Engineering seismic exploration aims at shallow imaging which is confused by statics if the surface is uneven. Direct pre-stack depth migration （DPDM） is based on accurate elevations of sources and receivers, by whi...Engineering seismic exploration aims at shallow imaging which is confused by statics if the surface is uneven. Direct pre-stack depth migration （DPDM） is based on accurate elevations of sources and receivers, by which static correction is completely abandoned before migration and surely the imaging quality is remarkably improved. To obtain some artificial shot gathers, high-order staggered-grid finite-difference （FD） method is adapted to model acoustic wave propagation. Since the shot gathers are always disturbed by regular interferences, the statics still must be applied to supporting the interference elimination by apparent velocity filtering method. Then all the shot gathers should be removed back to their original positions by reverse statics. Finally, they are migrated by pre-stack reverse-time depth migration and imaged. The numerical experiments show that the DPDM can ideally avoid the mistakes caused by statics and increase imaging precision.展开更多
Strong fluctuation of seabed,abrupt variation in depth and dip of seabed bring seismic imaging problems,such as irregular reflection waves,obvious multiple waves,serious lateral wave development,poor imaging on base s...Strong fluctuation of seabed,abrupt variation in depth and dip of seabed bring seismic imaging problems,such as irregular reflection waves,obvious multiple waves,serious lateral wave development,poor imaging on base surface and depression structure,low signal-to-noise ratio of middle and deep layers.In this paper,Gaussian beam migration imaging method is used to analyze the imaging effect of rugged seabed in deep water area,and the ray tracing method of wavefront construction method is used to analyze the kinematic characteristics of seismic waves.By improving the design of seismic data acquisition and observation system,imaging quality of fine structures is improved.展开更多
Objective:To explore the relationship between anesthetic depth and surgical stress response in minimally invasive cardiothoracic surgery.Methods:A total of 89 patients who underwent thoracoscopic minimally invasive ca...Objective:To explore the relationship between anesthetic depth and surgical stress response in minimally invasive cardiothoracic surgery.Methods:A total of 89 patients who underwent thoracoscopic minimally invasive cardiothoracic surgery in our hospital from June 2024 to December 2024 were selected as the research objects.They were divided into the light anesthesia group(n=45)and the deep anesthesia group(n=44).The vital signs at different intraoperative nodes and perioperative stress status of the two groups were compared.Results:Before lesion resection and after surgery,the mean arterial pressure and heart rate of the deep anesthesia group were lower than those of the light anesthesia group,with statistically significant differences.Conclusion:In thoracoscopic minimally invasive cardiothoracic surgery,deep anesthesia can effectively control the patient’s surgical stress response,but the postoperative awakening time is longer;patients under light anesthesia have a shorter awakening time,but the intraoperative stress response is obvious.展开更多
Presented in this study is a novel method for estimating the depth of single underwater source in shallow water,utilizing vector sensors.The approach leverages the depth distribution of the broadband Stokes parameters...Presented in this study is a novel method for estimating the depth of single underwater source in shallow water,utilizing vector sensors.The approach leverages the depth distribution of the broadband Stokes parameters to estimate source depth accurately.Unlike traditional matched field processing(MFP)and matched mode processing(MMP),the proposed approach can estimate source depth directly from the data received by sensors without requiring complete environmental information.Firstly,the broadband Stokes parameters(BSP)are established using the normal mode theory.Then the nonstationary phase approximation is used to simplify the theoretical derivation,which is necessary when dealing with broadband integrals.Additionally,range terms of the BSP are eliminated by normalization.By analyzing the depth distribution of the normalized broadband Stokes parameters(NBSP),it is found that the NBSP exhibit extreme values at the source depth,which can be used for source depth estimation.So the proposed depth estimation method is based on searching the peaks of the NBSP.Simulations show that this method is effective in relatively simple shallow water environments.Finally,the effect of source range,frequency bandwidth,sound speed profile(SSP),water depth,and signal-to-noise ratio(SNR)are studied.The findings indicate that the proposed method can accurately estimate the source depth when the SNR is greater than-5 d B and does not need to consider model mismatch issues.Additionally,variations in environmental parameters have minimal impact on estimation accuracy.Compared to MFP,the proposed method requires a higher SNR,but demonstrates superior robustness against fluctuations in environmental parameters.展开更多
The initial noise present in the depth images obtained with RGB-D sensors is a combination of hardware limitations in addition to the environmental factors,due to the limited capabilities of sensors,which also produce...The initial noise present in the depth images obtained with RGB-D sensors is a combination of hardware limitations in addition to the environmental factors,due to the limited capabilities of sensors,which also produce poor computer vision results.The common image denoising techniques tend to remove significant image details and also remove noise,provided they are based on space and frequency filtering.The updated framework presented in this paper is a novel denoising model that makes use of Boruta-driven feature selection using a Long Short-Term Memory Autoencoder(LSTMAE).The Boruta algorithm identifies the most useful depth features that are used to maximize the spatial structure integrity and reduce redundancy.An LSTMAE is then used to process these selected features and model depth pixel sequences to generate robust,noise-resistant representations.The system uses the encoder to encode the input data into a latent space that has been compressed before it is decoded to retrieve the clean image.Experiments on a benchmark data set show that the suggested technique attains a PSNR of 45 dB and an SSIM of 0.90,which is 10 dB higher than the performance of conventional convolutional autoencoders and 15 times higher than that of the wavelet-based models.Moreover,the feature selection step will decrease the input dimensionality by 40%,resulting in a 37.5%reduction in training time and a real-time inference rate of 200 FPS.Boruta-LSTMAE framework,therefore,offers a highly efficient and scalable system for depth image denoising,with a high potential to be applied to close-range 3D systems,such as robotic manipulation and gesture-based interfaces.展开更多
The transient phenomena of re-oxidation and slag entrapment occurring in the tundish during the ladle change-over process have been proven detrimental to clean steel production.Therefore,an unsteady three-phase turbul...The transient phenomena of re-oxidation and slag entrapment occurring in the tundish during the ladle change-over process have been proven detrimental to clean steel production.Therefore,an unsteady three-phase turbulence model,coupling velocity,temperature,and phase field was established to study the effect of the ladle shroud immersion depth on the slag eye formation,slag entrainment,slag dragging,air dragging,and flow characteristics during the ladle change-over process of a two-strand tundish.The results showed that reducing the immersion depth decreases the high-velocity region area under the slag layer in the quasi-steady process.During the emptying stage,as the molten bath level gradually decreases,the outlet temperature exhibits a trend of initially decreasing and subsequently increasing across all three shroud immersion depths.However,under a 210 mm shroud immersion depth,molten slag and air are dragged into the shroud,forming slag droplets and causing significant fluctuations,with a maximum scalar velocity of 0.0764 m/s at the monitoring point.In the filling stage,air and molten slag are dragged into the molten bath,forming bubbles and slag droplets at an immersion depth of 210 mm.Bubbles are observed within the molten slag layer,which can readily cause an emulsification phenomenon,making it easier to be dragged as slag droplets.Additionally,the slag eye area measured under 210 mm immersion depth at 45 s is 0.303 m^(2),while the maximum scalar velocity of 2.4259 m/s is detected at 12 s.At an immersion depth of 360 mm,the average area of the slag eye is minimized to 0.06268 m2,with corresponding variances of 0.006753,representing the optimal immersion depth.展开更多
Accurately estimating depth from underwater monocular images is essential for the target tracking task of unmanned underwater vehicles.This work proposes a method based on the Lpg-Lap Unet architecture.First,the Unet ...Accurately estimating depth from underwater monocular images is essential for the target tracking task of unmanned underwater vehicles.This work proposes a method based on the Lpg-Lap Unet architecture.First,the Unet architecture integrates Laplacian pyramid depth residuals and Sobel operators to improve the boundary details in depth images,which may suffer from the feature loss caused by upsampling and the blurriness of underwater images.Multiscale local planar guidance layers then fully exploit the intermediate depth features,and a comprehensive loss function ensures robustness and accuracy.Experimental results on benchmarks demonstrate the effectiveness of Lpg-Lap Unet and its superior performance over state-of-the-art models.An underwater target tracking system is then designed to further validate its real-time capabilities in the AirSim simulation platform.展开更多
Bathymetric measurement of shallow water is of fundamental importance to coastal environment research and resource management.However,there are still great challenges in estimating water depth using satellite observat...Bathymetric measurement of shallow water is of fundamental importance to coastal environment research and resource management.However,there are still great challenges in estimating water depth using satellite observations in turbid coastal waters.In this paper,we developed a physicsenhanced deep neural network to estimate bathymetry of highly turbid waters of the Changjiang(Yangtze)River estuary from dual-polarized synthetic aperture radar(SAR)images.Sentinel-1A/B SAR images with a spatial resolution of 20 m×22 m were collected and matched with water depth data from nautical charts during 2017-2023.For the input parameters of the model,in addition to the normalized radar backscatter cross section(NRCS)at single polarization and incidence angle,the impacts of both polarimetric characteristics and physical environmental factors on model performance were discussed in detail.Results of feature importance analysis and sensitivity experiments indicate that the polarization ratio and NRCS after removing the influence of background sea surface wind field make significant contributions to the bathymetry retrieval model.The root mean square error(RMSE)of SAR derived water depth decreases from 1.44 to 0.78 m within 0-30-m depth,and the mean relative error(MRE)is reduced from 15.6%to 8.6%.Compared with other machine learning models such as ResNet,XGBoost,and Random Forest,the MRE is reduced by 3.9%,5.7%,and 7.4%,respectively.The spatial distribution of SAR derived water depth also exhibits a high degree of consistency with observations,demonstrating the great potential of the model in estimating the depth of turbid shallow waters.展开更多
The extensive application of pre-stack depth migration has produced huge volumes of seismic data,which allows for the possibility of developing seismic inversions of reservoir properties from seismic data in the depth...The extensive application of pre-stack depth migration has produced huge volumes of seismic data,which allows for the possibility of developing seismic inversions of reservoir properties from seismic data in the depth domain.It is difficult to estimate seismic wavelets directly from seismic data due to the nonstationarity of the data in the depth domain.We conduct a velocity transformation of seismic data to make the seismic data stationary and then apply the ridge regression method to estimate a constant seismic wavelet.The estimated constant seismic wavelet is constructed as a set of space-variant seismic wavelets dominated by velocities at different spatial locations.Incorporating the weighted superposition principle,a synthetic seismogram is generated by directly employing the space-variant seismic wavelets in the depth domain.An inversion workflow based on the model-driven method is developed in the depth domain by incorporating the nonlinear conjugate gradient algorithm,which avoids additional data conversions between the time and depth domains.The impedance inversions of the synthetic and field seismic data in the depth domain show good results,which demonstrates that seismic inversion in the depth domain is feasible.The approach provides an alternative for forward numerical analyses and elastic property inversions of depth-domain seismic data.It is advantageous for further studies concerning the stability,accuracy,and efficiency of seismic inversions in the depth domain.展开更多
Due to the lack of accurate data and complex parameterization,the prediction of groundwater depth is a chal-lenge for numerical models.Machine learning can effectively solve this issue and has been proven useful in th...Due to the lack of accurate data and complex parameterization,the prediction of groundwater depth is a chal-lenge for numerical models.Machine learning can effectively solve this issue and has been proven useful in the prediction of groundwater depth in many areas.In this study,two new models are applied to the prediction of groundwater depth in the Ningxia area,China.The two models combine the improved dung beetle optimizer(DBO)algorithm with two deep learning models:The Multi-head Attention-Convolution Neural Network-Long Short Term Memory networks(MH-CNN-LSTM)and the Multi-head Attention-Convolution Neural Network-Gated Recurrent Unit(MH-CNN-GRU).The models with DBO show better prediction performance,with larger R(correlation coefficient),RPD(residual prediction deviation),and lower RMSE(root-mean-square error).Com-pared with the models with the original DBO,the R and RPD of models with the improved DBO increase by over 1.5%,and the RMSE decreases by over 1.8%,indicating better prediction results.In addition,compared with the multiple linear regression model,a traditional statistical model,deep learning models have better prediction performance.展开更多
Rare earth-doped inorganic compounds contribute mostly to the family of persistent luminescent materials due to the versatile energy levels of rare earth ions.One of the key research aims is to match the trap level st...Rare earth-doped inorganic compounds contribute mostly to the family of persistent luminescent materials due to the versatile energy levels of rare earth ions.One of the key research aims is to match the trap level stemming from the doped rare earth ion or intrinsic defects to the electronic structure of the host,and therefore thermoluminescence measurement becomes a radical technology in studying trap depth,which is one of the significant parameters that determine the properties of persistent luminescence and photostimulated luminescence.However,the results of trap depth obtained by different thermoluminescence methods are quite different so that they are not comparable.Herein,we analyzed different thermoluminescence methods,selected and improved the traditional peak position method of T_(m)/500 to be E=(-0.94Inβ+30.09)kT_(m).Only the experimental heating rate(β)is needed additionally,but the accuracy is improved greatly in most cases.This convenient and accurate method will accelerate the discovery of novel rare earth-doped materials.展开更多
Spatial computing and augmented reality are advancing rapidly,with the goal of seamlessly blending virtual and physical worlds.However,traditional depth-sensing systems are bulky and energy-intensive,limiting their us...Spatial computing and augmented reality are advancing rapidly,with the goal of seamlessly blending virtual and physical worlds.However,traditional depth-sensing systems are bulky and energy-intensive,limiting their use in wearable devices.To overcome this,recent research by X.Liu et al.presents a compact binocular metalens-based depth perception system that integrates efficient edge detection through an advanced neural network.This system enables accurate,realtime depth mapping even in complex environments,enhancing potential applications in augmented reality,robotics,and autonomous systems.展开更多
对于复杂天气场景图像模糊、低对比度和颜色失真所导致的深度信息预测不准的问题,以往的研究均以标准场景的深度图作为先验信息来对该类场景进行深度估计。然而,这一方式存在先验信息精度较低等问题。对此,提出一个基于多尺度注意力机...对于复杂天气场景图像模糊、低对比度和颜色失真所导致的深度信息预测不准的问题,以往的研究均以标准场景的深度图作为先验信息来对该类场景进行深度估计。然而,这一方式存在先验信息精度较低等问题。对此,提出一个基于多尺度注意力机制的单目深度估计模型TalentDepth,以实现对复杂天气场景的预测。首先,在编码器中融合多尺度注意力机制,在减少计算成本的同时,保留每个通道的信息,提高特征提取的效率和能力。其次,针对图像深度不清晰的问题,基于几何一致性,提出深度区域细化(Depth Region Refinement,DSR)模块,过滤不准确的像素点,以提高深度信息的可靠性。最后,输入图像翻译模型所生成的复杂样本,并计算相应原始图像上的标准损失来指导模型的自监督训练。在NuScence,KITTI和KITTI-C这3个数据集上,相比于基线模型,所提模型对误差和精度均有优化。展开更多
Depth maps play a crucial role in various practical applications such as computer vision,augmented reality,and autonomous driving.How to obtain clear and accurate depth information in video depth estimation is a signi...Depth maps play a crucial role in various practical applications such as computer vision,augmented reality,and autonomous driving.How to obtain clear and accurate depth information in video depth estimation is a significant challenge faced in the field of computer vision.However,existing monocular video depth estimation models tend to produce blurred or inaccurate depth information in regions with object edges and low texture.To address this issue,we propose a monocular depth estimation model architecture guided by semantic segmentation masks,which introduces semantic information into the model to correct the ambiguous depth regions.We have evaluated the proposed method,and experimental results show that our method improves the accuracy of edge depth,demonstrating the effectiveness of our approach.展开更多
自监督单目深度估计受到了国内外研究人员的广泛关注。现有基于深度学习的自监督单目深度估计方法主要采用编码器-解码器结构。然而,这些方法在编码过程中对输入图像进行下采样操作,导致部分图像信息,尤其是图像的边界信息丢失,进而影...自监督单目深度估计受到了国内外研究人员的广泛关注。现有基于深度学习的自监督单目深度估计方法主要采用编码器-解码器结构。然而,这些方法在编码过程中对输入图像进行下采样操作,导致部分图像信息,尤其是图像的边界信息丢失,进而影响深度图的精度。针对上述问题,提出一种基于拉普拉斯金字塔的自监督单目深度估计方法(Self-supervised Monocular Depth Estimation Based on the Laplace Pyramid,LpDepth)。此方法的核心思想是:首先,使用拉普拉斯残差图丰富编码特征,以弥补在下采样过程中丢失的特征信息;其次,在下采样过程中使用最大池化层突显和放大特征信息,使编码器在特征提取过程中更容易地提取到训练模型所需要的特征信息;最后,使用残差模块解决过拟合问题,提高解码器对特征的利用效率。在KITTI和Make3D等数据集上对所提方法进行了测试,同时将其与现有经典方法进行了比较。实验结果证明了所提方法的有效性。展开更多
Maintaining the s-polarization state of laser beams is important to achieve high modulation depth in a laser-interference-based super-resolution structured illumination microscope(SR-SIM).However,the imperfect optical...Maintaining the s-polarization state of laser beams is important to achieve high modulation depth in a laser-interference-based super-resolution structured illumination microscope(SR-SIM).However,the imperfect optical components can depolarize the laser beams hence degenerating the modulation depth.Here,we first presented a direct measurement method designed to estimate the modulation depth more precisely by shifting illumination patterns with equal phase steps.This measurement method greatly reduces the dependence of modulation depths on the samples,and then developed a polarization optimization method to achieve high modulation depth at all orientations by actively and quantitatively compensating for the additional phase difference using a combination of waveplate and a liquid crystal variable retarder(LCVR).Experimental results demonstrate that our method can achieve illumination patterns with modulation depth higher than 0.94 at three orientations with only one LCVR voltage,which enables isotropic resolution improvement.展开更多
In the dynamic scene of autonomous vehicles,the depth estimation of monocular cameras often faces the problem of inaccurate edge depth estimation.To solve this problem,we propose an unsupervised monocular depth estima...In the dynamic scene of autonomous vehicles,the depth estimation of monocular cameras often faces the problem of inaccurate edge depth estimation.To solve this problem,we propose an unsupervised monocular depth estimation model based on edge enhancement,which is specifically aimed at the depth perception challenge in dynamic scenes.The model consists of two core networks:a deep prediction network and a motion estimation network,both of which adopt an encoder-decoder architecture.The depth prediction network is based on the U-Net structure of ResNet18,which is responsible for generating the depth map of the scene.The motion estimation network is based on the U-Net structure of Flow-Net,focusing on the motion estimation of dynamic targets.In the decoding stage of the motion estimation network,we innovatively introduce an edge-enhanced decoder,which integrates a convolutional block attention module(CBAM)in the decoding process to enhance the recognition ability of the edge features of moving objects.In addition,we also designed a strip convolution module to improve the model’s capture efficiency of discrete moving targets.To further improve the performance of the model,we propose a novel edge regularization method based on the Laplace operator,which effectively accelerates the convergence process of themodel.Experimental results on the KITTI and Cityscapes datasets show that compared with the current advanced dynamic unsupervised monocular model,the proposed model has a significant improvement in depth estimation accuracy and convergence speed.Specifically,the rootmean square error(RMSE)is reduced by 4.8%compared with the DepthMotion algorithm,while the training convergence speed is increased by 36%,which shows the superior performance of the model in the depth estimation task in dynamic scenes.展开更多
Coal seam water injection in tunnels is an effective technical measure for preventing coal mine rock bursts.This study used the improved split Hopkinson pressure bar(SHPB)to apply three equal static stresses to water-...Coal seam water injection in tunnels is an effective technical measure for preventing coal mine rock bursts.This study used the improved split Hopkinson pressure bar(SHPB)to apply three equal static stresses to water-saturated coal to simulate the initial stress environment of coal at different depths.Then,dynamic mechanical experiments were conducted on the saturated coal at different depths to investigate the effects of water saturation and depth on the coal samples’dynamic mechanical properties.Under uniaxial compression and without lateral compression,the strength of coal samples decreased to varying degrees in the saturated state;under different depth conditions,the dynamic strength of coal in the saturated state decreased compared with that in the natural state.However,compared with that at 0 m,the reduction in the strength of coal under the saturated condition at 200,400,600,and 800 m was significantly reduced.The findings of this study provide a basic theoretical foundation for the prevention and control of dynamic coal mine disasters.展开更多
文摘Engineering seismic exploration aims at shallow imaging which is confused by statics if the surface is uneven. Direct pre-stack depth migration （DPDM） is based on accurate elevations of sources and receivers, by which static correction is completely abandoned before migration and surely the imaging quality is remarkably improved. To obtain some artificial shot gathers, high-order staggered-grid finite-difference （FD） method is adapted to model acoustic wave propagation. Since the shot gathers are always disturbed by regular interferences, the statics still must be applied to supporting the interference elimination by apparent velocity filtering method. Then all the shot gathers should be removed back to their original positions by reverse statics. Finally, they are migrated by pre-stack reverse-time depth migration and imaged. The numerical experiments show that the DPDM can ideally avoid the mistakes caused by statics and increase imaging precision.
基金Supported by projects of National Natural Science Foundation of China (No. 42074150)National Key R&D Program of China (No. 2017YFC0601305)。
文摘Strong fluctuation of seabed,abrupt variation in depth and dip of seabed bring seismic imaging problems,such as irregular reflection waves,obvious multiple waves,serious lateral wave development,poor imaging on base surface and depression structure,low signal-to-noise ratio of middle and deep layers.In this paper,Gaussian beam migration imaging method is used to analyze the imaging effect of rugged seabed in deep water area,and the ray tracing method of wavefront construction method is used to analyze the kinematic characteristics of seismic waves.By improving the design of seismic data acquisition and observation system,imaging quality of fine structures is improved.
文摘Objective:To explore the relationship between anesthetic depth and surgical stress response in minimally invasive cardiothoracic surgery.Methods:A total of 89 patients who underwent thoracoscopic minimally invasive cardiothoracic surgery in our hospital from June 2024 to December 2024 were selected as the research objects.They were divided into the light anesthesia group(n=45)and the deep anesthesia group(n=44).The vital signs at different intraoperative nodes and perioperative stress status of the two groups were compared.Results:Before lesion resection and after surgery,the mean arterial pressure and heart rate of the deep anesthesia group were lower than those of the light anesthesia group,with statistically significant differences.Conclusion:In thoracoscopic minimally invasive cardiothoracic surgery,deep anesthesia can effectively control the patient’s surgical stress response,but the postoperative awakening time is longer;patients under light anesthesia have a shorter awakening time,but the intraoperative stress response is obvious.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.12274348 and 12004335)the National Key Research and Development Program of China(Grant No.2024YFC2813800)。
文摘Presented in this study is a novel method for estimating the depth of single underwater source in shallow water,utilizing vector sensors.The approach leverages the depth distribution of the broadband Stokes parameters to estimate source depth accurately.Unlike traditional matched field processing(MFP)and matched mode processing(MMP),the proposed approach can estimate source depth directly from the data received by sensors without requiring complete environmental information.Firstly,the broadband Stokes parameters(BSP)are established using the normal mode theory.Then the nonstationary phase approximation is used to simplify the theoretical derivation,which is necessary when dealing with broadband integrals.Additionally,range terms of the BSP are eliminated by normalization.By analyzing the depth distribution of the normalized broadband Stokes parameters(NBSP),it is found that the NBSP exhibit extreme values at the source depth,which can be used for source depth estimation.So the proposed depth estimation method is based on searching the peaks of the NBSP.Simulations show that this method is effective in relatively simple shallow water environments.Finally,the effect of source range,frequency bandwidth,sound speed profile(SSP),water depth,and signal-to-noise ratio(SNR)are studied.The findings indicate that the proposed method can accurately estimate the source depth when the SNR is greater than-5 d B and does not need to consider model mismatch issues.Additionally,variations in environmental parameters have minimal impact on estimation accuracy.Compared to MFP,the proposed method requires a higher SNR,but demonstrates superior robustness against fluctuations in environmental parameters.
文摘The initial noise present in the depth images obtained with RGB-D sensors is a combination of hardware limitations in addition to the environmental factors,due to the limited capabilities of sensors,which also produce poor computer vision results.The common image denoising techniques tend to remove significant image details and also remove noise,provided they are based on space and frequency filtering.The updated framework presented in this paper is a novel denoising model that makes use of Boruta-driven feature selection using a Long Short-Term Memory Autoencoder(LSTMAE).The Boruta algorithm identifies the most useful depth features that are used to maximize the spatial structure integrity and reduce redundancy.An LSTMAE is then used to process these selected features and model depth pixel sequences to generate robust,noise-resistant representations.The system uses the encoder to encode the input data into a latent space that has been compressed before it is decoded to retrieve the clean image.Experiments on a benchmark data set show that the suggested technique attains a PSNR of 45 dB and an SSIM of 0.90,which is 10 dB higher than the performance of conventional convolutional autoencoders and 15 times higher than that of the wavelet-based models.Moreover,the feature selection step will decrease the input dimensionality by 40%,resulting in a 37.5%reduction in training time and a real-time inference rate of 200 FPS.Boruta-LSTMAE framework,therefore,offers a highly efficient and scalable system for depth image denoising,with a high potential to be applied to close-range 3D systems,such as robotic manipulation and gesture-based interfaces.
基金supported by the National Natural Science Foundation of China(Nos.52422408 and 52171031)the Liaoning Xingliao Talents-Top-notch Young Talents Project(No.XLYC2203064)+1 种基金the Excellent Youth Fund of Liaoning Natural Science Foundation(No.2023JH3/10200001)the Fundamental Research Funds for the Central Universities(No.N2425004).
文摘The transient phenomena of re-oxidation and slag entrapment occurring in the tundish during the ladle change-over process have been proven detrimental to clean steel production.Therefore,an unsteady three-phase turbulence model,coupling velocity,temperature,and phase field was established to study the effect of the ladle shroud immersion depth on the slag eye formation,slag entrainment,slag dragging,air dragging,and flow characteristics during the ladle change-over process of a two-strand tundish.The results showed that reducing the immersion depth decreases the high-velocity region area under the slag layer in the quasi-steady process.During the emptying stage,as the molten bath level gradually decreases,the outlet temperature exhibits a trend of initially decreasing and subsequently increasing across all three shroud immersion depths.However,under a 210 mm shroud immersion depth,molten slag and air are dragged into the shroud,forming slag droplets and causing significant fluctuations,with a maximum scalar velocity of 0.0764 m/s at the monitoring point.In the filling stage,air and molten slag are dragged into the molten bath,forming bubbles and slag droplets at an immersion depth of 210 mm.Bubbles are observed within the molten slag layer,which can readily cause an emulsification phenomenon,making it easier to be dragged as slag droplets.Additionally,the slag eye area measured under 210 mm immersion depth at 45 s is 0.303 m^(2),while the maximum scalar velocity of 2.4259 m/s is detected at 12 s.At an immersion depth of 360 mm,the average area of the slag eye is minimized to 0.06268 m2,with corresponding variances of 0.006753,representing the optimal immersion depth.
基金partially supported by the Natural Science Foundation of Shandong Province,China(No.ZR2023ME009)the National Natural Science Foundation of China(No.51909252)。
文摘Accurately estimating depth from underwater monocular images is essential for the target tracking task of unmanned underwater vehicles.This work proposes a method based on the Lpg-Lap Unet architecture.First,the Unet architecture integrates Laplacian pyramid depth residuals and Sobel operators to improve the boundary details in depth images,which may suffer from the feature loss caused by upsampling and the blurriness of underwater images.Multiscale local planar guidance layers then fully exploit the intermediate depth features,and a comprehensive loss function ensures robustness and accuracy.Experimental results on benchmarks demonstrate the effectiveness of Lpg-Lap Unet and its superior performance over state-of-the-art models.An underwater target tracking system is then designed to further validate its real-time capabilities in the AirSim simulation platform.
基金Supported by the National Natural Science Foundation of China(Nos.T2261149752,41976163,42476172)。
文摘Bathymetric measurement of shallow water is of fundamental importance to coastal environment research and resource management.However,there are still great challenges in estimating water depth using satellite observations in turbid coastal waters.In this paper,we developed a physicsenhanced deep neural network to estimate bathymetry of highly turbid waters of the Changjiang(Yangtze)River estuary from dual-polarized synthetic aperture radar(SAR)images.Sentinel-1A/B SAR images with a spatial resolution of 20 m×22 m were collected and matched with water depth data from nautical charts during 2017-2023.For the input parameters of the model,in addition to the normalized radar backscatter cross section(NRCS)at single polarization and incidence angle,the impacts of both polarimetric characteristics and physical environmental factors on model performance were discussed in detail.Results of feature importance analysis and sensitivity experiments indicate that the polarization ratio and NRCS after removing the influence of background sea surface wind field make significant contributions to the bathymetry retrieval model.The root mean square error(RMSE)of SAR derived water depth decreases from 1.44 to 0.78 m within 0-30-m depth,and the mean relative error(MRE)is reduced from 15.6%to 8.6%.Compared with other machine learning models such as ResNet,XGBoost,and Random Forest,the MRE is reduced by 3.9%,5.7%,and 7.4%,respectively.The spatial distribution of SAR derived water depth also exhibits a high degree of consistency with observations,demonstrating the great potential of the model in estimating the depth of turbid shallow waters.
基金supported by the National Natural Science Foundation of China(No.41574130,41874143 and 41374134)the National Science and Technology Major Project of China(No.2016ZX05014-001-009)the Sichuan Provincial Youth Science&Technology Innovative Research Group Fund(No.2016TD0023)
文摘The extensive application of pre-stack depth migration has produced huge volumes of seismic data,which allows for the possibility of developing seismic inversions of reservoir properties from seismic data in the depth domain.It is difficult to estimate seismic wavelets directly from seismic data due to the nonstationarity of the data in the depth domain.We conduct a velocity transformation of seismic data to make the seismic data stationary and then apply the ridge regression method to estimate a constant seismic wavelet.The estimated constant seismic wavelet is constructed as a set of space-variant seismic wavelets dominated by velocities at different spatial locations.Incorporating the weighted superposition principle,a synthetic seismogram is generated by directly employing the space-variant seismic wavelets in the depth domain.An inversion workflow based on the model-driven method is developed in the depth domain by incorporating the nonlinear conjugate gradient algorithm,which avoids additional data conversions between the time and depth domains.The impedance inversions of the synthetic and field seismic data in the depth domain show good results,which demonstrates that seismic inversion in the depth domain is feasible.The approach provides an alternative for forward numerical analyses and elastic property inversions of depth-domain seismic data.It is advantageous for further studies concerning the stability,accuracy,and efficiency of seismic inversions in the depth domain.
基金supported by the National Natural Science Foundation of China [grant numbers 42088101 and 42375048]。
文摘Due to the lack of accurate data and complex parameterization,the prediction of groundwater depth is a chal-lenge for numerical models.Machine learning can effectively solve this issue and has been proven useful in the prediction of groundwater depth in many areas.In this study,two new models are applied to the prediction of groundwater depth in the Ningxia area,China.The two models combine the improved dung beetle optimizer(DBO)algorithm with two deep learning models:The Multi-head Attention-Convolution Neural Network-Long Short Term Memory networks(MH-CNN-LSTM)and the Multi-head Attention-Convolution Neural Network-Gated Recurrent Unit(MH-CNN-GRU).The models with DBO show better prediction performance,with larger R(correlation coefficient),RPD(residual prediction deviation),and lower RMSE(root-mean-square error).Com-pared with the models with the original DBO,the R and RPD of models with the improved DBO increase by over 1.5%,and the RMSE decreases by over 1.8%,indicating better prediction results.In addition,compared with the multiple linear regression model,a traditional statistical model,deep learning models have better prediction performance.
基金Project supported by the National Natural Science Foundation of China(52372134,12274023)the Fundamental Re search Funds for the Central Universities(FRF-EYIT-23-04)。
文摘Rare earth-doped inorganic compounds contribute mostly to the family of persistent luminescent materials due to the versatile energy levels of rare earth ions.One of the key research aims is to match the trap level stemming from the doped rare earth ion or intrinsic defects to the electronic structure of the host,and therefore thermoluminescence measurement becomes a radical technology in studying trap depth,which is one of the significant parameters that determine the properties of persistent luminescence and photostimulated luminescence.However,the results of trap depth obtained by different thermoluminescence methods are quite different so that they are not comparable.Herein,we analyzed different thermoluminescence methods,selected and improved the traditional peak position method of T_(m)/500 to be E=(-0.94Inβ+30.09)kT_(m).Only the experimental heating rate(β)is needed additionally,but the accuracy is improved greatly in most cases.This convenient and accurate method will accelerate the discovery of novel rare earth-doped materials.
基金financially supported by the POSCO-POSTECH-RIST Convergence Research Center program funded by POSCOthe National Research Foundation (NRF) grants (RS-2024-00462912, RS-2024-00416272, RS-2024-00337012, RS-2024-00408446) funded by the Ministry of Science and ICT (MSIT) of the Korean government+2 种基金the Korea Evaluation Institute of Industrial Technology (KEIT) grant (No. 1415185027/20019169, Alchemist project) funded by the Ministry of Trade, Industry and Energy (MOTIE) of the Korean governmentthe Soseon Science fellowship funded by Community Chest of Koreathe NRF PhD fellowship (RS-2023-00275565) funded by the Ministry of Education (MOE) of the Korean government。
文摘Spatial computing and augmented reality are advancing rapidly,with the goal of seamlessly blending virtual and physical worlds.However,traditional depth-sensing systems are bulky and energy-intensive,limiting their use in wearable devices.To overcome this,recent research by X.Liu et al.presents a compact binocular metalens-based depth perception system that integrates efficient edge detection through an advanced neural network.This system enables accurate,realtime depth mapping even in complex environments,enhancing potential applications in augmented reality,robotics,and autonomous systems.
文摘对于复杂天气场景图像模糊、低对比度和颜色失真所导致的深度信息预测不准的问题,以往的研究均以标准场景的深度图作为先验信息来对该类场景进行深度估计。然而,这一方式存在先验信息精度较低等问题。对此,提出一个基于多尺度注意力机制的单目深度估计模型TalentDepth,以实现对复杂天气场景的预测。首先,在编码器中融合多尺度注意力机制,在减少计算成本的同时,保留每个通道的信息,提高特征提取的效率和能力。其次,针对图像深度不清晰的问题,基于几何一致性,提出深度区域细化(Depth Region Refinement,DSR)模块,过滤不准确的像素点,以提高深度信息的可靠性。最后,输入图像翻译模型所生成的复杂样本,并计算相应原始图像上的标准损失来指导模型的自监督训练。在NuScence,KITTI和KITTI-C这3个数据集上,相比于基线模型,所提模型对误差和精度均有优化。
文摘Depth maps play a crucial role in various practical applications such as computer vision,augmented reality,and autonomous driving.How to obtain clear and accurate depth information in video depth estimation is a significant challenge faced in the field of computer vision.However,existing monocular video depth estimation models tend to produce blurred or inaccurate depth information in regions with object edges and low texture.To address this issue,we propose a monocular depth estimation model architecture guided by semantic segmentation masks,which introduces semantic information into the model to correct the ambiguous depth regions.We have evaluated the proposed method,and experimental results show that our method improves the accuracy of edge depth,demonstrating the effectiveness of our approach.
文摘自监督单目深度估计受到了国内外研究人员的广泛关注。现有基于深度学习的自监督单目深度估计方法主要采用编码器-解码器结构。然而,这些方法在编码过程中对输入图像进行下采样操作,导致部分图像信息,尤其是图像的边界信息丢失,进而影响深度图的精度。针对上述问题,提出一种基于拉普拉斯金字塔的自监督单目深度估计方法(Self-supervised Monocular Depth Estimation Based on the Laplace Pyramid,LpDepth)。此方法的核心思想是:首先,使用拉普拉斯残差图丰富编码特征,以弥补在下采样过程中丢失的特征信息;其次,在下采样过程中使用最大池化层突显和放大特征信息,使编码器在特征提取过程中更容易地提取到训练模型所需要的特征信息;最后,使用残差模块解决过拟合问题,提高解码器对特征的利用效率。在KITTI和Make3D等数据集上对所提方法进行了测试,同时将其与现有经典方法进行了比较。实验结果证明了所提方法的有效性。
基金supported by the National Natural Science Foundation of China[Grant Nos.62205367 and 62141506]the Suzhou Basic Research Pilot Project[Grant Nos.SSD2023006 and SJC2021013]the National Key Research and Development Program of China[Grant No.2023YFF1205700].
文摘Maintaining the s-polarization state of laser beams is important to achieve high modulation depth in a laser-interference-based super-resolution structured illumination microscope(SR-SIM).However,the imperfect optical components can depolarize the laser beams hence degenerating the modulation depth.Here,we first presented a direct measurement method designed to estimate the modulation depth more precisely by shifting illumination patterns with equal phase steps.This measurement method greatly reduces the dependence of modulation depths on the samples,and then developed a polarization optimization method to achieve high modulation depth at all orientations by actively and quantitatively compensating for the additional phase difference using a combination of waveplate and a liquid crystal variable retarder(LCVR).Experimental results demonstrate that our method can achieve illumination patterns with modulation depth higher than 0.94 at three orientations with only one LCVR voltage,which enables isotropic resolution improvement.
基金funded by the Yangtze River Delta Science and Technology Innovation Community Joint Research Project(2023CSJGG1600)the Natural Science Foundation of Anhui Province(2208085MF173)Wuhu“ChiZhu Light”Major Science and Technology Project(2023ZD01,2023ZD03).
文摘In the dynamic scene of autonomous vehicles,the depth estimation of monocular cameras often faces the problem of inaccurate edge depth estimation.To solve this problem,we propose an unsupervised monocular depth estimation model based on edge enhancement,which is specifically aimed at the depth perception challenge in dynamic scenes.The model consists of two core networks:a deep prediction network and a motion estimation network,both of which adopt an encoder-decoder architecture.The depth prediction network is based on the U-Net structure of ResNet18,which is responsible for generating the depth map of the scene.The motion estimation network is based on the U-Net structure of Flow-Net,focusing on the motion estimation of dynamic targets.In the decoding stage of the motion estimation network,we innovatively introduce an edge-enhanced decoder,which integrates a convolutional block attention module(CBAM)in the decoding process to enhance the recognition ability of the edge features of moving objects.In addition,we also designed a strip convolution module to improve the model’s capture efficiency of discrete moving targets.To further improve the performance of the model,we propose a novel edge regularization method based on the Laplace operator,which effectively accelerates the convergence process of themodel.Experimental results on the KITTI and Cityscapes datasets show that compared with the current advanced dynamic unsupervised monocular model,the proposed model has a significant improvement in depth estimation accuracy and convergence speed.Specifically,the rootmean square error(RMSE)is reduced by 4.8%compared with the DepthMotion algorithm,while the training convergence speed is increased by 36%,which shows the superior performance of the model in the depth estimation task in dynamic scenes.
基金Projects(52225403,52074112)supported by the National Natural Science Foundation of ChinaProject(2022CFD009)supported by the Hubei Natural Science Foundation Innovation and Development Joint Fund Key Project,China+2 种基金Project(SDGZK2423)supported by the State Key Laboratory of Intelligent Construction and Healthy Operation and Maintenance of Deep Underground Engineering,ChinaProject(HJZKYBKT2024111)supported by the Xiangyang Federation of Social Sciences“Hanjiang Think Tank”Project,ChinaProject supported by the Hubei Superior and Distinctive Discipline Group of“New Energy Vehicle and Smart Transportation”,China。
文摘Coal seam water injection in tunnels is an effective technical measure for preventing coal mine rock bursts.This study used the improved split Hopkinson pressure bar(SHPB)to apply three equal static stresses to water-saturated coal to simulate the initial stress environment of coal at different depths.Then,dynamic mechanical experiments were conducted on the saturated coal at different depths to investigate the effects of water saturation and depth on the coal samples’dynamic mechanical properties.Under uniaxial compression and without lateral compression,the strength of coal samples decreased to varying degrees in the saturated state;under different depth conditions,the dynamic strength of coal in the saturated state decreased compared with that in the natural state.However,compared with that at 0 m,the reduction in the strength of coal under the saturated condition at 200,400,600,and 800 m was significantly reduced.The findings of this study provide a basic theoretical foundation for the prevention and control of dynamic coal mine disasters.
