Fish tracking in vertical slot fishways using computer vision techniques

Abstract

Vertical slot fishways are hydraulic structures which allow the upstream migration of fish through obstructions in rivers. The appropriate design of these devices should take into account the behavior and biological requirements of the target fish species. However, little is known at the present time about fish behavior in these artificial conditions, which hinders the development of more effective fishway design criteria. In this work, an efficient technique to study fish trajectories and behavior in vertical slot fishways is proposed. It uses computer vision techniques to analyze images collected from a camera system and effectively track fish inside the fishway. Edge and region analysis algorithms are employed to detect fish in extreme image conditions and Kalman filtering is used to track fish along time. The proposed solution has been extensively validated through several experiments, obtaining promising results which may help to improve the design of fish passage devices.

Pool-Type Fishway Design for a Potamodromous Cyprinid in the Iberian Peninsula: The Iberian Barbel—Synthesis and Future Directions

“…In the studied conducted with VSF [90], efficiency of passage was size-related, as 74.1% (n = 60) of the individuals greater than 10 cm TL were able to ascend an experimental VSF with a flow of 100 L·s −1 , whereas only half of them (49.2%, n = 31) were only able to do it with a 250 L·s −1 flow. Similar results were also reported by other authors on the same experimental device [80], who found passage success was the lowest (33.3%) for the smallest individuals (10-15 cm TL), increasing with increasing of fish size-50% for individuals of 15-20 cm TL and further to 80.0% for individuals of 20-25 cm TL-and then decreased (41.2%) for the largest individuals (>25 cm TL). In this study, using computer vision techniques [80], fish tracking also showed that individuals avoided high-velocity areas and mainly used the recirculation regions in the upstream part of the pools, in which velocity and turbulence were lower, to move within the pools and for resting before ascending through the high velocity areas of the slots.…”

“…Similar results were also reported by other authors on the same experimental device [80], who found passage success was the lowest (33.3%) for the smallest individuals (10-15 cm TL), increasing with increasing of fish size-50% for individuals of 15-20 cm TL and further to 80.0% for individuals of 20-25 cm TL-and then decreased (41.2%) for the largest individuals (>25 cm TL). In this study, using computer vision techniques [80], fish tracking also showed that individuals avoided high-velocity areas and mainly used the recirculation regions in the upstream part of the pools, in which velocity and turbulence were lower, to move within the pools and for resting before ascending through the high velocity areas of the slots. This preference of barbel for lower velocity and turbulence levels had also been observed for the NOF and OF designs (see previous sections) and is naturally expected since energy expenditures to maintain fish position are typically lower in such areas [104].…”

“…Velocity and turbulence levels in the fishway must thus be compatible with the fish swimming capabilities and behavior [34,78]. Fishways should also offer resting areas that allow fish to recover [79,80]. This is particularly important for species with weak swimming capabilities and/or in long fishways.…”

“…In the former, the VSF, which encompassed nine pools (2.4 m × 1.6 m) separated by 20 cm wide slots, was tested with bottom substrates. The remaining studies (n = 7, 87.5%) were all conducted under laboratory conditions, with the VSF having been tested for slopes ranging from 7.5% to 8.5%, with either 6 (n = 5, 71.4% [69,76,[93][94][95]) or 11 (n = 2, 28.6% [80,90]) pools (1.85 m-1.9 m × 1.0 m-1.5 m), separated by 10-and 27-cm wide slots, respectively. Of these lab studies, two (28.6%) [93,95] employed a variant of VSF, the multi-slot fishway (MSF [97]), featuring two consecutive slots per pool.…”

FishPath: aplicación informática de diseño de escalas de peces de hendidura vertical

“…Entre ellas, cabe destacar el desarrollo de técnicas de visión artificial para el seguimiento de peces dentro de estos dispositivos (Rodríguez et al, 2015). Con estas nuevas aproximaciones se pretende contribuir a evaluar la respuesta de los peces a diferentes características hidráulicas, a definir los posibles factores clave en el remonte y a mejorar los modelos existentes para predecir la eficiencia de los dispositivos.…”