This paper proposes a new approach to achieve direct visual servoing (DVS) based on discrete orthogonal moments (DOM). DVS is conducted whereby the extraction of geometric primitives, matching and tracking steps in the conventional feature-based visual servoing pipeline can be bypassed. Although DVS enables highly precise positioning, and suffers from a small convergence domain and poor robustness, due to the high non-linearity of the cost function to be minimized and the presence of redundant data between visual features. To tackle these issues, we propose a generic and augmented framework to take DOM as visual features into consideration. Through taking Tchebichef, Krawtchouk and Hahn moments as examples, we not only present the strategies for adaptive adjusting the parameters and orders of the visual features, but also exhibit the analytical formulation of the associated interaction matrix. Simulations demonstrate the robustness and accuracy of our method, as well as the advantages over the state of the art. The real experiments have also been performed to validate the effectiveness of our approach.

翻译：本文提出了一种基于离散正交矩（DOM）实现直接视觉伺服（DVS）的新方法。该方法通过绕过传统基于特征的视觉伺服流程中的几何基元提取、匹配与跟踪步骤，实现了直接视觉伺服。尽管DVS能够实现高精度定位，但由于待最小化代价函数的高度非线性以及视觉特征间存在冗余数据，其收敛域较小且鲁棒性较差。针对这些问题，我们提出了一种通用且增强的框架，将离散正交矩作为视觉特征。以Tchebichef矩、Krawtchouk矩和Hahn矩为例，我们不仅给出了视觉特征参数与阶次的自适应调整策略，还推导了相关交互矩阵的解析表达式。仿真结果验证了所提出方法的鲁棒性与精度，以及相较于当前先进方法的优势。此外，通过真实实验进一步证明了本方法的有效性。