期刊
INTERNATIONAL JOURNAL OF AGRICULTURAL AND BIOLOGICAL ENGINEERING
卷 14, 期 4, 页码 217-225出版社
CHINESE ACAD AGRICULTURAL ENGINEERING
DOI: 10.25165/j.ijabe.20211404.6315
关键词
machine vision; crop rows detection; navigation; multi-ROI
资金
- National Key Research and Development Program of China [2017YFD0700902]
- University Synergy Innovation Program of Anhui Province [GXXT-2020-011]
The study proposed an algorithm for detecting crop rows in maize fields based on adaptive multi-region of interest (multi-ROI), achieving a detection accuracy of 95.3% with an average computation time of 240.8 ms. The results indicate that the method performs well in field navigation and meets real-time and accuracy requirements.
Crop rows detection in maize fields remains a challenging problem due to variation in illumination and weeds interference under field conditions. This study proposed an algorithm for detecting crop rows based on adaptive multi-region of interest (multi-ROI). First, the image was segmented into crop and soil and divided into several horizontally labeled strips. Feature points were located in the first image strip and initial ROI was determined. Then, the ROI window was shifted upward. For the next image strip, the operations for the previous strip were repeated until multiple ROIs were obtained. Finally, the least square method was carried out to extract navigation lines and detection lines in multi-ROI. The detection accuracy of the method was 95.3%. The average computation time was 240.8 ms. The results suggest that the proposed method has generally favorable performance and can meet the real-time and accuracy requirements for field navigation.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据