Infrared Dim and Small Target Detection Based on Background Prediction
Infrared dim and small target detection is a key technology for various detection tasks. However, due to the lack of shape, texture, and other information, it is a challenging task to detect dim and small targets. Recently, since many traditional algorithms ignore the global information of infrared...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/15/3749 |
| _version_ | 1797586117185241088 |
|---|---|
| author | Jiankang Ma Haoran Guo Shenghui Rong Junjie Feng Bo He |
| author_facet | Jiankang Ma Haoran Guo Shenghui Rong Junjie Feng Bo He |
| author_sort | Jiankang Ma |
| collection | DOAJ |
| description | Infrared dim and small target detection is a key technology for various detection tasks. However, due to the lack of shape, texture, and other information, it is a challenging task to detect dim and small targets. Recently, since many traditional algorithms ignore the global information of infrared images, they generate some false alarms in complicated environments. To address this problem, in this paper, a coarse-to-fine deep learning-based method was proposed to detect dim and small targets. Firstly, a coarse-to-fine detection framework integrating deep learning and background prediction was applied for detecting targets. The framework contains a coarse detection module and a fine detection module. In the coarse detection stage, Region Proposal Network (RPN) is employed to generate masks in target candidate regions. Then, to further optimize the result, inpainting is utilized to predict the background using the global semantics of images. In this paper, an inpainting algorithm with a mask-aware dynamic filtering module was incorporated into the fine detection stage to estimate the background of the candidate targets. Finally, compared with existing algorithms, the experimental results indicate that the proposed framework has effective detection capability and robustness for complex surroundings. |
| first_indexed | 2024-03-11T00:17:44Z |
| format | Article |
| id | doaj.art-b930aeee7e9c437eae156ec6dc9adc45 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T00:17:44Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-b930aeee7e9c437eae156ec6dc9adc452023-11-18T23:30:17ZengMDPI AGRemote Sensing2072-42922023-07-011515374910.3390/rs15153749Infrared Dim and Small Target Detection Based on Background PredictionJiankang Ma0Haoran Guo1Shenghui Rong2Junjie Feng3Bo He4Underwater Vehicle Laboratory, School of Information Science and Engineering, Ocean University of China, Qingdao 266000, ChinaUnderwater Vehicle Laboratory, School of Information Science and Engineering, Ocean University of China, Qingdao 266000, ChinaUnderwater Vehicle Laboratory, School of Information Science and Engineering, Ocean University of China, Qingdao 266000, ChinaState Key Laboratory of Safety and Control for Chemicals, SINOPEC Research Institute of Safety Engineering Co., Ltd., 339 Songling Road, Qingdao 266100, ChinaUnderwater Vehicle Laboratory, School of Information Science and Engineering, Ocean University of China, Qingdao 266000, ChinaInfrared dim and small target detection is a key technology for various detection tasks. However, due to the lack of shape, texture, and other information, it is a challenging task to detect dim and small targets. Recently, since many traditional algorithms ignore the global information of infrared images, they generate some false alarms in complicated environments. To address this problem, in this paper, a coarse-to-fine deep learning-based method was proposed to detect dim and small targets. Firstly, a coarse-to-fine detection framework integrating deep learning and background prediction was applied for detecting targets. The framework contains a coarse detection module and a fine detection module. In the coarse detection stage, Region Proposal Network (RPN) is employed to generate masks in target candidate regions. Then, to further optimize the result, inpainting is utilized to predict the background using the global semantics of images. In this paper, an inpainting algorithm with a mask-aware dynamic filtering module was incorporated into the fine detection stage to estimate the background of the candidate targets. Finally, compared with existing algorithms, the experimental results indicate that the proposed framework has effective detection capability and robustness for complex surroundings.https://www.mdpi.com/2072-4292/15/15/3749infrared dim and small target detectionbackground predictionimage inpaintingRegion Proposal Network (RPN) |
| spellingShingle | Jiankang Ma Haoran Guo Shenghui Rong Junjie Feng Bo He Infrared Dim and Small Target Detection Based on Background Prediction Remote Sensing infrared dim and small target detection background prediction image inpainting Region Proposal Network (RPN) |
| title | Infrared Dim and Small Target Detection Based on Background Prediction |
| title_full | Infrared Dim and Small Target Detection Based on Background Prediction |
| title_fullStr | Infrared Dim and Small Target Detection Based on Background Prediction |
| title_full_unstemmed | Infrared Dim and Small Target Detection Based on Background Prediction |
| title_short | Infrared Dim and Small Target Detection Based on Background Prediction |
| title_sort | infrared dim and small target detection based on background prediction |
| topic | infrared dim and small target detection background prediction image inpainting Region Proposal Network (RPN) |
| url | https://www.mdpi.com/2072-4292/15/15/3749 |
| work_keys_str_mv | AT jiankangma infrareddimandsmalltargetdetectionbasedonbackgroundprediction AT haoranguo infrareddimandsmalltargetdetectionbasedonbackgroundprediction AT shenghuirong infrareddimandsmalltargetdetectionbasedonbackgroundprediction AT junjiefeng infrareddimandsmalltargetdetectionbasedonbackgroundprediction AT bohe infrareddimandsmalltargetdetectionbasedonbackgroundprediction |