Augmented solar images were used to research the adaptability of four representative image extraction and matching algorithms in space weather domain.These include the scale-invariant feature transform algorithm,speed...Augmented solar images were used to research the adaptability of four representative image extraction and matching algorithms in space weather domain.These include the scale-invariant feature transform algorithm,speeded-up robust features algorithm,binary robust invariant scalable keypoints algorithm,and oriented fast and rotated brief algorithm.The performance of these algorithms was estimated in terms of matching accuracy,feature point richness,and running time.The experiment result showed that no algorithm achieved high accuracy while keeping low running time,and all algorithms are not suitable for image feature extraction and matching of augmented solar images.To solve this problem,an improved method was proposed by using two-frame matching to utilize the accuracy advantage of the scale-invariant feature transform algorithm and the speed advantage of the oriented fast and rotated brief algorithm.Furthermore,our method and the four representative algorithms were applied to augmented solar images.Our application experiments proved that our method achieved a similar high recognition rate to the scale-invariant feature transform algorithm which is significantly higher than other algorithms.Our method also obtained a similar low running time to the oriented fast and rotated brief algorithm,which is significantly lower than other algorithms.展开更多
针对工业场景下经典迭代最近点(iterative closest point,ICP)算法在点云位姿估计中初始位姿敏感度高、迭代时间长的问题,提出一种基于RGB图像的快速点云配准方法。分别采集RGB图像和点云数据,使用ORB(oriented FAST and rotated BRIEF...针对工业场景下经典迭代最近点(iterative closest point,ICP)算法在点云位姿估计中初始位姿敏感度高、迭代时间长的问题,提出一种基于RGB图像的快速点云配准方法。分别采集RGB图像和点云数据,使用ORB(oriented FAST and rotated BRIEF)算法提取RGB图像特征点,利用Brute-Force算法进行初始匹配,采用随机采样一致性算法优化匹配,得到单应矩阵和旋转平移矩阵,求解汽车零配件初始位姿。进一步采用主成分分析法和双向KD树近邻搜索算法对预处理后的点云数据进行精确配准。实验结果表明,所提算法相较ICP算法,在配准速度和精度上分别提高了87.2%和5.0%,相对于FR-ICP(fast and robust iterative closest point)算法,在配准精度相当的情况下,配准速度提高了55%。展开更多
针对一些缺少参考对齐的本体匹配任务,提出一种基于深度无监督学习的匹配技术,通过对文本的上下文信息进行学习,提取到抽象文本特征,以此找到对齐。由于高维度输入会影响计算的效率,针对本体的多种描述构建CNN(convolutional neural net...针对一些缺少参考对齐的本体匹配任务,提出一种基于深度无监督学习的匹配技术,通过对文本的上下文信息进行学习,提取到抽象文本特征,以此找到对齐。由于高维度输入会影响计算的效率,针对本体的多种描述构建CNN(convolutional neural network)模块并且和不同的RNN(recurrent neural network)串行连接实现特征降维,提出一种改进的基于BiLSTM(bidirectional long and short term memory neural network)的注意力机制来提取较好的抽象特征。提出一种多主导的对齐集成策略将本体不同层次的对齐进行合并,提高匹配的质量。实验在OAEI(ontology alignment evaluation initiative)的benchmark测试集上进行,提出方法的评价指标较高,并且和其它匹配系统作比较,高质量的对齐验证了所提方法具有一定的先进性和创新性。展开更多
基金Supported by the Key Research Program of the Chinese Academy of Sciences(ZDRE-KT-2021-3)。
文摘Augmented solar images were used to research the adaptability of four representative image extraction and matching algorithms in space weather domain.These include the scale-invariant feature transform algorithm,speeded-up robust features algorithm,binary robust invariant scalable keypoints algorithm,and oriented fast and rotated brief algorithm.The performance of these algorithms was estimated in terms of matching accuracy,feature point richness,and running time.The experiment result showed that no algorithm achieved high accuracy while keeping low running time,and all algorithms are not suitable for image feature extraction and matching of augmented solar images.To solve this problem,an improved method was proposed by using two-frame matching to utilize the accuracy advantage of the scale-invariant feature transform algorithm and the speed advantage of the oriented fast and rotated brief algorithm.Furthermore,our method and the four representative algorithms were applied to augmented solar images.Our application experiments proved that our method achieved a similar high recognition rate to the scale-invariant feature transform algorithm which is significantly higher than other algorithms.Our method also obtained a similar low running time to the oriented fast and rotated brief algorithm,which is significantly lower than other algorithms.
文摘针对工业场景下经典迭代最近点(iterative closest point,ICP)算法在点云位姿估计中初始位姿敏感度高、迭代时间长的问题,提出一种基于RGB图像的快速点云配准方法。分别采集RGB图像和点云数据,使用ORB(oriented FAST and rotated BRIEF)算法提取RGB图像特征点,利用Brute-Force算法进行初始匹配,采用随机采样一致性算法优化匹配,得到单应矩阵和旋转平移矩阵,求解汽车零配件初始位姿。进一步采用主成分分析法和双向KD树近邻搜索算法对预处理后的点云数据进行精确配准。实验结果表明,所提算法相较ICP算法,在配准速度和精度上分别提高了87.2%和5.0%,相对于FR-ICP(fast and robust iterative closest point)算法,在配准精度相当的情况下,配准速度提高了55%。
文摘针对一些缺少参考对齐的本体匹配任务,提出一种基于深度无监督学习的匹配技术,通过对文本的上下文信息进行学习,提取到抽象文本特征,以此找到对齐。由于高维度输入会影响计算的效率,针对本体的多种描述构建CNN(convolutional neural network)模块并且和不同的RNN(recurrent neural network)串行连接实现特征降维,提出一种改进的基于BiLSTM(bidirectional long and short term memory neural network)的注意力机制来提取较好的抽象特征。提出一种多主导的对齐集成策略将本体不同层次的对齐进行合并,提高匹配的质量。实验在OAEI(ontology alignment evaluation initiative)的benchmark测试集上进行,提出方法的评价指标较高,并且和其它匹配系统作比较,高质量的对齐验证了所提方法具有一定的先进性和创新性。
