Low-light image enhancement is one of the most active research areas in the field of computer vision in recent years.In the low-light image enhancement process,loss of image details and increase in noise occur inevita...Low-light image enhancement is one of the most active research areas in the field of computer vision in recent years.In the low-light image enhancement process,loss of image details and increase in noise occur inevitably,influencing the quality of enhanced images.To alleviate this problem,a low-light image enhancement model called RetinexNet model based on Retinex theory was proposed in this study.The model was composed of an image decomposition module and a brightness enhancement module.In the decomposition module,a convolutional block attention module(CBAM)was incorporated to enhance feature representation capacity of the network,focusing on crucial features and suppressing irrelevant ones.A multifeature fusion denoising module was designed within the brightness enhancement module,circumventing the issue of feature loss during downsampling.The proposed model outperforms the existing algorithms in terms of PSNR and SSIM metrics on the publicly available datasets LOL and MIT-Adobe FiveK,as well as gives superior results in terms of NIQE metrics on the publicly available dataset LIME.展开更多
In this study,an underwater image enhancement method based on multi-scale adversarial network was proposed to solve the problem of detail blur and color distortion in underwater images.Firstly,the local features of ea...In this study,an underwater image enhancement method based on multi-scale adversarial network was proposed to solve the problem of detail blur and color distortion in underwater images.Firstly,the local features of each layer were enhanced into the global features by the proposed residual dense block,which ensured that the generated images retain more details.Secondly,a multi-scale structure was adopted to extract multi-scale semantic features of the original images.Finally,the features obtained from the dual channels were fused by an adaptive fusion module to further optimize the features.The discriminant network adopted the structure of the Markov discriminator.In addition,by constructing mean square error,structural similarity,and perceived color loss function,the generated image is consistent with the reference image in structure,color,and content.The experimental results showed that the enhanced underwater image deblurring effect of the proposed algorithm was good and the problem of underwater image color bias was effectively improved.In both subjective and objective evaluation indexes,the experimental results of the proposed algorithm are better than those of the comparison algorithm.展开更多
【目的】煤矿井下普遍存在低照度、弱纹理和结构化的特征退化场景,导致视觉SLAM(visual simultaneous localization and mapping)系统面临有效特征不足或误匹配率高的问题,严重制约了其定位的准确性和鲁棒性。【方法】提出一种基于边缘...【目的】煤矿井下普遍存在低照度、弱纹理和结构化的特征退化场景,导致视觉SLAM(visual simultaneous localization and mapping)系统面临有效特征不足或误匹配率高的问题,严重制约了其定位的准确性和鲁棒性。【方法】提出一种基于边缘感知增强的视觉SLAM方法。首先,构建了边缘感知约束的低光图像增强模块。通过自适应尺度的梯度域引导滤波器优化Retinex算法,以获得纹理清晰光照均匀的图像,从而显著提升了在低光照和不均匀光照条件下特征提取性能。其次,在视觉里程计中构建了边缘感知增强的特征提取和匹配模块,通过点线特征融合策略有效增强了弱纹理和结构化场景中特征的可检测性和匹配准确性。具体使用边缘绘制线特征提取算法(edge drawing lines,EDLines)提取线特征,定向FAST和旋转BRIEF点特征提取算法(oriented fast and rotated brief,ORB)提取点特征,并利用基于网格运动统计(grid-based motion statistics,GMS)和比值测试匹配算法进行精确匹配。最后,将该方法与ORB-SLAM2、ORB-SLAM3在TUM数据集和煤矿井下实景数据集上进行了全面实验验证,涵盖图像增强、特征匹配和定位等多个环节。【结果和结论】结果表明:(1)在TUM数据集上的测试结果显示,所提方法与ORB-SLAM2相比,绝对轨迹误差、相对轨迹误差的均方根误差分别降低了4%~38.46%、8.62%~50%;与ORB-SLAM3相比,绝对轨迹误差、相对轨迹误差的均方根误差分别降低了0~61.68%、3.63%~47.05%。(2)在煤矿井下实景实验中,所提方法的定位轨迹更接近于相机运动参考轨迹。(3)有效提高了视觉SLAM在煤矿井下特征退化场景中的准确性和鲁棒性,为视觉SLAM技术在煤矿井下的应用提供了技术解决方案。研究面向井下特征退化场景的视觉SLAM方法,对于推动煤矿井下移动式装备机器人化具有重要意义。展开更多
针对遥感地物建筑物图像目标尺度差异大、样本空间分布不均衡、地物边界模糊、场景区域跨度大所导致的分割效果不佳问题,本文提出一种融合动态特征增强高精度遥感建筑物分割算法。首先,构建New_GhostNetV2网络,利用自适应上下文感知卷积...针对遥感地物建筑物图像目标尺度差异大、样本空间分布不均衡、地物边界模糊、场景区域跨度大所导致的分割效果不佳问题,本文提出一种融合动态特征增强高精度遥感建筑物分割算法。首先,构建New_GhostNetV2网络,利用自适应上下文感知卷积,增强算法对样本空间特征的捕捉能力。其次,采用Ghost Convolution结合跳跃连接和特征分支策略设计多层级信息增强模块,增强特征整合。随后引入级联注意力CGA(cascaded group attention),通过组内独立注意力计算,加强模型对多样化地物形态的适应性。最后,通过动态深度特征增强器构造特征融合模块,进一步加强模型捕获能力。在WHU数据集上实验结果表明:改进算法较基线模型F1-Score提高8.57%,mIoU提高12.48%,与其他主流语义分割模型相比,改进DeepLabv3+具有更好的分割精度。展开更多
文摘Low-light image enhancement is one of the most active research areas in the field of computer vision in recent years.In the low-light image enhancement process,loss of image details and increase in noise occur inevitably,influencing the quality of enhanced images.To alleviate this problem,a low-light image enhancement model called RetinexNet model based on Retinex theory was proposed in this study.The model was composed of an image decomposition module and a brightness enhancement module.In the decomposition module,a convolutional block attention module(CBAM)was incorporated to enhance feature representation capacity of the network,focusing on crucial features and suppressing irrelevant ones.A multifeature fusion denoising module was designed within the brightness enhancement module,circumventing the issue of feature loss during downsampling.The proposed model outperforms the existing algorithms in terms of PSNR and SSIM metrics on the publicly available datasets LOL and MIT-Adobe FiveK,as well as gives superior results in terms of NIQE metrics on the publicly available dataset LIME.
文摘In this study,an underwater image enhancement method based on multi-scale adversarial network was proposed to solve the problem of detail blur and color distortion in underwater images.Firstly,the local features of each layer were enhanced into the global features by the proposed residual dense block,which ensured that the generated images retain more details.Secondly,a multi-scale structure was adopted to extract multi-scale semantic features of the original images.Finally,the features obtained from the dual channels were fused by an adaptive fusion module to further optimize the features.The discriminant network adopted the structure of the Markov discriminator.In addition,by constructing mean square error,structural similarity,and perceived color loss function,the generated image is consistent with the reference image in structure,color,and content.The experimental results showed that the enhanced underwater image deblurring effect of the proposed algorithm was good and the problem of underwater image color bias was effectively improved.In both subjective and objective evaluation indexes,the experimental results of the proposed algorithm are better than those of the comparison algorithm.
文摘【目的】煤矿井下普遍存在低照度、弱纹理和结构化的特征退化场景,导致视觉SLAM(visual simultaneous localization and mapping)系统面临有效特征不足或误匹配率高的问题,严重制约了其定位的准确性和鲁棒性。【方法】提出一种基于边缘感知增强的视觉SLAM方法。首先,构建了边缘感知约束的低光图像增强模块。通过自适应尺度的梯度域引导滤波器优化Retinex算法,以获得纹理清晰光照均匀的图像,从而显著提升了在低光照和不均匀光照条件下特征提取性能。其次,在视觉里程计中构建了边缘感知增强的特征提取和匹配模块,通过点线特征融合策略有效增强了弱纹理和结构化场景中特征的可检测性和匹配准确性。具体使用边缘绘制线特征提取算法(edge drawing lines,EDLines)提取线特征,定向FAST和旋转BRIEF点特征提取算法(oriented fast and rotated brief,ORB)提取点特征,并利用基于网格运动统计(grid-based motion statistics,GMS)和比值测试匹配算法进行精确匹配。最后,将该方法与ORB-SLAM2、ORB-SLAM3在TUM数据集和煤矿井下实景数据集上进行了全面实验验证,涵盖图像增强、特征匹配和定位等多个环节。【结果和结论】结果表明:(1)在TUM数据集上的测试结果显示,所提方法与ORB-SLAM2相比,绝对轨迹误差、相对轨迹误差的均方根误差分别降低了4%~38.46%、8.62%~50%;与ORB-SLAM3相比,绝对轨迹误差、相对轨迹误差的均方根误差分别降低了0~61.68%、3.63%~47.05%。(2)在煤矿井下实景实验中,所提方法的定位轨迹更接近于相机运动参考轨迹。(3)有效提高了视觉SLAM在煤矿井下特征退化场景中的准确性和鲁棒性,为视觉SLAM技术在煤矿井下的应用提供了技术解决方案。研究面向井下特征退化场景的视觉SLAM方法,对于推动煤矿井下移动式装备机器人化具有重要意义。
文摘针对遥感地物建筑物图像目标尺度差异大、样本空间分布不均衡、地物边界模糊、场景区域跨度大所导致的分割效果不佳问题,本文提出一种融合动态特征增强高精度遥感建筑物分割算法。首先,构建New_GhostNetV2网络,利用自适应上下文感知卷积,增强算法对样本空间特征的捕捉能力。其次,采用Ghost Convolution结合跳跃连接和特征分支策略设计多层级信息增强模块,增强特征整合。随后引入级联注意力CGA(cascaded group attention),通过组内独立注意力计算,加强模型对多样化地物形态的适应性。最后,通过动态深度特征增强器构造特征融合模块,进一步加强模型捕获能力。在WHU数据集上实验结果表明:改进算法较基线模型F1-Score提高8.57%,mIoU提高12.48%,与其他主流语义分割模型相比,改进DeepLabv3+具有更好的分割精度。
