Conventional feature detection algorithms are largely based on clustered two-dimensional (2D) blocks of information. However, corners located at the centre of gradually greying blocks of information cannot be extracted using these algorithms. The edge feature points described by the algorithms are often affected by background changes, leading to significant differences in the descriptors for the same feature. These issues are detrimental to subsequent matching processes. Therefore, we propose a new feature detection method that will provide more useful corner information for subsequent tracking and detection processes, particularly for edge features. The edge information of corners is used to search for points that satisfy the requirements for inner greyscale consistency. The points are then used to construct point-symmetric structures. The zeroth-order inner greyscale data, first-order gradient orientation differences, and angular directions of the point-symmetric connections of the structures are considered structural attributes, which help search for feature points. Similar feature points are then clustered using a hierarchical clustering algorithm, followed by extracting the feature points from point pair features of the same type. It was experimentally demonstrated that the proposed point-symmetric structural features would help increase the number of valid feature points that can be extracted from an image.

中文翻译：

---

基于点对层次聚类的特征提取方法

传统的特征检测算法主要基于聚类的二维 (2D) 信息块。然而，使用这些算法无法提取位于逐渐变灰的信息块中心的角点。算法描述的边缘特征点经常受到背景变化的影响，导致相同特征的描述符存在显着差异。这些问题不利于后续的匹配过程。因此，我们提出了一种新的特征检测方法，它将为后续的跟踪和检测过程提供更多有用的角点信息，尤其是边缘特征。角点的边缘信息用于搜索满足内部灰度一致性要求的点。然后使用这些点来构建点对称结构。零阶内部灰度数据、一阶梯度方向差异和结构点对称连接的角方向被视为结构属性，有助于搜索特征点。然后使用层次聚类算法对相似的特征点进行聚类，然后从相同类型的点对特征中提取特征点。实验证明，所提出的点对称结构特征将有助于增加可以从图像中提取的有效特征点的数量。然后使用层次聚类算法对相似的特征点进行聚类，然后从相同类型的点对特征中提取特征点。实验证明，所提出的点对称结构特征将有助于增加可以从图像中提取的有效特征点的数量。然后使用层次聚类算法对相似的特征点进行聚类，然后从相同类型的点对特征中提取特征点。实验证明，所提出的点对称结构特征将有助于增加可以从图像中提取的有效特征点的数量。