毕敏娜,张铁民,庄晓霖,杨秀丽,梁莉,焦培荣.基于色差信息多色彩模型的黄羽鸡快速分割方法[J].农业机械学报,2016,47(12):293-298,308.
Bi Minna,Zhang Tiemin,Zhuang Xiaolin,Yang Xiuli,Liang Li,Jiao Peirong.Fast Segmentation Method of Yellow Feather Chicken Based on Difference of Color Information in Different Color Models[J].Transactions of the Chinese Society for Agricultural Machinery,2016,47(12):293-298,308.
摘要点击次数: 2352
全文下载次数: 1311
基于色差信息多色彩模型的黄羽鸡快速分割方法   [下载全文]
Fast Segmentation Method of Yellow Feather Chicken Based on Difference of Color Information in Different Color Models   [Download Pdf][in English]
投稿时间:2016-08-03  
DOI:10.6041/j.issn.1000-1298.2016.12.036
中文关键词:  黄羽鸡  色彩模型  色差信息  机器视觉  图像分割
基金项目:国家自然科学基金项目(51177053)、广东省省级科技计划项目(2014A050503061)和国际科技合作领域项目
作者单位
毕敏娜 华南农业大学 
张铁民 华南农业大学 
庄晓霖 华南农业大学 
杨秀丽 华南农业大学 
梁莉 华南农业大学 
焦培荣 华南农业大学 
中文摘要:快速准确分割出复杂背景下的鸡只图像,是应用机器视觉系统快速识别实际饲养环境下病鸡的关键步骤。以某鸡舍散养的黄羽肉鸡为分割目标,提出了一种基于色差信息的多色彩模型鸡只分割方法。首先对200幅自然环境下拍摄的图像在常用的色彩模型下,分析了鸡冠、鸡身羽毛、鸡肚羽毛以及背景的颜色特征,利用背景在RGB色彩模型的R、G、B三分量色差信息特征进行一次分割,去除大部分的背景,然后转换到HSV色彩模型,获取黄羽鸡不同部位的H分量阈值,再由H阈值范围提取鸡身、鸡冠实现二次分割,最终得到分割目标。实验结果表明所提方法实际分割正确率为86.3%,优于L*a*b*色彩模型聚类的78.4%。所提方法复杂度小,运算时间短,适用于实时分割场合。
Bi Minna  Zhang Tiemin  Zhuang Xiaolin  Yang Xiuli  Liang Li  Jiao Peirong
South China Agricultural University,South China Agricultural University,South China Agricultural University,South China Agricultural University,South China Agricultural University and South China Agricultural University
Key Words:yellow feather chicken  color model  color difference information  computer vision  image segmentation
Abstract:The first step to identify the sick chicken in the farms by machine vision system is segment of object from images fast and correctly. However, it is a challenge to extract the chicken from pictures because of the complex background. A segmentation method based on the difference of three components of RGB model and HSV model was presented to extract yellow feather broilers from the image. Totally 200 images were taken under the natural environment by using digital cameras and iPhone 6. Totally 30 images were selected from 200 images to setup pixels data sets for the color components analysis. Background and feather data sets included 10 sample areas in each selected image. Each sample area had 10×10 pixels. Comb data sets had three sample areas of each selected image and included 5×5 pixels for each sample area. All data sets were analyzed in the different color models, such as RGB, HSV, L*a*b*. It was found that the value of R, G, B components of the background and the chicken belly was nearly the same or very close while the average value was different. This characteristic was used to abandon the background pixels in the RGB model. Then the remaining part of the image was converted to the HSV color model. The research obtained H component threshold for comb and feather by statistics data sets, respectively. Totally 102 images were processed in the experiment. The result showed that segmentation accuracy of yellow feather broilers from images using the proposed method was 86.3%, which was better than that of L*a*b* color model (78.4%). This method was simple with short calculation time and was suitable for real-time segmentation.

Transactions of the Chinese Society for Agriculture Machinery (CSAM), in charged of China Association for Science and Technology (CAST), sponsored by CSAM and Chinese Academy of Agricultural Mechanization Science(CAAMS), started publication in 1957. It is the earliest interdisciplinary journal in Chinese which combines agricultural and engineering. It always closely grasps the development direction of agriculture engineering disciplines and the published papers represent the highest academic level of agriculture engineering in China. Currently, nearly 8,000 papers have been already published. There are around 3,000 papers contributed to the journal each year, but only around 600 of them will be accepted. Transactions of CSAM focuses on a wide range of agricultural machinery, irrigation, electronics, robotics, agro-products engineering, biological energy, agricultural structures and environment and more. Subjects in Transactions of the CSAM have been embodied by many internationally well-known index systems, such as: EI Compendex, CA, CSA, etc.

   下载PDF阅读器