Research on extraction and reproduction of deformation camouflage spot based on generative adversarial network model
The method of describing deformation camouflage spots based on feature space has some shortcomings, such as inaccurate description and difficult reproduction. Depending on the strong fitting ability of the generative adversarial network model, the distribution of deformation camouflage spot pattern...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2020-06-01
|
| Series: | Defence Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2214914719305367 |
| _version_ | 1831588571476131840 |
|---|---|
| author | Xin Yang Wei-dong Xu Qi Jia Ling Li Wan-nian Zhu Ji-yao Tian Hao Xu |
| author_facet | Xin Yang Wei-dong Xu Qi Jia Ling Li Wan-nian Zhu Ji-yao Tian Hao Xu |
| author_sort | Xin Yang |
| collection | DOAJ |
| description | The method of describing deformation camouflage spots based on feature space has some shortcomings, such as inaccurate description and difficult reproduction. Depending on the strong fitting ability of the generative adversarial network model, the distribution of deformation camouflage spot pattern can be directly fitted, thus simplifying the process of spot extraction and reproduction. The requirements of background spot extraction are analyzed theoretically. The calculation formula of limiting the range of image spot pixels is given and two kinds of spot data sets, forestland and snowfield, are established. Spot feature is decomposed into shape, size and color features, and a GAN (Generative Adversarial Network) framework is established. The effects of different loss functions on network training results are analyzed in the experiment. In the meantime, when the input dimension of generator network is 128, the balance between sample diversity and quality can be achieved. The effects of sample generation are investigated in two aspects. Subjectively, the probability of the generated spots being distinguished in the background is counted, and the results are all less than 20% and mostly close to zero. Objectively, the features of the spot shape are calculated and the independent sample T-test is applied to verify that the features are from the same distribution, and all the P-Values are much higher than 0.05. Both subjective and objective methods prove that the spots generated by this method are similar to the background spots. The proposed method can directly generate the desired camouflage pattern spots, which provides a new technical method for the deformation camouflage pattern design and camouflage effect evaluation. |
| first_indexed | 2024-12-17T22:15:39Z |
| format | Article |
| id | doaj.art-4910ce6260c0411aa656b1f123ba38ed |
| institution | Directory Open Access Journal |
| issn | 2214-9147 |
| language | English |
| last_indexed | 2024-12-17T22:15:39Z |
| publishDate | 2020-06-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | Defence Technology |
| spelling | doaj.art-4910ce6260c0411aa656b1f123ba38ed2022-12-21T21:30:36ZengKeAi Communications Co., Ltd.Defence Technology2214-91472020-06-01163555563Research on extraction and reproduction of deformation camouflage spot based on generative adversarial network modelXin Yang0Wei-dong Xu1Qi Jia2Ling Li3Wan-nian Zhu4Ji-yao Tian5Hao Xu6National Key Laboratory of Lightning Protection and Electromagnetic Camouflage, Amy Engineering University, Nanjing, Jiangsu, 210007, China; Corresponding author.National Key Laboratory of Lightning Protection and Electromagnetic Camouflage, Amy Engineering University, Nanjing, Jiangsu, 210007, ChinaNational Key Laboratory of Lightning Protection and Electromagnetic Camouflage, Amy Engineering University, Nanjing, Jiangsu, 210007, ChinaNational Key Laboratory of Lightning Protection and Electromagnetic Camouflage, Amy Engineering University, Nanjing, Jiangsu, 210007, ChinaTeaching and Research Office of Camouflage in Training Center, Army Engineering University, Xuzhou, Jiangsu, 221004, ChinaNational Key Laboratory of Lightning Protection and Electromagnetic Camouflage, Amy Engineering University, Nanjing, Jiangsu, 210007, ChinaTeaching and Research Office of Camouflage in Training Center, Army Engineering University, Xuzhou, Jiangsu, 221004, ChinaThe method of describing deformation camouflage spots based on feature space has some shortcomings, such as inaccurate description and difficult reproduction. Depending on the strong fitting ability of the generative adversarial network model, the distribution of deformation camouflage spot pattern can be directly fitted, thus simplifying the process of spot extraction and reproduction. The requirements of background spot extraction are analyzed theoretically. The calculation formula of limiting the range of image spot pixels is given and two kinds of spot data sets, forestland and snowfield, are established. Spot feature is decomposed into shape, size and color features, and a GAN (Generative Adversarial Network) framework is established. The effects of different loss functions on network training results are analyzed in the experiment. In the meantime, when the input dimension of generator network is 128, the balance between sample diversity and quality can be achieved. The effects of sample generation are investigated in two aspects. Subjectively, the probability of the generated spots being distinguished in the background is counted, and the results are all less than 20% and mostly close to zero. Objectively, the features of the spot shape are calculated and the independent sample T-test is applied to verify that the features are from the same distribution, and all the P-Values are much higher than 0.05. Both subjective and objective methods prove that the spots generated by this method are similar to the background spots. The proposed method can directly generate the desired camouflage pattern spots, which provides a new technical method for the deformation camouflage pattern design and camouflage effect evaluation.http://www.sciencedirect.com/science/article/pii/S2214914719305367Deformation camouflageGenerative adversarial networkSpot featureShape description |
| spellingShingle | Xin Yang Wei-dong Xu Qi Jia Ling Li Wan-nian Zhu Ji-yao Tian Hao Xu Research on extraction and reproduction of deformation camouflage spot based on generative adversarial network model Defence Technology Deformation camouflage Generative adversarial network Spot feature Shape description |
| title | Research on extraction and reproduction of deformation camouflage spot based on generative adversarial network model |
| title_full | Research on extraction and reproduction of deformation camouflage spot based on generative adversarial network model |
| title_fullStr | Research on extraction and reproduction of deformation camouflage spot based on generative adversarial network model |
| title_full_unstemmed | Research on extraction and reproduction of deformation camouflage spot based on generative adversarial network model |
| title_short | Research on extraction and reproduction of deformation camouflage spot based on generative adversarial network model |
| title_sort | research on extraction and reproduction of deformation camouflage spot based on generative adversarial network model |
| topic | Deformation camouflage Generative adversarial network Spot feature Shape description |
| url | http://www.sciencedirect.com/science/article/pii/S2214914719305367 |
| work_keys_str_mv | AT xinyang researchonextractionandreproductionofdeformationcamouflagespotbasedongenerativeadversarialnetworkmodel AT weidongxu researchonextractionandreproductionofdeformationcamouflagespotbasedongenerativeadversarialnetworkmodel AT qijia researchonextractionandreproductionofdeformationcamouflagespotbasedongenerativeadversarialnetworkmodel AT lingli researchonextractionandreproductionofdeformationcamouflagespotbasedongenerativeadversarialnetworkmodel AT wannianzhu researchonextractionandreproductionofdeformationcamouflagespotbasedongenerativeadversarialnetworkmodel AT jiyaotian researchonextractionandreproductionofdeformationcamouflagespotbasedongenerativeadversarialnetworkmodel AT haoxu researchonextractionandreproductionofdeformationcamouflagespotbasedongenerativeadversarialnetworkmodel |