No abstract

The posture data of ornamental turtle is a quantitative index to evaluate the quality of the turtle. From the young turtle to the adult turtle, the posture data is constantly changing and the quality can also change accordingly. An integrated observation platform is designed and implemented. The automatic extraction of five posture data, i.e., the length of carapace, the width of carapace, the height of carapace, the length of plastron, and the width of plastron, is realized by using OpenCV based computer vision technology. The results of the experiment and the data of artificial measurement were compared and analyzed. The average fitting degree of the two values reached 99.2%. This method can extract the posture data of ornamental turtle quickly and accurately, and then track its growth and development. It will greatly reduce the workload of data collection in the process of ornamental turtle breeding, and effectively improve the accuracy of data collection. At the same time, it will reduce the risk of damage, and have important production and application value.

No abstract

Koi is graceful and colorful. In the process of breeding, monitoring the growth state and predicting the body mass of the broodstock are both important. The broodstock will surface on the water while being feed. At this time, the digital camera captures the feeding state image rapidly. The head and mouth of the broodstock show the semi-spindle shape and bright color significantly which have very high contrast with the water background in the image. Based on the method of OpenCV image visual, feature triangle was defined based on the extracted colorful semi-spindle shape automatically. The projection area of the triangle in the image was computed through the vector graphics calculation by computer. A great deal of measurement data was taken analysis on the correlation between the shape parameters and the body mass of the broodstock by MATLAB. A correlation analysis model was established between the projection area of the feature triangle and the body mass. Through this method, the body mass of the broodstock in the aquaculture pond was estimated automatically. The estimating error of the body mass was lower than 9 percent. This method will reduce the workload of collecting the growth state data during the breeding process of the broodstock greatly. And the method can also improve the accuracy of the body mass estimating effectively, which has important production and application value.

The royal goldfish has high ornamental value and is usually cultured in small aquaculture water, which requires high water quality. In the industry, water viscosity is usually used to measure the quality of water quality. The fresh and suitable water is conducive to the survival and reproduction of the royal goldfish, while the water with excessive viscosity is easy to cause the royal goldfish to get sick or even die. In this paper, the computer vision technology is used to track and detect the bubble group on the surface of the royal goldfish small aquaculture water in real-time, and the time change fitting model of the bubble group covering the water surface area is established, which can directly reflect the change of the bubble burst rate of the small aquaculture water. Based on this, the viscosity level of the small aquaculture water is quantitatively evaluated. The experimental results show that the coefficient a in the fitting model is highly correlated with the viscosity level. This method can evaluate the viscosity of small aquaculture water in real-time and automatically, and send early warning information to aquaculture technicians quickly, which is of great significance to ensure the health and safety of royal goldfish culture.