Resumen
The optimal water flow in fish breeding tanks is one of the crucial elements necessary for the well-being and proper growth of fish, such as salmon or trout. Considering the round tanks and the uneven distribution of water-flow velocity, ensuring a nearly optimal flow is an important task that may be performed using various sensors installed to monitor the water flow. Nevertheless, observing the rapid development of video analysis methods and considering the increasing availability of relatively cheap cameras, the use of video feedback has become an interesting alternative that limits the number of sensors inside the water tanks in accordance with the requirements of fish breeders. In this paper, an analysis of the use of optical flow algorithms for this purpose is performed and an estimation method based on their features is proposed. The results of the flow estimation using the proposed method are verified experimentally and compared with the measurement results obtained using the professional water-flow meter, demonstrating a high correlation, exceeding 0.9, confirming the proposed solution as a good alternative in comparison to the use of expensive sensors and meters.