摘要
基于机器视觉的田间车辆自动导航是农用车辆导航的热门研究方向,但含较密集杂草的农田作物行提取,目前依然是个难题。该文提出一种适用于密集杂草农田的,主要基于频率和颜色信息的农田图像分割算法。通过小波多分辨率分解后构建的频率总量指标,利用作物产生主频信息的总量优势,结合作物行的交替及最大类间方差法、颜色模型分量变换,实现农田杂草的去除,并通过最小二乘法拟合直线,实现农田作物行提取。实验表明算法能有效克服密集杂草干扰,针对480′640像素大小图像,单幅处理时间平均为132 ms。
Vision-based agricultural vehicle navigation has become a popular research area of automated guidance, however, crop row detection in high weeds field is still a challenging topic. An image segmentation method mainly based on frequency and color information is proposed to remove weeds. The algorithm is based on total frequency parameters, more total crop frequency, alternation regular of crop rows, Otsu method and color model transformation. The total frequency parameters are obtained from wavelet multi-resolution decomposition. The least square method is used in fitting straight line to detect the crop rows. Experiments show that the algorithm can effectively overcome the high weeds. The average processing time of a single 480 ′640 pixels image is 132 ms.
出处
《电子与信息学报》
EI
CSCD
北大核心
2016年第1期63-70,共8页
Journal of Electronics & Information Technology
基金
国家自然科学基金(61272311)
浙江省自然科学基金重点项目(LZ15F020004)
机械工程浙江省高校重中之重学科和浙江理工大学重点实验室优秀青年人才培养基金(ZSTUME01B17)
计算机应用创新重点学科研究生创新研究项目(XDY14003)
浙江理工大学科研启动基金(13032156-Y)
浙江理工大学521资助计划项目~~
关键词
田间导航
作物行
小波变换
最大类间方差
Agriculture navigation
Crop rows
Wavelet transformation
Otsu
