为提高目标6D姿态追踪网络的收敛能力和追踪精度,提出一种基于少量数据驱动的目标6D姿态追踪复用预测网络。以当前时刻的彩色及深度(red green blue and depth,RGB-D)图像和上一时刻的目标渲染值作为输入,通过2个独立的特征编码器提取...为提高目标6D姿态追踪网络的收敛能力和追踪精度,提出一种基于少量数据驱动的目标6D姿态追踪复用预测网络。以当前时刻的彩色及深度(red green blue and depth,RGB-D)图像和上一时刻的目标渲染值作为输入,通过2个独立的特征编码器提取特征矩阵,在特征编码器中引入通道注意力机制模块,保证有选择性地调整通道信息的权重;构建复用预测网络模块,将特征矩阵解耦得到旋转矩阵,通过旋转矩阵前向传播与特征矩阵融合,将融合的结果再次解耦得到物体6D姿态的旋转矩阵与平移矩阵,并采用李代数方法通过2个矩阵计算出目标的6D姿态。实验结果表明:在使用少量数据训练网络模型的情况下,与MaskFusion、“TEASER++”和se(3)-Tracknet等方法相比,所提方法能够提高目标6D姿态追踪的准确率。展开更多
目的探究巨噬细胞表面特异分子跨膜4域亚家族A成员6D(membrane-spanning 4-domains subfamily A member 6D,Ms4a6d)基因敲除对雌性小鼠生育力的影响。方法构建Ms4a6d基因敲除小鼠,以各周龄纯合Ms4a6d基因敲除(Ms4a6d^(-/-))小鼠为实验组...目的探究巨噬细胞表面特异分子跨膜4域亚家族A成员6D(membrane-spanning 4-domains subfamily A member 6D,Ms4a6d)基因敲除对雌性小鼠生育力的影响。方法构建Ms4a6d基因敲除小鼠,以各周龄纯合Ms4a6d基因敲除(Ms4a6d^(-/-))小鼠为实验组;采用qPCR、琼脂糖凝胶法鉴定小鼠基因型;运用HE染色、免疫荧光、ELISA等方法检测血清抗缪勒管激素(anti-müllerian hormone,AMH)和雌性Ms4a6d^(-/-)小鼠卵巢中巨噬细胞数量及各级卵泡构成变化;通过生育力实验比较成年Ms4a6d^(-/-)雌鼠妊娠率及平均产仔数变化。结果与同周龄野生型(Ms4a6d+/+)雌鼠比较,2周龄和4周龄的Ms4a6d^(-/-)雌鼠卵巢组织中巨噬细胞显著减少(P<0.01);8周龄时2组卵巢巨噬细胞差异无统计学意义;8周龄Ms4a6d^(-/-)雌鼠卵巢系数显著降低(P<0.01);8周龄时卵巢组织中原始卵泡、初级卵泡、次级卵泡和窦卵泡数量显著减少(P<0.05),各年龄段Ms4a6d^(-/-)雌鼠血清中AMH显著降低(P<0.05)。成年Ms4a6d^(-/-)雌鼠的平均妊娠率为56%,每胎产仔数为(4.1±1.1)只,均显著低于同龄野生型雌鼠的妊娠率(89%)和每胎产仔数[(6.3±1.2)只]。结论Ms4a6d基因敲除导致青春期前雌鼠卵巢组织中巨噬细胞数量减少,抑制其生长卵泡发育,最终表现为成年雌鼠卵巢储备减少,生育力降低。展开更多
A novel 6D dissipative model with an unstable equilibrium point is introduced herein.Some of the dynamic characteristics of the proposed model were explored via analyses and numerical simulations including critical po...A novel 6D dissipative model with an unstable equilibrium point is introduced herein.Some of the dynamic characteristics of the proposed model were explored via analyses and numerical simulations including critical points,stability,Lyapunov exponents,time phase portraits,and circuit implementation.Also,anti-synchronization phenomena were implemented on the new system.Firstly,the error dynamics is found.Then,four different controllers are adopted to stabilize this error relying on the nonlinear control technique with two main ways:linearization and Lyapunov stability theory.In comparison with previous works,the present controllers realize anti-synchronization based on another method/linearization method.Finally,a comparison between the two ways was made.The simulation results show the effectiveness and accuracy of the first analytical strategy.展开更多
Monocular 6D pose estimation is a functional task in the field of com-puter vision and robotics.In recent years,2D-3D correspondence-based methods have achieved improved performance in multiview and depth data-based s...Monocular 6D pose estimation is a functional task in the field of com-puter vision and robotics.In recent years,2D-3D correspondence-based methods have achieved improved performance in multiview and depth data-based scenes.However,for monocular 6D pose estimation,these methods are affected by the prediction results of the 2D-3D correspondences and the robustness of the per-spective-n-point(PnP)algorithm.There is still a difference in the distance from the expected estimation effect.To obtain a more effective feature representation result,edge enhancement is proposed to increase the shape information of the object by analyzing the influence of inaccurate 2D-3D matching on 6D pose regression and comparing the effectiveness of the intermediate representation.Furthermore,although the transformation matrix is composed of rotation and translation matrices from 3D model points to 2D pixel points,the two variables are essentially different and the same network cannot be used for both variables in the regression process.Therefore,to improve the effectiveness of the PnP algo-rithm,this paper designs a dual-branch PnP network to predict rotation and trans-lation information.Finally,the proposed method is verified on the public LM,LM-O and YCB-Video datasets.The ADD(S)values of the proposed method are 94.2 and 62.84 on the LM and LM-O datasets,respectively.The AUC of ADD(-S)value on YCB-Video is 81.1.These experimental results show that the performance of the proposed method is superior to that of similar methods.展开更多
文摘为提高目标6D姿态追踪网络的收敛能力和追踪精度,提出一种基于少量数据驱动的目标6D姿态追踪复用预测网络。以当前时刻的彩色及深度(red green blue and depth,RGB-D)图像和上一时刻的目标渲染值作为输入,通过2个独立的特征编码器提取特征矩阵,在特征编码器中引入通道注意力机制模块,保证有选择性地调整通道信息的权重;构建复用预测网络模块,将特征矩阵解耦得到旋转矩阵,通过旋转矩阵前向传播与特征矩阵融合,将融合的结果再次解耦得到物体6D姿态的旋转矩阵与平移矩阵,并采用李代数方法通过2个矩阵计算出目标的6D姿态。实验结果表明:在使用少量数据训练网络模型的情况下,与MaskFusion、“TEASER++”和se(3)-Tracknet等方法相比,所提方法能够提高目标6D姿态追踪的准确率。
文摘目的探究巨噬细胞表面特异分子跨膜4域亚家族A成员6D(membrane-spanning 4-domains subfamily A member 6D,Ms4a6d)基因敲除对雌性小鼠生育力的影响。方法构建Ms4a6d基因敲除小鼠,以各周龄纯合Ms4a6d基因敲除(Ms4a6d^(-/-))小鼠为实验组;采用qPCR、琼脂糖凝胶法鉴定小鼠基因型;运用HE染色、免疫荧光、ELISA等方法检测血清抗缪勒管激素(anti-müllerian hormone,AMH)和雌性Ms4a6d^(-/-)小鼠卵巢中巨噬细胞数量及各级卵泡构成变化;通过生育力实验比较成年Ms4a6d^(-/-)雌鼠妊娠率及平均产仔数变化。结果与同周龄野生型(Ms4a6d+/+)雌鼠比较,2周龄和4周龄的Ms4a6d^(-/-)雌鼠卵巢组织中巨噬细胞显著减少(P<0.01);8周龄时2组卵巢巨噬细胞差异无统计学意义;8周龄Ms4a6d^(-/-)雌鼠卵巢系数显著降低(P<0.01);8周龄时卵巢组织中原始卵泡、初级卵泡、次级卵泡和窦卵泡数量显著减少(P<0.05),各年龄段Ms4a6d^(-/-)雌鼠血清中AMH显著降低(P<0.05)。成年Ms4a6d^(-/-)雌鼠的平均妊娠率为56%,每胎产仔数为(4.1±1.1)只,均显著低于同龄野生型雌鼠的妊娠率(89%)和每胎产仔数[(6.3±1.2)只]。结论Ms4a6d基因敲除导致青春期前雌鼠卵巢组织中巨噬细胞数量减少,抑制其生长卵泡发育,最终表现为成年雌鼠卵巢储备减少,生育力降低。
文摘A novel 6D dissipative model with an unstable equilibrium point is introduced herein.Some of the dynamic characteristics of the proposed model were explored via analyses and numerical simulations including critical points,stability,Lyapunov exponents,time phase portraits,and circuit implementation.Also,anti-synchronization phenomena were implemented on the new system.Firstly,the error dynamics is found.Then,four different controllers are adopted to stabilize this error relying on the nonlinear control technique with two main ways:linearization and Lyapunov stability theory.In comparison with previous works,the present controllers realize anti-synchronization based on another method/linearization method.Finally,a comparison between the two ways was made.The simulation results show the effectiveness and accuracy of the first analytical strategy.
基金This work was supported by the National Natural Science Foundation of China(No.61871196 and 62001176)the Natural Science Foundation of Fujian Province of China(No.2019J01082 and 2020J01085)the Promotion Program for Young and Middle-aged Teachers in Science and Technology Research of Huaqiao University(ZQN-YX601).
文摘Monocular 6D pose estimation is a functional task in the field of com-puter vision and robotics.In recent years,2D-3D correspondence-based methods have achieved improved performance in multiview and depth data-based scenes.However,for monocular 6D pose estimation,these methods are affected by the prediction results of the 2D-3D correspondences and the robustness of the per-spective-n-point(PnP)algorithm.There is still a difference in the distance from the expected estimation effect.To obtain a more effective feature representation result,edge enhancement is proposed to increase the shape information of the object by analyzing the influence of inaccurate 2D-3D matching on 6D pose regression and comparing the effectiveness of the intermediate representation.Furthermore,although the transformation matrix is composed of rotation and translation matrices from 3D model points to 2D pixel points,the two variables are essentially different and the same network cannot be used for both variables in the regression process.Therefore,to improve the effectiveness of the PnP algo-rithm,this paper designs a dual-branch PnP network to predict rotation and trans-lation information.Finally,the proposed method is verified on the public LM,LM-O and YCB-Video datasets.The ADD(S)values of the proposed method are 94.2 and 62.84 on the LM and LM-O datasets,respectively.The AUC of ADD(-S)value on YCB-Video is 81.1.These experimental results show that the performance of the proposed method is superior to that of similar methods.