The newly developed FishCam is used to monitor fish migration especially in fish passes. To avoid time and cost consuming field work for fish pass monitoring, this project aims to develop a semi-automatic monitoring system that enables a continuous observation of fish migration. The FishCam migration monitoring system consists of a detection tunnel and a high resolution camera , which is mainly based on the technology of security cameras. The camera system is recording video clips of migrating fish and drifting particles with a size covering more than 1 – 3% of the number of pixels of the image. The underwater camera is installed in a pyramid stump shaped housing filled with freshwater to keep the influence of turbidity in the fish pass to a minimum. Migration of fish is recorded without contact and stress. The ongoing key challenge is the development of a robust image classification algorithm, which counts, measures and classifies the passing fish. In the first step fish are separated from non-fish moving objects (e.g. foliage and woody debris, shadows and light reflections). To get the best single image of each object for the classification, a “fish benchmark” value was implemented. This benchmark value compares the actual shape of the object with a schematic model of a typical fish species. In its current state, the program is able to detect and track moving objects from the recorded videos. The first classification step is already implemented in the software and performs reasonably well with an accuracy of more than 90%. In step two, the length of the fish can be derived through geometric analysis of images from different view angles. The determination of the fish lengths was tested successfully but still needs to be fully automatized. The final objective of the classification algorithm will be the classification of migrating fish species.