针对动态场景下视觉SLAM(Simultaneous Localization and Mapping)系统中深度学习分割网络实时性不足,以及相机非期望运动导致位姿估计偏差的问题,提出一种基于跨域掩膜分割的视觉SLAM算法.该算法采用轻量化YOLO-fastest网络结合背景减...针对动态场景下视觉SLAM(Simultaneous Localization and Mapping)系统中深度学习分割网络实时性不足,以及相机非期望运动导致位姿估计偏差的问题,提出一种基于跨域掩膜分割的视觉SLAM算法.该算法采用轻量化YOLO-fastest网络结合背景减除法实现运动物体检测,利用深度图结合深度阈值分割构建跨域掩膜分割机制,并设计相机运动几何校正策略补偿检测框坐标误差,在实现运动物体分割的同时提升处理速度.为优化特征点利用率,采用金字塔光流对动态特征点进行帧间连续跟踪与更新,同时确保仅由静态特征点参与位姿估计过程.在TUM数据集上进行系统性评估,实验结果表明,相比于ORB-SLAM3算法,该算法的绝对位姿误差平均降幅达97.1%,与使用深度学习分割网络的DynaSLAM和DS-SLAM的动态SLAM算法相比,其单帧跟踪时间大幅减少,在精度与效率之间实现了更好的平衡.展开更多
Since Tian Jun proposed the difference expansion embedding technique,based on which,many reversible watermarking techniques were proposed.However,these methods do not perform well when the payload is high.In this pape...Since Tian Jun proposed the difference expansion embedding technique,based on which,many reversible watermarking techniques were proposed.However,these methods do not perform well when the payload is high.In this paper,we proposed an expandable difference threshold controlled scheme for these three methods.Experiments show that our scheme improves the performance of these three methods for heavy payload.展开更多
In order to simplify the three-dimensional building group model, this paper proposes a clustering generalization method based on visual cognitive theory. The method uses road elements to roughly divide scenes, and the...In order to simplify the three-dimensional building group model, this paper proposes a clustering generalization method based on visual cognitive theory. The method uses road elements to roughly divide scenes, and then uses spatial cognitive elements such as direction, area, height and their topological constraints to classify them precisely, so as to make them conform to the urban morphological characteristics. Delaunay triangulation network and boundary tracking synthesis algorithm are used to merge and summarize the models, and the models are stored hierarchically. The proposed algorithm should be verified experimentally with a typical urban complex model. The experimental results show that the efficiency of the method used in this paper is at least 20% higher than that of previous one, and with the growth of test data, the higher efficiency is improved. The classification results conform to human cognitive habits, and the generalization levels of different models can be relatively unified by adaptive control of each threshold in the clustering generalization process.展开更多
根据人眼对彩色图像不同颜色通道的敏感度不同,利用掩蔽效应对人眼感知立体图像质量产生的影响,提出了一种基于视觉阈值分析和通道融合的彩色图像客观质量评价方法。利用人眼视觉阈值确定立体图像的失真是否在人眼可察觉的范围,若失真...根据人眼对彩色图像不同颜色通道的敏感度不同,利用掩蔽效应对人眼感知立体图像质量产生的影响,提出了一种基于视觉阈值分析和通道融合的彩色图像客观质量评价方法。利用人眼视觉阈值确定立体图像的失真是否在人眼可察觉的范围,若失真程度小于视觉掩蔽阈值,则认为没有失真。利用原始和失真彩色图像RGB三通道各自左视点差值图和右视点差值图的奇异值与人眼视觉掩蔽阈值图的奇异值距离来衡量失真图像左右视点图像的质量。原始和失真图像对的绝对差图之差值图像和原始图像对的双目恰可察觉失真阈值图之间的奇异值距离被用于评价失真立体图像的深度感知好坏。不同失真类型下,左右视点质量融合以及左右视点评价和深度感知评价的融合其加权权值不同。对JPEG压缩、JPEG2000压缩、高斯白噪声、高斯模糊和H.264编码5种不同程度失真的312幅退化图像进行了测试,结果显示本文方法与主观感知有较好的一致性,总体CC(Pearson Linear Correlation Coefficient)达到0.94,总体SROCC(Spearman Rank Order Correlation Coefficient)达到0.94,整体均方根误差(RMSE)控制在5.9以内。展开更多
文摘针对动态场景下视觉SLAM(Simultaneous Localization and Mapping)系统中深度学习分割网络实时性不足,以及相机非期望运动导致位姿估计偏差的问题,提出一种基于跨域掩膜分割的视觉SLAM算法.该算法采用轻量化YOLO-fastest网络结合背景减除法实现运动物体检测,利用深度图结合深度阈值分割构建跨域掩膜分割机制,并设计相机运动几何校正策略补偿检测框坐标误差,在实现运动物体分割的同时提升处理速度.为优化特征点利用率,采用金字塔光流对动态特征点进行帧间连续跟踪与更新,同时确保仅由静态特征点参与位姿估计过程.在TUM数据集上进行系统性评估,实验结果表明,相比于ORB-SLAM3算法,该算法的绝对位姿误差平均降幅达97.1%,与使用深度学习分割网络的DynaSLAM和DS-SLAM的动态SLAM算法相比,其单帧跟踪时间大幅减少,在精度与效率之间实现了更好的平衡.
基金the National High Technology Research and Development Program (863) of China (No.2007AA02Z452) the National Natural Science Foundation of China (Nos.30570511 and 30770589)
文摘Since Tian Jun proposed the difference expansion embedding technique,based on which,many reversible watermarking techniques were proposed.However,these methods do not perform well when the payload is high.In this paper,we proposed an expandable difference threshold controlled scheme for these three methods.Experiments show that our scheme improves the performance of these three methods for heavy payload.
文摘In order to simplify the three-dimensional building group model, this paper proposes a clustering generalization method based on visual cognitive theory. The method uses road elements to roughly divide scenes, and then uses spatial cognitive elements such as direction, area, height and their topological constraints to classify them precisely, so as to make them conform to the urban morphological characteristics. Delaunay triangulation network and boundary tracking synthesis algorithm are used to merge and summarize the models, and the models are stored hierarchically. The proposed algorithm should be verified experimentally with a typical urban complex model. The experimental results show that the efficiency of the method used in this paper is at least 20% higher than that of previous one, and with the growth of test data, the higher efficiency is improved. The classification results conform to human cognitive habits, and the generalization levels of different models can be relatively unified by adaptive control of each threshold in the clustering generalization process.
文摘根据人眼对彩色图像不同颜色通道的敏感度不同,利用掩蔽效应对人眼感知立体图像质量产生的影响,提出了一种基于视觉阈值分析和通道融合的彩色图像客观质量评价方法。利用人眼视觉阈值确定立体图像的失真是否在人眼可察觉的范围,若失真程度小于视觉掩蔽阈值,则认为没有失真。利用原始和失真彩色图像RGB三通道各自左视点差值图和右视点差值图的奇异值与人眼视觉掩蔽阈值图的奇异值距离来衡量失真图像左右视点图像的质量。原始和失真图像对的绝对差图之差值图像和原始图像对的双目恰可察觉失真阈值图之间的奇异值距离被用于评价失真立体图像的深度感知好坏。不同失真类型下,左右视点质量融合以及左右视点评价和深度感知评价的融合其加权权值不同。对JPEG压缩、JPEG2000压缩、高斯白噪声、高斯模糊和H.264编码5种不同程度失真的312幅退化图像进行了测试,结果显示本文方法与主观感知有较好的一致性,总体CC(Pearson Linear Correlation Coefficient)达到0.94,总体SROCC(Spearman Rank Order Correlation Coefficient)达到0.94,整体均方根误差(RMSE)控制在5.9以内。
