Manhole cover defect recognition is of significant practical importance as it can accurately identify damaged or missing covers, enabling timely replacement and maintenance. Traditional manhole cover detection techniq...Manhole cover defect recognition is of significant practical importance as it can accurately identify damaged or missing covers, enabling timely replacement and maintenance. Traditional manhole cover detection techniques primarily focus on detecting the presence of covers rather than classifying the types of defects. However, manhole cover defects exhibit small inter-class feature differences and large intra-class feature variations, which makes their recognition challenging. To improve the classification of manhole cover defect types, we propose a Progressive Dual-Branch Feature Fusion Network (PDBFFN). The baseline backbone network adopts a multi-stage hierarchical architecture design using Res-Net50 as the visual feature extractor, from which both local and global information is obtained. Additionally, a Feature Enhancement Module (FEM) and a Fusion Module (FM) are introduced to enhance the network’s ability to learn critical features. Experimental results demonstrate that our model achieves a classification accuracy of 82.6% on a manhole cover defect dataset, outperforming several state-of-the-art fine-grained image classification models.展开更多
Remote sensing image(RSI)with concurrently high spatial,temporal,and spectral resolutions cannot be produced by a single sensor.Multisource RSI fusion is a convenient technique to realize high spatial resolution multi...Remote sensing image(RSI)with concurrently high spatial,temporal,and spectral resolutions cannot be produced by a single sensor.Multisource RSI fusion is a convenient technique to realize high spatial resolution multispectral(MS)images(spatial spectral fusion,i.e.SSF)and high temporal and spatial resolution MS images(spatiotemporal fusion,i.e.STF).Currently,deep learning-based fusion models can only implement SSF or STF,lacking models that perform both SSF and STF.Multiresolution generative adversarial networks with bidirectional adaptive-stage progressive guided fusion(BAPGF)for RSI are proposed to implement both SSF and STF,namely BPF-MGAN.A bidirectional adaptive-stage feature extraction architecture infine-scale-to-coarse-scale and coarse-scale-to-fine-scale modes is introduced.The designed BAPGF introduces a previous fusion result-oriented cross-stage-level dual-residual attention fusion strategy to enhance critical information and suppress superfluous information.Adaptive resolution U-shaped discriminators are implemented to feed multiresolution context into the generator.A generalized multitask loss function unlimited by no-reference images is developed to strengthen the model via constraints on the multiscale feature,structural,and content similarities.The BPF-MGAN model is validated on SSF datasets and STF datasets.Compared with the state-of-the-art SSF and STF models,results demonstrate the superior performance of the proposed BPF-MGAN model in both subjective and objective evaluations.展开更多
In the standard fusion reactors, mainly tokamaks, the mechanical gain obtained is below 1. On the other hand, there are colliding beam fusion reactors, for which, the not neutral plasma and the space charge limit the ...In the standard fusion reactors, mainly tokamaks, the mechanical gain obtained is below 1. On the other hand, there are colliding beam fusion reactors, for which, the not neutral plasma and the space charge limit the number of fusions to a very small number. Consequently, the mechanical gain is extremely low. The proposed reactor is also a colliding beam fusion reactor, configured in Stellarator, using directed beams. D+/T+ ions are injected in opposition, with electrons, at high speeds, so as to form a neutral beam. All these particles turn in a magnetic loop in form of figure of “0” (“racetrack”). The plasma is initially non-thermal but, as expected, rapidly becomes thermal, so all states between non-thermal and thermal exist in this reactor. The main advantage of this reactor is that this plasma after having been brought up near to the optimum conditions for fusion (around 68 keV), is then maintained in this state, thanks to low energy non-thermal ions (≤15 keV). So the energetic cost is low and the mechanical gain (</span><i><span style="font-family:Verdana;">Q</span></i><span style="font-family:Verdana;">) is high (</span></span><span style="font-family:Verdana;">>></span><span style="font-family:Verdana;">1). The goal of this article is to study a different type of fusion reactor, its advantages (no net plasma current inside this reactor, so no disruptive instabilities and consequently a continuous working, a relatively simple way to control the reactor thanks to the particles injectors), and its drawbacks, using a simulator tool. The finding results are valuable for possible future fusion reactors able to generate massive energy in a cleaner and safer way than fission reactors.展开更多
文摘Manhole cover defect recognition is of significant practical importance as it can accurately identify damaged or missing covers, enabling timely replacement and maintenance. Traditional manhole cover detection techniques primarily focus on detecting the presence of covers rather than classifying the types of defects. However, manhole cover defects exhibit small inter-class feature differences and large intra-class feature variations, which makes their recognition challenging. To improve the classification of manhole cover defect types, we propose a Progressive Dual-Branch Feature Fusion Network (PDBFFN). The baseline backbone network adopts a multi-stage hierarchical architecture design using Res-Net50 as the visual feature extractor, from which both local and global information is obtained. Additionally, a Feature Enhancement Module (FEM) and a Fusion Module (FM) are introduced to enhance the network’s ability to learn critical features. Experimental results demonstrate that our model achieves a classification accuracy of 82.6% on a manhole cover defect dataset, outperforming several state-of-the-art fine-grained image classification models.
基金funded by the National Key Research and Development Program of China under Grants 2020YFB2104400 and 2020YFB2104401the National Natural Science Foundation of China under Grant 82260362the Hainan Major Science and Technology Program of China under Grant ZDKJ202017.
文摘Remote sensing image(RSI)with concurrently high spatial,temporal,and spectral resolutions cannot be produced by a single sensor.Multisource RSI fusion is a convenient technique to realize high spatial resolution multispectral(MS)images(spatial spectral fusion,i.e.SSF)and high temporal and spatial resolution MS images(spatiotemporal fusion,i.e.STF).Currently,deep learning-based fusion models can only implement SSF or STF,lacking models that perform both SSF and STF.Multiresolution generative adversarial networks with bidirectional adaptive-stage progressive guided fusion(BAPGF)for RSI are proposed to implement both SSF and STF,namely BPF-MGAN.A bidirectional adaptive-stage feature extraction architecture infine-scale-to-coarse-scale and coarse-scale-to-fine-scale modes is introduced.The designed BAPGF introduces a previous fusion result-oriented cross-stage-level dual-residual attention fusion strategy to enhance critical information and suppress superfluous information.Adaptive resolution U-shaped discriminators are implemented to feed multiresolution context into the generator.A generalized multitask loss function unlimited by no-reference images is developed to strengthen the model via constraints on the multiscale feature,structural,and content similarities.The BPF-MGAN model is validated on SSF datasets and STF datasets.Compared with the state-of-the-art SSF and STF models,results demonstrate the superior performance of the proposed BPF-MGAN model in both subjective and objective evaluations.
文摘In the standard fusion reactors, mainly tokamaks, the mechanical gain obtained is below 1. On the other hand, there are colliding beam fusion reactors, for which, the not neutral plasma and the space charge limit the number of fusions to a very small number. Consequently, the mechanical gain is extremely low. The proposed reactor is also a colliding beam fusion reactor, configured in Stellarator, using directed beams. D+/T+ ions are injected in opposition, with electrons, at high speeds, so as to form a neutral beam. All these particles turn in a magnetic loop in form of figure of “0” (“racetrack”). The plasma is initially non-thermal but, as expected, rapidly becomes thermal, so all states between non-thermal and thermal exist in this reactor. The main advantage of this reactor is that this plasma after having been brought up near to the optimum conditions for fusion (around 68 keV), is then maintained in this state, thanks to low energy non-thermal ions (≤15 keV). So the energetic cost is low and the mechanical gain (</span><i><span style="font-family:Verdana;">Q</span></i><span style="font-family:Verdana;">) is high (</span></span><span style="font-family:Verdana;">>></span><span style="font-family:Verdana;">1). The goal of this article is to study a different type of fusion reactor, its advantages (no net plasma current inside this reactor, so no disruptive instabilities and consequently a continuous working, a relatively simple way to control the reactor thanks to the particles injectors), and its drawbacks, using a simulator tool. The finding results are valuable for possible future fusion reactors able to generate massive energy in a cleaner and safer way than fission reactors.
