基于计算机视觉和非参数估计的蟹苗数量估算方法研究

Study on total estimation method of crab larvae based on computer vision and non-parametric estimation

养殖池内蟹苗的数量估计在蟹苗养殖中有着重要意义.但现有的数量估计方法操作复杂且实用性不强,因此提出一种基于计算机视觉和非参数估计的蟹苗数量估算方法.首先在养殖池内分水层采集视频,通过背景建模得到前景图像,并使用分水岭算法和轮廓提取得到视频中的蟹苗数量,并作为样本数据,然后通过核密度估计得出概率密度函数,最后结合该函数和样本数据估算出池内蟹苗数量.结果表明,该方法对于容积约为1000L、蟹苗密度100～160只/L的小型蟹苗养殖池,估算蟹苗数量的平均正确率为82.14%.研究表明,采用该方法不仅可以解决采集视频过程的操作繁琐、幼苗转移的问题,而且能够避免图像处理过程中部分背景杂质的干扰.该方法还可以推广到虾苗和鱼苗等生物的幼苗估计,具有良好的通用性和可行性.

Crab larvae total estimation is of great significance in crab breeding; however, the existing totalestimation methods are complicated and unpractical. Therefore, an estimation method based on computer visionand non-parametric estimation was presented in this paper. Firstly, the videos were captured at different layersof the breeding pond, the foreground image was obtained by using image processing, and the number of crabsin the video was calculated by watershed algorithm and contour extraction to be used as the sample data. Thenthe probability density function was obtained by kernel density estimation. Finally, combining with the functionand sample data, the total number of crabs was estimated. The results showed that the average correct rate ofthe method was 82.14% when the density of crab was between 100 and 160 individuals per liter for small crabponds with a capacity of 1 000 L. The study not only solved the complicated operation and crabs transferringproblems in capturing video, but also solved the interference of background impurities in the image processing.The method could also be extended to the estimation of many other species such as shrimps and fish fries, andhas good versatility and feasibility.