基于复数神经网络的双视角视觉转角测量方法  

Double-perspective visual angular measurement method based on complex neural networks

作　　者：俞翔栋 于文峰 柯瑞庭 陈洪宇 陶建峰[2,3] Yu Xiangdong;Yu Wenfeng;Ke Ruiting;Chen Hongyu;Tao Jianfeng(SMDERI,Power Plant Division,Shanghai 201108,China;School of Mechanical Engineering,Shanghai Jiao Tong University,Shanghai 201108,China;State Key Laboratory of Mechanical System and Vibration,Shanghai Jiao Tong University,Shanghai 201108,China)

机构地区：[1]中国船舶集团有限公司第七一一研究所动力装置事业部,上海201108 [2]上海交通大学机械与动力工程学院,上海201108 [3]上海交通大学机械系统与振动国家重点实验室,上海201108

出　　处：《电子测量技术》2024年第18期9-14,共6页Electronic Measurement Technology

摘　　要：为改善单视觉的转角测量方法容易受到环境或系统随机干扰的不稳定性,提出了一种基于复数神经网络的双视角视觉转角测量方法。人为进行特征提取,并评估其与角度的相关性和单调性来进行特征筛选。为解决0°和360°标签数值差距大对训练结果的影响,将角度用欧拉公式表示,并构建复数输入,复数输出的复数神经网络来进行转角计算。实验结果显示,这种测量方法在测量准度上有显著提升,相比基于深度神经网络的单视角方法,其平均误差降低0.322°,均方根误差降低0.64°,在不同环境测试集上保持高效性能。该模型在保持传统数学模型的约束和稳定性的前提下,充分利用了双视角对于环境干扰的鲁棒性,结合复数神经网络对于角度标签的强大拟合能力,提高了径向视觉角度测量的准确性和稳定性。To enhance the stability of angle measurement methods based on single-vision techniques,which are susceptible to random disturbances from environmental or systemic sources,we propose a dual-viewpoint visual angle measurement method based on complex-valued neural networks.Feature extraction is conducted manually,followed by an assessment of the features’relevance and monotonicity with respect to angles to facilitate feature selection.To address the significant numerical discrepancy between the 0°and 360°labels,which impacts training outcomes,angles are represented using Euler′s formula.This representation facilitates the construction of a complex-valued neural network with both complex inputs and outputs for angle computation.Experimental results demonstrate a significant improvement in measurement accuracy;the proposed method reduces the mean error by 0.322°and the root mean square error by 0.64°compared to methods based on deep neural networks using a single viewpoint,maintaining high performance across various environmental test sets.By leveraging the robustness against environmental disturbances provided by dual viewpoints and the strong fitting capabilities of complex-valued neural networks for angle labels,this model enhances the accuracy and stability of radial visual angle measurements while adhering to the constraints and stability of mathematical models.

关 键 词：双视角转角测量 机器视觉 复数神经网络 混合模型 

分 类 号：TN06[电子电信—物理电子学]