Nighttime image dehazing aims to remove the effect of haze on the images captured in nighttime,which however,raises new challenges such as severe color distortion,more complex lighting conditions,and lower contrast.In...Nighttime image dehazing aims to remove the effect of haze on the images captured in nighttime,which however,raises new challenges such as severe color distortion,more complex lighting conditions,and lower contrast.Instead of estimating the transmission map and atmospheric light that are difficult to be accurately acquired in nighttime,we propose a nighttime image dehazing method composed of a color cast removal and a dual path multi-scale fusion algorithm.We first propose a human visual system(HVS)inspired color correction model,which is effective for removing the color deviation on nighttime hazy images.Then,we propose to use dual path strategy that includes an underexposure and a contrast enhancement path for multi-scale fusion,where the weight maps are achieved by selecting appropriate exposed areas under Gaussian pyramids.Extensive experiments demonstrate that the visual effect of the hazy nighttime images in real-world datasets can be significantly improved by our method regarding contrast,color fidelity,and visibility.In addition,our method outperforms the state-of-the-art methods qualitatively and quantitatively.展开更多
The problem of finished surface being not first-order continuous commonly exists in machining sculptured surfaces with a torus cutter and some other types of cutters. To solve this problem, a dual drive curve tool pat...The problem of finished surface being not first-order continuous commonly exists in machining sculptured surfaces with a torus cutter and some other types of cutters. To solve this problem, a dual drive curve tool path planning method is proposed in this article. First, the maximum machining strip width of a whole tool path can be obtained through optimizing each tool position with multi-point machining （MPM） method. Second, two drive curves are then determined according to the obtained maximum machining strip width. Finally, the tool is positioned once more along the dual drive curve under the condition of tool path smoothness. A computer simulation and cutting experiments are carried out to testify the performance of the new method. The machined surface is measured with a coordinate measuring machine （CMM） to examine the machining quality. The results obtained show that this method can effectively eliminate sharp scallops between adjacent tool paths, keep tool paths smooth, and improve the surface machining quality as well as machining efficiency.展开更多
The accurate monitoring of optical thin-film thickness is a key technique for depositing optical thin-film. For existing coating equipments, which are low precision and automation level on monitoring thin-film thickne...The accurate monitoring of optical thin-film thickness is a key technique for depositing optical thin-film. For existing coating equipments, which are low precision and automation level on monitoring thin-film thickness, a new photoelectric control and analysis system has been developed. In the new system, main techniques include a photoelectric system with dual-light path, a dual-lock-phase circuit system and a comprehensive digital processing-control-analysis system.The test results of new system show that the static and dynamic stabilities and the control precision of thin-film thickness are extremely increased. The standard deviation of thin-film thickness, which indicates the duplication of thin-film thickness monitoring, is equal to or less than 0.72%. The display resolution limit on reflectivity is 0.02 %. In the system, the linearity of drift is very high, and the static drift ratio approaches zero.展开更多
The problem of passive detection discussed in this paper involves searching and locating an aerial emitter by dualaircraft using passive radars. In order to improve the detection probability and accuracy, a fuzzy Q le...The problem of passive detection discussed in this paper involves searching and locating an aerial emitter by dualaircraft using passive radars. In order to improve the detection probability and accuracy, a fuzzy Q learning algorithrn for dual-aircraft flight path planning is proposed. The passive detection task model of the dual-aircraft is set up based on the partition of the target active radar＇s radiation area. The problem is formulated as a Markov decision process （MDP） by using the fuzzy theory to make a generalization of the state space and defining the transition functions, action space and reward function properly. Details of the path planning algorithm are presented. Simulation results indicate that the algorithm can provide adaptive strategies for dual-aircraft to control their flight paths to detect a non-maneuvering or maneu- vering target.展开更多
This work summarizes the structure and operating features of a high-performance 3-stage dual-delay-path (DDP) voltage-controlled ring oscillator (VCRO) with self-biased delay cells for Phase-Locked Loop (PLL) structur...This work summarizes the structure and operating features of a high-performance 3-stage dual-delay-path (DDP) voltage-controlled ring oscillator (VCRO) with self-biased delay cells for Phase-Locked Loop (PLL) structurebased clock generation and digital system driving. For a voltage supply V<sub>DD</sub> = 1.8 V, the resulting set of performance parameters include power consumption P<sub><sub></sub>DC</sub> = 4.68 mW and phase noise PN@1MHz = -107.8 dBc/Hz. From the trade-off involving P<sub>DC</sub> and PN, a system level high performance is obtained considering a reference figure-of-merit ( FoM = -224 dBc/Hz ). Implemented at schematic level by applying CMOS-based technology (UMC L180), the proposed VCRO was designed at Cadence environment and optimized at MunEDA WiCkeD tool.展开更多
With the development of advanced high strength steel,especially for dual-phase steel,the model algorithm for cooling control after hot rolling has to achieve the targeted coiling temperature control at the location of...With the development of advanced high strength steel,especially for dual-phase steel,the model algorithm for cooling control after hot rolling has to achieve the targeted coiling temperature control at the location of downcoiler whilst maintaining the cooling path control based on strip microstructure along the whole cooling section.A cooling path control algorithm was proposed for the laminar cooling process as a solution to practical difficulties associated with the realization of the thermal cycle during cooling process.The heat conduction equation coupled with the carbon diffusion equation with moving boundary was employed in order to simulate temperature change and phase transformation kinetics,making it possible to observe the temperature field and the phase fraction of the strip in real time.On this basis,an optimization method was utilized for valve settings to ensure the minimum deviations between the predicted and actual cooling path of the strip,taking into account the constraints of the cooling equipment′s specific capacity,cooling line length,etc.Results showed that the model algorithm was able to achieve the online cooling path control for dual-phase steel.展开更多
目的红外小目标检测旨在从复杂背景中准确识别和定位弱小红外目标,在海上侦查、军事救援等任务中具有重要的应用前景。然而,受限于红外图像中目标尺寸小、对比度低等因素,当前的检测方法仍难以实现检测精度与误报率之间的平衡。针对上...目的红外小目标检测旨在从复杂背景中准确识别和定位弱小红外目标,在海上侦查、军事救援等任务中具有重要的应用前景。然而,受限于红外图像中目标尺寸小、对比度低等因素,当前的检测方法仍难以实现检测精度与误报率之间的平衡。针对上述问题,提出一种基于选择性注意力的红外小目标检测网络(selective attentionbased network for infrared small target detection,SANet)。方法具体而言,设计了双路径语义感知模块,用于增强网络对弱小目标的感知能力。该模块融合了标准卷积与风车型卷积两种路径,兼顾局部空间一致性与全局上下文感知能力,并进一步引入空间/通道注意力机制以细化特征表达,从而有效提升了目标与背景的可区分性。此外,为克服U-Net中静态跳跃连接在特征融合中的局限性,进一步提出了选择性注意力融合模块。该模块基于空间动态权重机制实现跨尺度特征的自适应融合,能够根据空间显著性选择性增强关键区域,从而提升对真实目标与误报的辨识能力。结果在3个公开基准数据集上的实验结果验证了所提出的SANet在交并比(intersection over union,IoU)、nIoU、P_(d)和F_(a)4个指标上均优于现有先进方法,其中,本文方法的IoU指标在上述基准数据集上比次优方法分别提升1.93%、4.32%和2.21%。结论SANet有效增强了网络对小目标的感知能力、关键特征的表达能力以及背景干扰的抑制能力。源代码可以在https://gitcode.com/m0_61988291/SANet上获取。展开更多
基金supported by Higher Education Scientific Research Project of Ningxia(NGY2017009)。
文摘Nighttime image dehazing aims to remove the effect of haze on the images captured in nighttime,which however,raises new challenges such as severe color distortion,more complex lighting conditions,and lower contrast.Instead of estimating the transmission map and atmospheric light that are difficult to be accurately acquired in nighttime,we propose a nighttime image dehazing method composed of a color cast removal and a dual path multi-scale fusion algorithm.We first propose a human visual system(HVS)inspired color correction model,which is effective for removing the color deviation on nighttime hazy images.Then,we propose to use dual path strategy that includes an underexposure and a contrast enhancement path for multi-scale fusion,where the weight maps are achieved by selecting appropriate exposed areas under Gaussian pyramids.Extensive experiments demonstrate that the visual effect of the hazy nighttime images in real-world datasets can be significantly improved by our method regarding contrast,color fidelity,and visibility.In addition,our method outperforms the state-of-the-art methods qualitatively and quantitatively.
基金National Natural Science Foundation of China (50875012)National High-tech Research and Development Program (2008AA04Z124)+1 种基金National Science and Technology Major Project (2009ZX04001-141)Joint Construction Project of Beijing Municipal Commission of Education
文摘The problem of finished surface being not first-order continuous commonly exists in machining sculptured surfaces with a torus cutter and some other types of cutters. To solve this problem, a dual drive curve tool path planning method is proposed in this article. First, the maximum machining strip width of a whole tool path can be obtained through optimizing each tool position with multi-point machining （MPM） method. Second, two drive curves are then determined according to the obtained maximum machining strip width. Finally, the tool is positioned once more along the dual drive curve under the condition of tool path smoothness. A computer simulation and cutting experiments are carried out to testify the performance of the new method. The machined surface is measured with a coordinate measuring machine （CMM） to examine the machining quality. The results obtained show that this method can effectively eliminate sharp scallops between adjacent tool paths, keep tool paths smooth, and improve the surface machining quality as well as machining efficiency.
基金Sponsored by the Ordnance Industry Scientific Research Fund(ZZ9682-3).
文摘The accurate monitoring of optical thin-film thickness is a key technique for depositing optical thin-film. For existing coating equipments, which are low precision and automation level on monitoring thin-film thickness, a new photoelectric control and analysis system has been developed. In the new system, main techniques include a photoelectric system with dual-light path, a dual-lock-phase circuit system and a comprehensive digital processing-control-analysis system.The test results of new system show that the static and dynamic stabilities and the control precision of thin-film thickness are extremely increased. The standard deviation of thin-film thickness, which indicates the duplication of thin-film thickness monitoring, is equal to or less than 0.72%. The display resolution limit on reflectivity is 0.02 %. In the system, the linearity of drift is very high, and the static drift ratio approaches zero.
基金supported by the National Natural Science Foundation of China(60874040)
文摘The problem of passive detection discussed in this paper involves searching and locating an aerial emitter by dualaircraft using passive radars. In order to improve the detection probability and accuracy, a fuzzy Q learning algorithrn for dual-aircraft flight path planning is proposed. The passive detection task model of the dual-aircraft is set up based on the partition of the target active radar＇s radiation area. The problem is formulated as a Markov decision process （MDP） by using the fuzzy theory to make a generalization of the state space and defining the transition functions, action space and reward function properly. Details of the path planning algorithm are presented. Simulation results indicate that the algorithm can provide adaptive strategies for dual-aircraft to control their flight paths to detect a non-maneuvering or maneu- vering target.
文摘This work summarizes the structure and operating features of a high-performance 3-stage dual-delay-path (DDP) voltage-controlled ring oscillator (VCRO) with self-biased delay cells for Phase-Locked Loop (PLL) structurebased clock generation and digital system driving. For a voltage supply V<sub>DD</sub> = 1.8 V, the resulting set of performance parameters include power consumption P<sub><sub></sub>DC</sub> = 4.68 mW and phase noise PN@1MHz = -107.8 dBc/Hz. From the trade-off involving P<sub>DC</sub> and PN, a system level high performance is obtained considering a reference figure-of-merit ( FoM = -224 dBc/Hz ). Implemented at schematic level by applying CMOS-based technology (UMC L180), the proposed VCRO was designed at Cadence environment and optimized at MunEDA WiCkeD tool.
文摘With the development of advanced high strength steel,especially for dual-phase steel,the model algorithm for cooling control after hot rolling has to achieve the targeted coiling temperature control at the location of downcoiler whilst maintaining the cooling path control based on strip microstructure along the whole cooling section.A cooling path control algorithm was proposed for the laminar cooling process as a solution to practical difficulties associated with the realization of the thermal cycle during cooling process.The heat conduction equation coupled with the carbon diffusion equation with moving boundary was employed in order to simulate temperature change and phase transformation kinetics,making it possible to observe the temperature field and the phase fraction of the strip in real time.On this basis,an optimization method was utilized for valve settings to ensure the minimum deviations between the predicted and actual cooling path of the strip,taking into account the constraints of the cooling equipment′s specific capacity,cooling line length,etc.Results showed that the model algorithm was able to achieve the online cooling path control for dual-phase steel.
文摘目的红外小目标检测旨在从复杂背景中准确识别和定位弱小红外目标,在海上侦查、军事救援等任务中具有重要的应用前景。然而,受限于红外图像中目标尺寸小、对比度低等因素,当前的检测方法仍难以实现检测精度与误报率之间的平衡。针对上述问题,提出一种基于选择性注意力的红外小目标检测网络(selective attentionbased network for infrared small target detection,SANet)。方法具体而言,设计了双路径语义感知模块,用于增强网络对弱小目标的感知能力。该模块融合了标准卷积与风车型卷积两种路径,兼顾局部空间一致性与全局上下文感知能力,并进一步引入空间/通道注意力机制以细化特征表达,从而有效提升了目标与背景的可区分性。此外,为克服U-Net中静态跳跃连接在特征融合中的局限性,进一步提出了选择性注意力融合模块。该模块基于空间动态权重机制实现跨尺度特征的自适应融合,能够根据空间显著性选择性增强关键区域,从而提升对真实目标与误报的辨识能力。结果在3个公开基准数据集上的实验结果验证了所提出的SANet在交并比(intersection over union,IoU)、nIoU、P_(d)和F_(a)4个指标上均优于现有先进方法,其中,本文方法的IoU指标在上述基准数据集上比次优方法分别提升1.93%、4.32%和2.21%。结论SANet有效增强了网络对小目标的感知能力、关键特征的表达能力以及背景干扰的抑制能力。源代码可以在https://gitcode.com/m0_61988291/SANet上获取。
