition, although the video detection algorithm can be used as a method to solve the problem of small object detection, the temporal feature fusion method of current video detection is very dependent on the quality of a single feature map. Therefore, this paper aims to enhance the features of small objects of a single image. First, an attentional multi‐scale feature fusion enhancement (A‐MSFFE) network is built on the memory‐enhanced global‐local aggregation (MEGA) to supplement semantic and spatial information of small objects. Then, a context feature enhancement (CFE) module is designed for obtaining different receptive fields through different dilated convolutions. Meanwhile, a video detection dataset about the airport is established. Finally, the experimental results show that the proposed method can improve the detection accuracies of small objects and outperform other state‐of‐the‐art video object detection algorithms in self‐built airport dataset. |
| first_indexed | 2024-04-14T05:50:15Z |
| format | Article |
| id | doaj.art-442dccb50364456ebdf95fb288cc1844 |
| institution | Directory Open Access Journal |
| issn | 1751-9659 1751-9667 |
| language | English |
| last_indexed | 2024-04-14T05:50:15Z |
| publishDate | 2022-09-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Image Processing |
| spelling | doaj.art-442dccb50364456ebdf95fb288cc18442022-12-22T02:09:08ZengWileyIET Image Processing1751-96591751-96672022-09-0116112863287410.1049/ipr2.12387Airport small object detection based on feature enhancementXuan Zhu0Binbin Liang1Daoyong Fu2Guoxin Huang3Fan Yang4Wei Li5School of Aeronautics and Astronautics Sichuan University Chengdu ChinaSchool of Aeronautics and Astronautics Sichuan University Chengdu ChinaSchool of Aeronautics and Astronautics Sichuan University Chengdu ChinaCollege of Computer Science Sichuan University Chengdu ChinaSchool of Aeronautics and Astronautics Sichuan University Chengdu ChinaSchool of Aeronautics and Astronautics Sichuan University Chengdu ChinaAbstract Video object detection is essential for airport surface surveillance, but the objects on the scene are mostly small objects with low resolution, they have no obvious feature information. Due to the scale differences of the objects and the fixed receptive field on the feature maps, detectors cannot model multi‐scale context information and cover all objects. In addition, although the video detection algorithm can be used as a method to solve the problem of small object detection, the temporal feature fusion method of current video detection is very dependent on the quality of a single feature map. Therefore, this paper aims to enhance the features of small objects of a single image. First, an attentional multi‐scale feature fusion enhancement (A‐MSFFE) network is built on the memory‐enhanced global‐local aggregation (MEGA) to supplement semantic and spatial information of small objects. Then, a context feature enhancement (CFE) module is designed for obtaining different receptive fields through different dilated convolutions. Meanwhile, a video detection dataset about the airport is established. Finally, the experimental results show that the proposed method can improve the detection accuracies of small objects and outperform other state‐of‐the‐art video object detection algorithms in self‐built airport dataset.https://doi.org/10.1049/ipr2.12387 |
| spellingShingle | Xuan Zhu Binbin Liang Daoyong Fu Guoxin Huang Fan Yang Wei Li Airport small object detection based on feature enhancement IET Image Processing |
| title | Airport small object detection based on feature enhancement |
| title_full | Airport small object detection based on feature enhancement |
| title_fullStr | Airport small object detection based on feature enhancement |
| title_full_unstemmed | Airport small object detection based on feature enhancement |
| title_short | Airport small object detection based on feature enhancement |
| title_sort | airport small object detection based on feature enhancement |
| url | https://doi.org/10.1049/ipr2.12387 |
| work_keys_str_mv | AT xuanzhu airportsmallobjectdetectionbasedonfeatureenhancement AT binbinliang airportsmallobjectdetectionbasedonfeatureenhancement AT daoyongfu airportsmallobjectdetectionbasedonfeatureenhancement AT guoxinhuang airportsmallobjectdetectionbasedonfeatureenhancement AT fanyang airportsmallobjectdetectionbasedonfeatureenhancement AT weili airportsmallobjectdetectionbasedonfeatureenhancement |