摘要
为了解决扑翼飞行机器人实时控制过程中视觉图像自主识别和宽视野导航规划的难题,实现基于视觉的扑翼飞行机器人的宽视野规划导航控制,提出了基于聚类分析的扑翼飞行机器人视觉图像处理方法和边缘检测方法,并且基于块匹配的图像拼接方法,构建了基于遥操作的扑翼飞行机器人视觉感知构架。利用聚类分析方法对扑翼飞行机器人视觉图像数据进行分类,并利用典型的边缘检测算法对聚类分析处理后的机器人图像进行图像边缘检测,合理提取了扑翼飞行机器人视觉目标轮廓特征和环境边缘特征。利用块匹配对扑翼飞行机器人视觉图像数据进行图像配准,并利用图像融合算法提高了图像清晰度。以扑翼飞行机器人和视觉相机搭建了扑翼飞行机器人实验平台。对基于聚类分析的飞行机器人视觉图像处理方法和图像拼接方法进行了实验验证,系列实验结果验证了所提算法的有效性。
To solve the problems of visual image autonomous recognition and wide-field navigation planning in the real-time control process of flapping-wing flying robots and realize the wide-field planning navigation control of these robots based on vision,we propose a visual image processing method and edge detection method for flapping-wing flying robots based on clustering analysis and an image mosaic method based on block matching to construct a vision perception framework of flapping-wing flying robots based on teleoperation.The visual image data of flapping-wing flying robots are classified using clustering analysis,and image edge detection is performed on the robot image after clustering analysis processing using a typical edge detection algorithm.The contour features of the visual object and the environmental edge features of the flapping-wing flying robot are reasonably extracted.Block matching is performed for image registration of the flapping-wing flying robot vision image data,and an image fusion algorithm is used to improve image clarity.A flapping-wing flying robot experimental platform is constructed with a flapping-wing flying robot and a visual camera.The flight robot vision image processing method and image mosaic method based on clustering analysis are experimentally verified.A series of experimental results verify the effectiveness of the proposed algorithm.
作者
丁伟
张峰
崔龙
宋敏
刘钊铭
王宏伟
缪磊
DING Wei;ZHANG Feng;CUI Long;SONG Min;LIU Zhaoming;WANG Hongwei;MIAO Lei(College of Automation,Shenyang Institute of Engineering,Shenyang 110136,China;State Key Laboratory of Robotics,Shenyang Institute of Automation,Chinese Academy of Sciences,Shenyang 110016,China)
出处
《信息与控制》
CSCD
北大核心
2024年第3期416-432,共17页
Information and Control
基金
国家自然科学基金合作计划资助项目(U2013208)
中国科学院青年创新促进会项目(2020202)
沈阳市中青年科技创新人才支持计划项目(RC210314)
关键词
扑翼飞行机器人
视觉图像处理
聚类分析
边缘检测
图像拼接
flapping-wing flying robot
visual image processing
cluster analysis
edge detection
image stitching
