Click on “Download PDF” for the PDF version or on the title for the HTML version.

If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

Abstract. With the increase in the scale and density of aquaculture, the problem of fish diseases is getting more and more serious, resulting in economic losses of 4 billion yuan each year. The practice has proved that vaccination plays an important role in the large-scale and intensive fish industry. To improve the vaccination rate, it is necessary to adjust the injection site in real-time according to the size of the fish when vaccinating spindle-shaped fish. In this paper, grass carp was taken as the research object, the fry length L, width W, thickness T and injection position X, Y were measured, and regression analysis was carried out to determine the optimal injection site prediction model. Finally, an image acquisition device was designed, and the predicted length L and width W of the fry were experimentally obtained. The results showed that the maximum error between the predicted injection site and the actual injection site was less than 6%, which could be applied to actual production within the allowable error range.