Aquaculture is difficult to be monitored in real-time due to the influence of vast water area and complex environment. Machine vision uses the machine to replace the human eye to convert the target into image signals and send them to the special image processing system, so as to get the morphological information of the target. Combining machine vision and UAV technology could revolutionize aquaculture. The real-time image processing device installed on the UAV can quickly and accurately identify fish schools or monitor water conditions. This paper explores the application of machine vision in aquaculture UAVs, which is of great significance for the following research.