Detecting objects in underwater image sequences and video frames automatically, requires the application of selected algorithms in consecutive steps. Most of these algorithms are controlled by a set of parameters, which need to be calibrated for an optimal detection result. Those parameters determine the effectivity and efficiency of an algorithm and their impact is usually well known. There are however further non-algorithmic impact factors (or hidden parameters), which bias the training of a machine learning system as well as the subsequent detection process and thus need to be well understood and taken into account. In the context of megafauna detection in benthic images, we investigate the effects of some of these parameters on our machine learning based detection system iSIS. The images to be analyzed were taken at the deep-sea, long-term observatory HAUSGARTEN in which five experts labeled seven distinct object classes as an annotation gold standard. We found, that the hidden parameters from imaging as well as the fusion of expert knowledge could partly be compensated and were able to achieve detection performances of 0.67 precision and 0.87 recall. Despite the efforts to compensate the hidden parameters, the detection performance was still varying across the image transect. This poses the potential occurrence of further hidden parameters not taken into account so far. © 2012 IEEE.