Recirculating aquaculture systems (RAS), a land based intensive aquaculture technology, are being adapted globally as a sustainable alternative to wild fishing . Since RAS grow the fish in a controlled environment, precision technologies can be conveniently adapted to improve system performance and reliability and assist growers with important fish management decisions . R ecent advancements in computer vision and artificial intelligence (AI) have significantly improved the reliability, repeatability, and accuracy of the models and drawn interest of the aquaculture industry and research community. The convolutional neural network (CNN) assisted image classification and object detection models are being developed in the aquaculture industry for fish management including feed optimization , biomass and yield estimation, fish health and waste management. However, machine learning approaches are data-intensive and model precision and accuracy primarily depend on the data quality. When imaging underwater, challenges including turbidity, fish density, and distortions caused by the underwater environment are expected to impede feature identification. Therefore, this study was conducted to investigate the effect of number and quality of images, imaging conditions and pre-processing operations on the fish detection accuracy of the object detection model . A n underwater sensing platform was developed with four commercially available imaging sensor s [Raspberry Pi camera ( model: Pi 4 HQ, Raspberry Pi foundation, Cambridge, UK); GoPro (model: HERO9, GoPro, Inc., California, USA ); Oak-D (model: Oak-D Depth AI , Luxonis , Colorado, USA); Ubiquiti security camera (model: G3, Ubiquiti Inc., New York, USA )] customized and deployed in a RAS tank with Rainbow trout. The i mages from all the sensors were first collected with ambient LED lighting at an interval of 5 sec . Later, supplemental LED lighting was added above the tank to acquire the imagery data for comparison with ambient lighting . The acquired images from various imaging sensors in different light conditions were divided in batches of 100 images and annotated as partial and whole fish. The annotated images were segregated into training, validation and test datasets in a ratio of 70:20:10, respectively and utilized to train a custom Yolo V5 model in Roboflow software (Roboflow, Inc., Des Moines, Iowa, USA ) for fish detection . The effect of sensor specific image quality, number of images, light conditions, and image augmentation on fish detection accuracy is being investigated and pertaining results will be presented in terms of precision, mean average precision, and recall .
Keyword: precision aquaculture, deep neural network, artificial intelligence, RAS, machine learning