针对传统局部不变特征的景象匹配算法冗余点多、实时性差、抗几何变换不突出的情况,提出基于CenSurE-star的无人机(UAV)景象匹配算法。首先采用Cen Sur E特征星型滤波器(CenSurE-star)提取基准图和实时图中的特征点,并生成FREAK二进制...针对传统局部不变特征的景象匹配算法冗余点多、实时性差、抗几何变换不突出的情况,提出基于CenSurE-star的无人机(UAV)景象匹配算法。首先采用Cen Sur E特征星型滤波器(CenSurE-star)提取基准图和实时图中的特征点,并生成FREAK二进制描述符;然后将汉明距离作为特征点的相似性判定度量,采用K近邻距离比值的方法提取匹配点对;最后利用基于RANSAC的定位模型得到空间几何变换关系,实现图像匹配并获取定位点经纬坐标。算法性能评价实验表明,本文算法不仅相对于SIFT、SURF、ORB算法,对各种变换具有更好的鲁棒性,而且相对于改进的SIFT、SURF算法处理时间有更大程度的缩短,算法定位误差在0.8个像素内,尺度误差在0.02倍内,旋转角度误差在0.04°内。基于算法进行外场飞行实验,实验证明算法定位精度较高,可以适应地貌信息较少的环境,并能满足无人机视觉辅助导航的需求。展开更多
The sparse representation-based classification algorithm has been used for human face recognition. But an image database was restricted to human frontal faces with only slight illumination and expression changes. Crop...The sparse representation-based classification algorithm has been used for human face recognition. But an image database was restricted to human frontal faces with only slight illumination and expression changes. Cropping and normalization of the face needs to be done beforehand. This paper uses a sparse representation-based algorithm for generic image classification with some intra-class variations and background clutter. A hierarchical framework based on the sparse representation is developed which flexibly combines different global and local features. Experiments with the hierarchical framework on 25 object categories selected from the Caltech101 dataset show that exploiting the advantage of local features with the hierarchical framework improves the classification performance and that the framework is robust to image occlusions, background clutter, and viewpoint changes.展开更多
提出一种基于图像梯度旋转直方图(RHG,rotation histogram of gradients)的快速计算旋转不变特征描述符算法。RHG描述符使用直方图旋转的方法获得旋转不变性,采用直方图加权合并的方法降低边界效应引起的描述符统计矢量的突变。RHG描述...提出一种基于图像梯度旋转直方图(RHG,rotation histogram of gradients)的快速计算旋转不变特征描述符算法。RHG描述符使用直方图旋转的方法获得旋转不变性,采用直方图加权合并的方法降低边界效应引起的描述符统计矢量的突变。RHG描述符将特征点主方向的计算与描述符的计算合并,提高了计算效率。RHG描述符在图像存在尺度改变、3维视角变化引起的变形、旋转变化、照度改变和噪声等因素的影响下,具有较强的鲁棒性。RHG描述符的性能与尺度不变特征变换(SIFT,scale invariant feature transform)描述符相近,但计算速度提高2倍以上。展开更多
文摘针对传统局部不变特征的景象匹配算法冗余点多、实时性差、抗几何变换不突出的情况,提出基于CenSurE-star的无人机(UAV)景象匹配算法。首先采用Cen Sur E特征星型滤波器(CenSurE-star)提取基准图和实时图中的特征点,并生成FREAK二进制描述符;然后将汉明距离作为特征点的相似性判定度量,采用K近邻距离比值的方法提取匹配点对;最后利用基于RANSAC的定位模型得到空间几何变换关系,实现图像匹配并获取定位点经纬坐标。算法性能评价实验表明,本文算法不仅相对于SIFT、SURF、ORB算法,对各种变换具有更好的鲁棒性,而且相对于改进的SIFT、SURF算法处理时间有更大程度的缩短,算法定位误差在0.8个像素内,尺度误差在0.02倍内,旋转角度误差在0.04°内。基于算法进行外场飞行实验,实验证明算法定位精度较高,可以适应地貌信息较少的环境,并能满足无人机视觉辅助导航的需求。
基金Supported by the National Natural Science Foundation of China(No. 90820305)the National Basic Research and Development Program (973) Program of China(No. 2007CB311003)
文摘The sparse representation-based classification algorithm has been used for human face recognition. But an image database was restricted to human frontal faces with only slight illumination and expression changes. Cropping and normalization of the face needs to be done beforehand. This paper uses a sparse representation-based algorithm for generic image classification with some intra-class variations and background clutter. A hierarchical framework based on the sparse representation is developed which flexibly combines different global and local features. Experiments with the hierarchical framework on 25 object categories selected from the Caltech101 dataset show that exploiting the advantage of local features with the hierarchical framework improves the classification performance and that the framework is robust to image occlusions, background clutter, and viewpoint changes.