Double Weight-Based SAR and Infrared Sensor Fusion for Automatic Ground Target Recognition with Deep Learning
This paper presents a novel double weight-based synthetic aperture radar (SAR) and infrared (IR) sensor fusion method (DW-SIF) for automatic ground target recognition (ATR). IR-based ATR can provide accurate recognition because of its high image resolution but it is affected by the weather condition...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2072-4292/10/1/72 |
| _version_ | 1828424982707830784 |
|---|---|
| author | Sungho Kim Woo-Jin Song So-Hyun Kim |
| author_facet | Sungho Kim Woo-Jin Song So-Hyun Kim |
| author_sort | Sungho Kim |
| collection | DOAJ |
| description | This paper presents a novel double weight-based synthetic aperture radar (SAR) and infrared (IR) sensor fusion method (DW-SIF) for automatic ground target recognition (ATR). IR-based ATR can provide accurate recognition because of its high image resolution but it is affected by the weather conditions. On the other hand, SAR-based ATR shows a low recognition rate due to the noisy low resolution but can provide consistent performance regardless of the weather conditions. The fusion of an active sensor (SAR) and a passive sensor (IR) can lead to upgraded performance. This paper proposes a doubly weighted neural network fusion scheme at the decision level. The first weight ( α ) can measure the offline sensor confidence per target category based on the classification rate for an evaluation set. The second weight ( β ) can measure the online sensor reliability based on the score distribution for a test target image. The LeNet architecture-based deep convolution network (14 layers) is used as an individual classifier. Doubly weighted sensor scores are fused by two types of fusion schemes, such as the sum-based linear fusion scheme ( α β -sum) and neural network-based nonlinear fusion scheme ( α β -NN). The experimental results confirmed the proposed linear fusion method ( α β -sum) to have the best performance among the linear fusion schemes available (SAR-CNN, IR-CNN, α -sum, β -sum, α β -sum, and Bayesian fusion). In addition, the proposed nonlinear fusion method ( α β -NN) showed superior target recognition performance to linear fusion on the OKTAL-SE-based synthetic database. |
| first_indexed | 2024-12-10T16:24:44Z |
| format | Article |
| id | doaj.art-4ea9d421276c4613b1fcb09921a46c92 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-12-10T16:24:44Z |
| publishDate | 2018-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-4ea9d421276c4613b1fcb09921a46c922022-12-22T01:41:42ZengMDPI AGRemote Sensing2072-42922018-01-011017210.3390/rs10010072rs10010072Double Weight-Based SAR and Infrared Sensor Fusion for Automatic Ground Target Recognition with Deep LearningSungho Kim0Woo-Jin Song1So-Hyun Kim2Department of Electronic Engineering, Yeungnam University, 280 Daehak-Ro, Gyeongsan, Gyeongbuk 38541, KoreaDepartment of Electrical Engineering, Pohang University of Science and Technology, Pohang, Gyeongbuk 37673, KoreaAgency for Defense Development, 111 Sunam-dong, Daejeon 34186, KoreaThis paper presents a novel double weight-based synthetic aperture radar (SAR) and infrared (IR) sensor fusion method (DW-SIF) for automatic ground target recognition (ATR). IR-based ATR can provide accurate recognition because of its high image resolution but it is affected by the weather conditions. On the other hand, SAR-based ATR shows a low recognition rate due to the noisy low resolution but can provide consistent performance regardless of the weather conditions. The fusion of an active sensor (SAR) and a passive sensor (IR) can lead to upgraded performance. This paper proposes a doubly weighted neural network fusion scheme at the decision level. The first weight ( α ) can measure the offline sensor confidence per target category based on the classification rate for an evaluation set. The second weight ( β ) can measure the online sensor reliability based on the score distribution for a test target image. The LeNet architecture-based deep convolution network (14 layers) is used as an individual classifier. Doubly weighted sensor scores are fused by two types of fusion schemes, such as the sum-based linear fusion scheme ( α β -sum) and neural network-based nonlinear fusion scheme ( α β -NN). The experimental results confirmed the proposed linear fusion method ( α β -sum) to have the best performance among the linear fusion schemes available (SAR-CNN, IR-CNN, α -sum, β -sum, α β -sum, and Bayesian fusion). In addition, the proposed nonlinear fusion method ( α β -NN) showed superior target recognition performance to linear fusion on the OKTAL-SE-based synthetic database.http://www.mdpi.com/2072-4292/10/1/72SARIRfusiondouble weightslinearnonlineardeep learningOKTAL-SE |
| spellingShingle | Sungho Kim Woo-Jin Song So-Hyun Kim Double Weight-Based SAR and Infrared Sensor Fusion for Automatic Ground Target Recognition with Deep Learning Remote Sensing SAR IR fusion double weights linear nonlinear deep learning OKTAL-SE |
| title | Double Weight-Based SAR and Infrared Sensor Fusion for Automatic Ground Target Recognition with Deep Learning |
| title_full | Double Weight-Based SAR and Infrared Sensor Fusion for Automatic Ground Target Recognition with Deep Learning |
| title_fullStr | Double Weight-Based SAR and Infrared Sensor Fusion for Automatic Ground Target Recognition with Deep Learning |
| title_full_unstemmed | Double Weight-Based SAR and Infrared Sensor Fusion for Automatic Ground Target Recognition with Deep Learning |
| title_short | Double Weight-Based SAR and Infrared Sensor Fusion for Automatic Ground Target Recognition with Deep Learning |
| title_sort | double weight based sar and infrared sensor fusion for automatic ground target recognition with deep learning |
| topic | SAR IR fusion double weights linear nonlinear deep learning OKTAL-SE |
| url | http://www.mdpi.com/2072-4292/10/1/72 |
| work_keys_str_mv | AT sunghokim doubleweightbasedsarandinfraredsensorfusionforautomaticgroundtargetrecognitionwithdeeplearning AT woojinsong doubleweightbasedsarandinfraredsensorfusionforautomaticgroundtargetrecognitionwithdeeplearning AT sohyunkim doubleweightbasedsarandinfraredsensorfusionforautomaticgroundtargetrecognitionwithdeeplearning |