We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
基于 SURF 特征点的包装空间双目视觉定位研究.
- Authors
祁晓玲
- Abstract
In order to facilitate the manipulator with the multi-degrees of freedom to recognize and grasp a specific package, accurately locate the outer edge contour of the package, and strengthen the grasping accuracy and visual feature recognition of the outer edge contour of the package by the manipulator operating system, based on the positioning of SURF feature points in binocular machine vision, the image information collection accuracy of the detection system was improved, and the key points of target package edge calibration core recognition and positioning in complex environment were determined. Based on the traditional monocular vision, the application and construction of binocular vision SURF feature points were analyzed. Taking the bottle packaging in the actual complex environment as an example, the feature extraction method of the outer edge of this kind of packaging was demonstrated, and the comparison experiment of SURF local feature extraction results was carried out. The results show that the SURF feature points and optimization measures based on binocular vision reduce the CDF value by about 46% compared with monocular recognition and positioning, provide a more accurate recognition method for the establishment of the target packaging calibration mode of the manipulator in the visual complex environment, and meet the effective positioning requirements of the target packaging recognition operation in the complex environment.
- Publication
Packaging & Food Machinery, 2022, Vol 40, Issue 2, p82
- ISSN
1005-1295
- Publication type
Article
- DOI
10.3969/j.issn.1005-1295.2022.02.015