CAJ | 학술논문

根据杂草颜色特征，提出了新的图像分割算法，在RGB空间直接将杂草从土壤背帚中分割出来。首先顺序搜索图像中每一个像素点，如果当前像素RGB值中G〉R且G〉嚣，则将该像素值置1（杂草），否则为0（背景），从而完成图像分割。然后采用8邻域消除孤立点，并确定杂草区域位置。利用VisualC＋＋开发了除草机器人杂草识别软件，设计了除草机器人结构模型。试验表明，该分割算法实时性好，可有效识别出杂草，并能够适应户外自然先变化。除草机器人机械臂能够准确定位，完成除草动作。
근거잡초안색특정，제출료신적도상분할산법，재RGB공간직접장잡초종토양배추중분할출래。수선순서수색도상중매일개상소점，여과당전상소RGB치중G〉R차G〉효，칙장해상소치치1（잡초），부칙위0（배경），종이완성도상분할。연후채용8린역소제고립점，병학정잡초구역위치。이용VisualC＋＋개발료제초궤기인잡초식별연건，설계료제초궤기인결구모형。시험표명，해분할산법실시성호，가유효식별출잡초，병능구괄응호외자연선변화。제초궤기인궤계비능구준학정위，완성제초동작。
A new segmentation algorithm of image was proposed to discriminate weeds from background by using col- or information in RGB space. Firstly, the plant-soil-residue image was analyzed and calculated pixel by pixel, pixel was considered as weed when G〉R and G~〉B and its value was set to 1 ;otherwise,the pixel was considered as back- ground and its value was set to 0. Afterwards,8-neighborhood method was applied to eliminate the isolated points and the locations of weed regions were obtained. The software of weed recognition for weeding robot was developed by means of Visual C＋＋ and a model of robot structure was designed. Experiments show that this algorithm is ro- bust to the variation of the natural light and takes less time in image processing. The mechanical arm of weeding ro bot could be precisely positioned and carry out weeding activities.