GCT-VAE-GAN: An Image Enhancement Network for Low-Light Cattle Farm Scenes by Integrating Fusion Gate Transformation Mechanism and Variational Autoencoder GAN
In the context of cattle farm environments, intricate environmental interferences have presented challenges that impede seamless data acquisition. This paper introduces a novel approach, the integration of a fusion gate transformation mechanism and a variational autoencoder GAN, which we term GCT-VA...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10302291/ |
| _version_ | 1797617696704036864 |
|---|---|
| author | Chengchao Wang Guohong Gao Jianping Wang Yingying Lv Qian Li Zhiyu Li Xueyan Zhang Haoyu Wu |
| author_facet | Chengchao Wang Guohong Gao Jianping Wang Yingying Lv Qian Li Zhiyu Li Xueyan Zhang Haoyu Wu |
| author_sort | Chengchao Wang |
| collection | DOAJ |
| description | In the context of cattle farm environments, intricate environmental interferences have presented challenges that impede seamless data acquisition. This paper introduces a novel approach, the integration of a fusion gate transformation mechanism and a variational autoencoder GAN, which we term GCT-VAE-GAN, aimed at enhancing low-light images from cattle farm settings. Initially, our approach involves the design of an encoding network tasked with augmenting the original images. Subsequently, we advance our methodology by formulating a generative network to effectively address the challenges of image diversification and poor image quality. Notably, the inclusion of an attention mechanism block within the FFN layer facilitates the fusion of these extracted features, resulting in the generation of high-quality images. Furthermore, to achieve proficient image discrimination, we implement a dual-discriminator structured discriminative network for the conclusive image discrimination task. The culmination of our approach involves the formulation of a comprehensive joint loss function, thereby constituting the core of the model’s loss module. Moreover, through comparative experiments, we aptly demonstrate the remarkable superiority of the GCT-VAE-GAN approach. The conducted experiments reveal the model’s consistent performance and resilience under varying illumination scenarios. The outcomes of our study underscore its significant relevance in elevating the quality of low-light images within cattle farm contexts. Furthermore, our approach exhibits the potential to enhance the efficacy of computer vision tasks, signifying a notable stride toward improved agricultural imaging techniques. |
| first_indexed | 2024-03-11T07:58:31Z |
| format | Article |
| id | doaj.art-2b818341d0644f27b1d95d3ba6507a5d |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-11T07:58:31Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-2b818341d0644f27b1d95d3ba6507a5d2023-11-17T00:00:54ZengIEEEIEEE Access2169-35362023-01-011112665012666010.1109/ACCESS.2023.332892310302291GCT-VAE-GAN: An Image Enhancement Network for Low-Light Cattle Farm Scenes by Integrating Fusion Gate Transformation Mechanism and Variational Autoencoder GANChengchao Wang0Guohong Gao1https://orcid.org/0000-0001-6923-7178Jianping Wang2Yingying Lv3Qian Li4Zhiyu Li5Xueyan Zhang6Haoyu Wu7Henan Institute of Science and Technology, Xinxiang, ChinaHenan Institute of Science and Technology, Xinxiang, ChinaHenan Institute of Science and Technology, Xinxiang, ChinaHenan Institute of Science and Technology, Xinxiang, ChinaHenan Institute of Science and Technology, Xinxiang, ChinaHenan Institute of Science and Technology, Xinxiang, ChinaHenan Institute of Science and Technology, Xinxiang, ChinaWenzhou University, Wenzhou, ChinaIn the context of cattle farm environments, intricate environmental interferences have presented challenges that impede seamless data acquisition. This paper introduces a novel approach, the integration of a fusion gate transformation mechanism and a variational autoencoder GAN, which we term GCT-VAE-GAN, aimed at enhancing low-light images from cattle farm settings. Initially, our approach involves the design of an encoding network tasked with augmenting the original images. Subsequently, we advance our methodology by formulating a generative network to effectively address the challenges of image diversification and poor image quality. Notably, the inclusion of an attention mechanism block within the FFN layer facilitates the fusion of these extracted features, resulting in the generation of high-quality images. Furthermore, to achieve proficient image discrimination, we implement a dual-discriminator structured discriminative network for the conclusive image discrimination task. The culmination of our approach involves the formulation of a comprehensive joint loss function, thereby constituting the core of the model’s loss module. Moreover, through comparative experiments, we aptly demonstrate the remarkable superiority of the GCT-VAE-GAN approach. The conducted experiments reveal the model’s consistent performance and resilience under varying illumination scenarios. The outcomes of our study underscore its significant relevance in elevating the quality of low-light images within cattle farm contexts. Furthermore, our approach exhibits the potential to enhance the efficacy of computer vision tasks, signifying a notable stride toward improved agricultural imaging techniques.https://ieeexplore.ieee.org/document/10302291/Low-light image enhancementGANVAEquality evaluation |
| spellingShingle | Chengchao Wang Guohong Gao Jianping Wang Yingying Lv Qian Li Zhiyu Li Xueyan Zhang Haoyu Wu GCT-VAE-GAN: An Image Enhancement Network for Low-Light Cattle Farm Scenes by Integrating Fusion Gate Transformation Mechanism and Variational Autoencoder GAN IEEE Access Low-light image enhancement GAN VAE quality evaluation |
| title | GCT-VAE-GAN: An Image Enhancement Network for Low-Light Cattle Farm Scenes by Integrating Fusion Gate Transformation Mechanism and Variational Autoencoder GAN |
| title_full | GCT-VAE-GAN: An Image Enhancement Network for Low-Light Cattle Farm Scenes by Integrating Fusion Gate Transformation Mechanism and Variational Autoencoder GAN |
| title_fullStr | GCT-VAE-GAN: An Image Enhancement Network for Low-Light Cattle Farm Scenes by Integrating Fusion Gate Transformation Mechanism and Variational Autoencoder GAN |
| title_full_unstemmed | GCT-VAE-GAN: An Image Enhancement Network for Low-Light Cattle Farm Scenes by Integrating Fusion Gate Transformation Mechanism and Variational Autoencoder GAN |
| title_short | GCT-VAE-GAN: An Image Enhancement Network for Low-Light Cattle Farm Scenes by Integrating Fusion Gate Transformation Mechanism and Variational Autoencoder GAN |
| title_sort | gct vae gan an image enhancement network for low light cattle farm scenes by integrating fusion gate transformation mechanism and variational autoencoder gan |
| topic | Low-light image enhancement GAN VAE quality evaluation |
| url | https://ieeexplore.ieee.org/document/10302291/ |
| work_keys_str_mv | AT chengchaowang gctvaegananimageenhancementnetworkforlowlightcattlefarmscenesbyintegratingfusiongatetransformationmechanismandvariationalautoencodergan AT guohonggao gctvaegananimageenhancementnetworkforlowlightcattlefarmscenesbyintegratingfusiongatetransformationmechanismandvariationalautoencodergan AT jianpingwang gctvaegananimageenhancementnetworkforlowlightcattlefarmscenesbyintegratingfusiongatetransformationmechanismandvariationalautoencodergan AT yingyinglv gctvaegananimageenhancementnetworkforlowlightcattlefarmscenesbyintegratingfusiongatetransformationmechanismandvariationalautoencodergan AT qianli gctvaegananimageenhancementnetworkforlowlightcattlefarmscenesbyintegratingfusiongatetransformationmechanismandvariationalautoencodergan AT zhiyuli gctvaegananimageenhancementnetworkforlowlightcattlefarmscenesbyintegratingfusiongatetransformationmechanismandvariationalautoencodergan AT xueyanzhang gctvaegananimageenhancementnetworkforlowlightcattlefarmscenesbyintegratingfusiongatetransformationmechanismandvariationalautoencodergan AT haoyuwu gctvaegananimageenhancementnetworkforlowlightcattlefarmscenesbyintegratingfusiongatetransformationmechanismandvariationalautoencodergan |