基于鱼群摄食规律的投饵系统研究

Research on Bait Casting System Based on Feeding Rule of Fish

随着工厂化循环水养殖与海洋养殖业的不断发展,传统的投饵方式因没有合理运用鱼群进食时的参数信息,造成饵料浪费,同时多余的饵料会再次污染水质,为此提出基于鱼群摄食规律的投饵系统研究,从而实现精准的实时投喂。计算机视觉技术作为一项快速、客观、无损的检测方法,已被逐渐用于水产动物视觉属性的测量中,鱼群摄食时的参数信息可通过计算机视觉技术获取。文中提取的参数信息是目标鱼群面积和目标鱼群密集度。运用摄像机采集鱼群摄食图像,利用Lab VIEW对图像进行滤波处理、二值化处理、粒子过滤,提取鱼群个体图像坐标和像素面积,分析参数并改进Kmeans算法以建立目标鱼群密集度模型,结合实时图像处理结果得出的目标鱼群面积跟时间的关系、目标鱼群密集度跟时间的关系构建智能投饵系统,最终利用单片机控制精准投喂。实验结果证明该投饵系统相比于传统投饵系统能够节约饵料,做到更加精准投喂。

With the development of factory recirculating aquaculture and marine aquaculture,the traditional mechanical feeding bait was not rational use of the fish when eating the parameters of information, the excess food will result in food waste and pollute the water quality. Therefore it is necessary to study the precise bait casting system and a bait casting system based on feeding rule of fish is put forward. As a fast, objective and nondestructive detection method, computer vision technology has been used in the measurement of aquatic animal visual properties.The information for fish feeding can be obtained by computer vision techniques. The information extracted in this paper is the target fish area and the target fish density. Using the camera to collect the pictures of fish feeding, the images are filtered, binarized and filtered by the LabVIEW. The image coordinates and area of the fish are extracted, the information are analyzed and the Kmeans algorithm is improved to build the fish-crowd model. The relationship between area and time, the relationship between fish density and time response to the law of fish feeding, and finally use the single-chip to control precision feeding. The bait casting system is used in cage culture in Xiangshan, Zhejiang Province. The experimental results show that the bait casting system can save food and achieve more accurate feeding compared with the traditional bait casting system.