Ground imagery,which produces large amounts of valuable data at high frequencies, is increasingly used by fluvialgeomorphologists to survey and understand processes.While such technology provides immense quantitiesof information, it can be challenging to analyze and requires automatization and associated development of newmethodologies. This paper presents a new approach to automate the processing of image analysis to monitorwood delivery from the upstream Rhône River (France). The Génissiat dam is used as an observation window;all pieces of wood coming from the catchment are trapped here, hence a wood raft accumulates over time. In2011, we installed an Axis 211W camera to acquire oblique images of the reservoir every 10 min with the goalof automatically detecting a wood raft area, in order to transform it to wood weight (t) and flux (t/d). Themethodologywe developed is based on random forest classification to detect the wood raft surface over time, whichprovided a good classification rate of 97.2%. Based on 14 mechanical wood extractions that included weight ofwood removed each time, conducted during the survey period, we established a relationship between woodweight and wood raft surface area observed just before the extraction (R2 = 0.93). We found that using suchtechniques to continuously monitor wood flux is difficult because the raft undergoes very significant changesthrough time in terms of density, with a very high interday and intraday variability. Misclassifications causedby changes in weather conditions can be mitigated as well as errors from variation in pixel resolution (owingto camera position or window size), but a set of effects on raft density and mobility must still be explored(e.g., damoperation effects,wind on the reservoir surface). At this stage, only peak flow contribution towood deliverycan bewell calculated, but determining an accurate, continuous series ofwood flux is not possible. Severalrecommendations are made in terms of maximizing the potential benefit of such monitoring.