Target Recognition in Infrared Circumferential Scanning System via Deep Convolutional Neural Networks
With an infrared circumferential scanning system (IRCSS), we can realize long-time surveillance over a large field of view. Recognizing targets in the field of view automatically is a crucial component of improving environmental awareness under the trend of informatization, especially in the defense...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/7/1922 |
| _version_ | 1797571985822187520 |
|---|---|
| author | Gao Chen Weihua Wang |
| author_facet | Gao Chen Weihua Wang |
| author_sort | Gao Chen |
| collection | DOAJ |
| description | With an infrared circumferential scanning system (IRCSS), we can realize long-time surveillance over a large field of view. Recognizing targets in the field of view automatically is a crucial component of improving environmental awareness under the trend of informatization, especially in the defense system. Target recognition consists of two subtasks: detection and identification, corresponding to the position and category of the target, respectively. In this study, we propose a deep convolutional neural network (DCNN)-based method to realize the end-to-end target recognition in the IRCSS. Existing DCNN-based methods require a large annotated dataset for training, while public infrared datasets are mostly used for target tracking. Therefore, we build an infrared target recognition dataset to both overcome the shortage of data and enhance the adaptability of the algorithm in various scenes. We then use data augmentation and exploit the optimal cross-domain transfer learning strategy for network training. In this process, we design the smoother L1 as the loss function in bounding box regression for better localization performance. In the experiments, the proposed method achieved 82.7 mAP, accomplishing the end-to-end infrared target recognition with high effectiveness on accuracy. |
| first_indexed | 2024-03-10T20:48:18Z |
| format | Article |
| id | doaj.art-ddb674dfd87a4080b0af891cddd0eb97 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T20:48:18Z |
| publishDate | 2020-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-ddb674dfd87a4080b0af891cddd0eb972023-11-19T20:09:38ZengMDPI AGSensors1424-82202020-03-01207192210.3390/s20071922Target Recognition in Infrared Circumferential Scanning System via Deep Convolutional Neural NetworksGao Chen0Weihua Wang1National Key Laboratory of Science and Technology on ATR, National University of Defense Technology, Changsha 410073, ChinaNational Key Laboratory of Science and Technology on ATR, National University of Defense Technology, Changsha 410073, ChinaWith an infrared circumferential scanning system (IRCSS), we can realize long-time surveillance over a large field of view. Recognizing targets in the field of view automatically is a crucial component of improving environmental awareness under the trend of informatization, especially in the defense system. Target recognition consists of two subtasks: detection and identification, corresponding to the position and category of the target, respectively. In this study, we propose a deep convolutional neural network (DCNN)-based method to realize the end-to-end target recognition in the IRCSS. Existing DCNN-based methods require a large annotated dataset for training, while public infrared datasets are mostly used for target tracking. Therefore, we build an infrared target recognition dataset to both overcome the shortage of data and enhance the adaptability of the algorithm in various scenes. We then use data augmentation and exploit the optimal cross-domain transfer learning strategy for network training. In this process, we design the smoother L1 as the loss function in bounding box regression for better localization performance. In the experiments, the proposed method achieved 82.7 mAP, accomplishing the end-to-end infrared target recognition with high effectiveness on accuracy.https://www.mdpi.com/1424-8220/20/7/1922infrared circumferential scanning systemtarget recognitiondeep convolutional neural networksdata augmentationtransfer learningbounding box regression |
| spellingShingle | Gao Chen Weihua Wang Target Recognition in Infrared Circumferential Scanning System via Deep Convolutional Neural Networks Sensors infrared circumferential scanning system target recognition deep convolutional neural networks data augmentation transfer learning bounding box regression |
| title | Target Recognition in Infrared Circumferential Scanning System via Deep Convolutional Neural Networks |
| title_full | Target Recognition in Infrared Circumferential Scanning System via Deep Convolutional Neural Networks |
| title_fullStr | Target Recognition in Infrared Circumferential Scanning System via Deep Convolutional Neural Networks |
| title_full_unstemmed | Target Recognition in Infrared Circumferential Scanning System via Deep Convolutional Neural Networks |
| title_short | Target Recognition in Infrared Circumferential Scanning System via Deep Convolutional Neural Networks |
| title_sort | target recognition in infrared circumferential scanning system via deep convolutional neural networks |
| topic | infrared circumferential scanning system target recognition deep convolutional neural networks data augmentation transfer learning bounding box regression |
| url | https://www.mdpi.com/1424-8220/20/7/1922 |
| work_keys_str_mv | AT gaochen targetrecognitionininfraredcircumferentialscanningsystemviadeepconvolutionalneuralnetworks AT weihuawang targetrecognitionininfraredcircumferentialscanningsystemviadeepconvolutionalneuralnetworks |